Index: linux-4.9.20-rt16/Documentation/sysrq.txt
===================================================================
--- linux-4.9.20-rt16.orig/Documentation/sysrq.txt
+++ linux-4.9.20-rt16/Documentation/sysrq.txt
@@ -59,10 +59,17 @@ On PowerPC - Press 'ALT - Print Screen (
 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
Index: linux-4.9.20-rt16/Documentation/trace/histograms.txt
===================================================================
--- /dev/null
+++ linux-4.9.20-rt16/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.
Index: linux-4.9.20-rt16/MAINTAINERS
===================================================================
--- linux-4.9.20-rt16.orig/MAINTAINERS
+++ linux-4.9.20-rt16/MAINTAINERS
@@ -5196,6 +5196,23 @@ F:	fs/fuse/
 F:	include/uapi/linux/fuse.h
 F:	Documentation/filesystems/fuse.txt
 
+FUTEX SUBSYSTEM
+M:	Thomas Gleixner <tglx@linutronix.de>
+M:	Ingo Molnar <mingo@redhat.com>
+R:	Peter Zijlstra <peterz@infradead.org>
+R:	Darren Hart <dvhart@infradead.org>
+L:	linux-kernel@vger.kernel.org
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking/core
+S:	Maintained
+F:	kernel/futex.c
+F:	kernel/futex_compat.c
+F:	include/asm-generic/futex.h
+F:	include/linux/futex.h
+F:	include/uapi/linux/futex.h
+F:	tools/testing/selftests/futex/
+F:	tools/perf/bench/futex*
+F:	Documentation/*futex*
+
 FUTURE DOMAIN TMC-16x0 SCSI DRIVER (16-bit)
 M:	Rik Faith <faith@cs.unc.edu>
 L:	linux-scsi@vger.kernel.org
Index: linux-4.9.20-rt16/arch/Kconfig
===================================================================
--- linux-4.9.20-rt16.orig/arch/Kconfig
+++ linux-4.9.20-rt16/arch/Kconfig
@@ -9,6 +9,7 @@ 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
@@ -52,6 +53,7 @@ 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
Index: linux-4.9.20-rt16/arch/arm/Kconfig
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm/Kconfig
+++ linux-4.9.20-rt16/arch/arm/Kconfig
@@ -36,7 +36,7 @@ config ARM
 	select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
 	select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
 	select HAVE_ARCH_HARDENED_USERCOPY
-	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
+	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU && !PREEMPT_RT_BASE
 	select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
 	select HAVE_ARCH_SECCOMP_FILTER if (AEABI && !OABI_COMPAT)
@@ -75,6 +75,7 @@ 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
Index: linux-4.9.20-rt16/arch/arm/include/asm/irq.h
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm/include/asm/irq.h
+++ linux-4.9.20-rt16/arch/arm/include/asm/irq.h
@@ -22,6 +22,8 @@
 #endif
 
 #ifndef __ASSEMBLY__
+#include <linux/cpumask.h>
+
 struct irqaction;
 struct pt_regs;
 extern void migrate_irqs(void);
Index: linux-4.9.20-rt16/arch/arm/include/asm/switch_to.h
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm/include/asm/switch_to.h
+++ linux-4.9.20-rt16/arch/arm/include/asm/switch_to.h
@@ -3,6 +3,13 @@
 
 #include <linux/thread_info.h>
 
+#if defined CONFIG_PREEMPT_RT_FULL && defined CONFIG_HIGHMEM
+void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p);
+#else
+static inline void
+switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) { }
+#endif
+
 /*
  * For v7 SMP cores running a preemptible kernel we may be pre-empted
  * during a TLB maintenance operation, so execute an inner-shareable dsb
@@ -25,6 +32,7 @@ extern struct task_struct *__switch_to(s
 #define switch_to(prev,next,last)					\
 do {									\
 	__complete_pending_tlbi();					\
+	switch_kmaps(prev, next);					\
 	last = __switch_to(prev,task_thread_info(prev), task_thread_info(next));	\
 } while (0)
 
Index: linux-4.9.20-rt16/arch/arm/include/asm/thread_info.h
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm/include/asm/thread_info.h
+++ linux-4.9.20-rt16/arch/arm/include/asm/thread_info.h
@@ -49,6 +49,7 @@ struct cpu_context_save {
 struct thread_info {
 	unsigned long		flags;		/* low level flags */
 	int			preempt_count;	/* 0 => preemptable, <0 => bug */
+	int			preempt_lazy_count; /* 0 => preemptable, <0 => bug */
 	mm_segment_t		addr_limit;	/* address limit */
 	struct task_struct	*task;		/* main task structure */
 	__u32			cpu;		/* cpu */
@@ -142,7 +143,8 @@ extern int vfp_restore_user_hwstate(stru
 #define TIF_SYSCALL_TRACE	4	/* syscall trace active */
 #define TIF_SYSCALL_AUDIT	5	/* syscall auditing active */
 #define TIF_SYSCALL_TRACEPOINT	6	/* syscall tracepoint instrumentation */
-#define TIF_SECCOMP		7	/* seccomp syscall filtering active */
+#define TIF_SECCOMP		8	/* seccomp syscall filtering active */
+#define TIF_NEED_RESCHED_LAZY	7
 
 #define TIF_NOHZ		12	/* in adaptive nohz mode */
 #define TIF_USING_IWMMXT	17
@@ -152,6 +154,7 @@ extern int vfp_restore_user_hwstate(stru
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
+#define _TIF_NEED_RESCHED_LAZY	(1 << TIF_NEED_RESCHED_LAZY)
 #define _TIF_UPROBE		(1 << TIF_UPROBE)
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
@@ -167,7 +170,8 @@ extern int vfp_restore_user_hwstate(stru
  * Change these and you break ASM code in entry-common.S
  */
 #define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
-				 _TIF_NOTIFY_RESUME | _TIF_UPROBE)
+				 _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
+				 _TIF_NEED_RESCHED_LAZY)
 
 #endif /* __KERNEL__ */
 #endif /* __ASM_ARM_THREAD_INFO_H */
Index: linux-4.9.20-rt16/arch/arm/kernel/asm-offsets.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm/kernel/asm-offsets.c
+++ linux-4.9.20-rt16/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));
+  DEFINE(TI_PREEMPT_LAZY,	offsetof(struct thread_info, preempt_lazy_count));
   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));
Index: linux-4.9.20-rt16/arch/arm/kernel/entry-armv.S
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm/kernel/entry-armv.S
+++ linux-4.9.20-rt16/arch/arm/kernel/entry-armv.S
@@ -220,11 +220,18 @@ __irq_svc:
 
 #ifdef CONFIG_PREEMPT
 	ldr	r8, [tsk, #TI_PREEMPT]		@ get preempt count
-	ldr	r0, [tsk, #TI_FLAGS]		@ get flags
 	teq	r8, #0				@ if preempt count != 0
+	bne	1f				@ return from exeption
+	ldr	r0, [tsk, #TI_FLAGS]		@ get flags
+	tst	r0, #_TIF_NEED_RESCHED		@ if NEED_RESCHED is set
+	blne	svc_preempt			@ preempt!
+
+	ldr	r8, [tsk, #TI_PREEMPT_LAZY]	@ get preempt lazy count
+	teq	r8, #0				@ if preempt lazy count != 0
 	movne	r0, #0				@ force flags to 0
-	tst	r0, #_TIF_NEED_RESCHED
+	tst	r0, #_TIF_NEED_RESCHED_LAZY
 	blne	svc_preempt
+1:
 #endif
 
 	svc_exit r5, irq = 1			@ return from exception
@@ -239,8 +246,14 @@ 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
+	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
 
 __und_fault:
Index: linux-4.9.20-rt16/arch/arm/kernel/entry-common.S
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm/kernel/entry-common.S
+++ linux-4.9.20-rt16/arch/arm/kernel/entry-common.S
@@ -36,7 +36,9 @@ ret_fast_syscall:
  UNWIND(.cantunwind	)
 	disable_irq_notrace			@ disable interrupts
 	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
-	tst	r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
+	tst	r1, #((_TIF_SYSCALL_WORK | _TIF_WORK_MASK) & ~_TIF_SECCOMP)
+	bne	fast_work_pending
+	tst	r1, #_TIF_SECCOMP
 	bne	fast_work_pending
 
 	/* perform architecture specific actions before user return */
@@ -62,8 +64,11 @@ ret_fast_syscall:
 	str	r0, [sp, #S_R0 + S_OFF]!	@ save returned r0
 	disable_irq_notrace			@ disable interrupts
 	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
-	tst	r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
+	tst	r1, #((_TIF_SYSCALL_WORK | _TIF_WORK_MASK) & ~_TIF_SECCOMP)
+	bne 	do_slower_path
+	tst	r1, #_TIF_SECCOMP
 	beq	no_work_pending
+do_slower_path:
  UNWIND(.fnend		)
 ENDPROC(ret_fast_syscall)
 
Index: linux-4.9.20-rt16/arch/arm/kernel/patch.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm/kernel/patch.c
+++ linux-4.9.20-rt16/arch/arm/kernel/patch.c
@@ -15,7 +15,7 @@ struct patch {
 	unsigned int insn;
 };
 
-static DEFINE_SPINLOCK(patch_lock);
+static DEFINE_RAW_SPINLOCK(patch_lock);
 
 static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags)
 	__acquires(&patch_lock)
@@ -32,7 +32,7 @@ static void __kprobes *patch_map(void *a
 		return addr;
 
 	if (flags)
-		spin_lock_irqsave(&patch_lock, *flags);
+		raw_spin_lock_irqsave(&patch_lock, *flags);
 	else
 		__acquire(&patch_lock);
 
@@ -47,7 +47,7 @@ static void __kprobes patch_unmap(int fi
 	clear_fixmap(fixmap);
 
 	if (flags)
-		spin_unlock_irqrestore(&patch_lock, *flags);
+		raw_spin_unlock_irqrestore(&patch_lock, *flags);
 	else
 		__release(&patch_lock);
 }
Index: linux-4.9.20-rt16/arch/arm/kernel/process.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm/kernel/process.c
+++ linux-4.9.20-rt16/arch/arm/kernel/process.c
@@ -322,6 +322,30 @@ unsigned long arch_randomize_brk(struct
 }
 
 #ifdef CONFIG_MMU
+/*
+ * CONFIG_SPLIT_PTLOCK_CPUS results in a page->ptl lock.  If the lock is not
+ * initialized by pgtable_page_ctor() then a coredump of the vector page will
+ * fail.
+ */
+static int __init vectors_user_mapping_init_page(void)
+{
+	struct page *page;
+	unsigned long addr = 0xffff0000;
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	pgd = pgd_offset_k(addr);
+	pud = pud_offset(pgd, addr);
+	pmd = pmd_offset(pud, addr);
+	page = pmd_page(*(pmd));
+
+	pgtable_page_ctor(page);
+
+	return 0;
+}
+late_initcall(vectors_user_mapping_init_page);
+
 #ifdef CONFIG_KUSER_HELPERS
 /*
  * The vectors page is always readable from user space for the
Index: linux-4.9.20-rt16/arch/arm/kernel/signal.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm/kernel/signal.c
+++ linux-4.9.20-rt16/arch/arm/kernel/signal.c
@@ -572,7 +572,8 @@ do_work_pending(struct pt_regs *regs, un
 	 */
 	trace_hardirqs_off();
 	do {
-		if (likely(thread_flags & _TIF_NEED_RESCHED)) {
+		if (likely(thread_flags & (_TIF_NEED_RESCHED |
+					   _TIF_NEED_RESCHED_LAZY))) {
 			schedule();
 		} else {
 			if (unlikely(!user_mode(regs)))
Index: linux-4.9.20-rt16/arch/arm/kernel/smp.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm/kernel/smp.c
+++ linux-4.9.20-rt16/arch/arm/kernel/smp.c
@@ -234,8 +234,6 @@ int __cpu_disable(void)
 	flush_cache_louis();
 	local_flush_tlb_all();
 
-	clear_tasks_mm_cpumask(cpu);
-
 	return 0;
 }
 
@@ -251,6 +249,9 @@ void __cpu_die(unsigned int cpu)
 		pr_err("CPU%u: cpu didn't die\n", cpu);
 		return;
 	}
+
+	clear_tasks_mm_cpumask(cpu);
+
 	pr_notice("CPU%u: shutdown\n", cpu);
 
 	/*
Index: linux-4.9.20-rt16/arch/arm/kernel/unwind.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm/kernel/unwind.c
+++ linux-4.9.20-rt16/arch/arm/kernel/unwind.c
@@ -93,7 +93,7 @@ extern const struct unwind_idx __start_u
 static const struct unwind_idx *__origin_unwind_idx;
 extern const struct unwind_idx __stop_unwind_idx[];
 
-static DEFINE_SPINLOCK(unwind_lock);
+static DEFINE_RAW_SPINLOCK(unwind_lock);
 static LIST_HEAD(unwind_tables);
 
 /* Convert a prel31 symbol to an absolute address */
@@ -201,7 +201,7 @@ static const struct unwind_idx *unwind_f
 		/* module unwind tables */
 		struct unwind_table *table;
 
-		spin_lock_irqsave(&unwind_lock, flags);
+		raw_spin_lock_irqsave(&unwind_lock, flags);
 		list_for_each_entry(table, &unwind_tables, list) {
 			if (addr >= table->begin_addr &&
 			    addr < table->end_addr) {
@@ -213,7 +213,7 @@ static const struct unwind_idx *unwind_f
 				break;
 			}
 		}
-		spin_unlock_irqrestore(&unwind_lock, flags);
+		raw_spin_unlock_irqrestore(&unwind_lock, flags);
 	}
 
 	pr_debug("%s: idx = %p\n", __func__, idx);
@@ -529,9 +529,9 @@ struct unwind_table *unwind_table_add(un
 	tab->begin_addr = text_addr;
 	tab->end_addr = text_addr + text_size;
 
-	spin_lock_irqsave(&unwind_lock, flags);
+	raw_spin_lock_irqsave(&unwind_lock, flags);
 	list_add_tail(&tab->list, &unwind_tables);
-	spin_unlock_irqrestore(&unwind_lock, flags);
+	raw_spin_unlock_irqrestore(&unwind_lock, flags);
 
 	return tab;
 }
@@ -543,9 +543,9 @@ void unwind_table_del(struct unwind_tabl
 	if (!tab)
 		return;
 
-	spin_lock_irqsave(&unwind_lock, flags);
+	raw_spin_lock_irqsave(&unwind_lock, flags);
 	list_del(&tab->list);
-	spin_unlock_irqrestore(&unwind_lock, flags);
+	raw_spin_unlock_irqrestore(&unwind_lock, flags);
 
 	kfree(tab);
 }
Index: linux-4.9.20-rt16/arch/arm/kvm/arm.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm/kvm/arm.c
+++ linux-4.9.20-rt16/arch/arm/kvm/arm.c
@@ -619,7 +619,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_v
 		 * involves poking the GIC, which must be done in a
 		 * non-preemptible context.
 		 */
-		preempt_disable();
+		migrate_disable();
 		kvm_pmu_flush_hwstate(vcpu);
 		kvm_timer_flush_hwstate(vcpu);
 		kvm_vgic_flush_hwstate(vcpu);
@@ -640,7 +640,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_v
 			kvm_pmu_sync_hwstate(vcpu);
 			kvm_timer_sync_hwstate(vcpu);
 			kvm_vgic_sync_hwstate(vcpu);
-			preempt_enable();
+			migrate_enable();
 			continue;
 		}
 
@@ -696,7 +696,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_v
 
 		kvm_vgic_sync_hwstate(vcpu);
 
-		preempt_enable();
+		migrate_enable();
 
 		ret = handle_exit(vcpu, run, ret);
 	}
Index: linux-4.9.20-rt16/arch/arm/mach-exynos/platsmp.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm/mach-exynos/platsmp.c
+++ linux-4.9.20-rt16/arch/arm/mach-exynos/platsmp.c
@@ -229,7 +229,7 @@ static void __iomem *scu_base_addr(void)
 	return (void __iomem *)(S5P_VA_SCU);
 }
 
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
 
 static void exynos_secondary_init(unsigned int cpu)
 {
@@ -242,8 +242,8 @@ static void exynos_secondary_init(unsign
 	/*
 	 * Synchronise with the boot thread.
 	 */
-	spin_lock(&boot_lock);
-	spin_unlock(&boot_lock);
+	raw_spin_lock(&boot_lock);
+	raw_spin_unlock(&boot_lock);
 }
 
 int exynos_set_boot_addr(u32 core_id, unsigned long boot_addr)
@@ -307,7 +307,7 @@ static int exynos_boot_secondary(unsigne
 	 * Set synchronisation state between this boot processor
 	 * and the secondary one
 	 */
-	spin_lock(&boot_lock);
+	raw_spin_lock(&boot_lock);
 
 	/*
 	 * The secondary processor is waiting to be released from
@@ -334,7 +334,7 @@ static int exynos_boot_secondary(unsigne
 
 		if (timeout == 0) {
 			printk(KERN_ERR "cpu1 power enable failed");
-			spin_unlock(&boot_lock);
+			raw_spin_unlock(&boot_lock);
 			return -ETIMEDOUT;
 		}
 	}
@@ -380,7 +380,7 @@ static int exynos_boot_secondary(unsigne
 	 * calibrations, then wait for it to finish
 	 */
 fail:
-	spin_unlock(&boot_lock);
+	raw_spin_unlock(&boot_lock);
 
 	return pen_release != -1 ? ret : 0;
 }
Index: linux-4.9.20-rt16/arch/arm/mach-hisi/platmcpm.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm/mach-hisi/platmcpm.c
+++ linux-4.9.20-rt16/arch/arm/mach-hisi/platmcpm.c
@@ -61,7 +61,7 @@
 
 static void __iomem *sysctrl, *fabric;
 static int hip04_cpu_table[HIP04_MAX_CLUSTERS][HIP04_MAX_CPUS_PER_CLUSTER];
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
 static u32 fabric_phys_addr;
 /*
  * [0]: bootwrapper physical address
@@ -113,7 +113,7 @@ static int hip04_boot_secondary(unsigned
 	if (cluster >= HIP04_MAX_CLUSTERS || cpu >= HIP04_MAX_CPUS_PER_CLUSTER)
 		return -EINVAL;
 
-	spin_lock_irq(&boot_lock);
+	raw_spin_lock_irq(&boot_lock);
 
 	if (hip04_cpu_table[cluster][cpu])
 		goto out;
@@ -147,7 +147,7 @@ static int hip04_boot_secondary(unsigned
 
 out:
 	hip04_cpu_table[cluster][cpu]++;
-	spin_unlock_irq(&boot_lock);
+	raw_spin_unlock_irq(&boot_lock);
 
 	return 0;
 }
@@ -162,11 +162,11 @@ static void hip04_cpu_die(unsigned int l
 	cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
 	cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
 
-	spin_lock(&boot_lock);
+	raw_spin_lock(&boot_lock);
 	hip04_cpu_table[cluster][cpu]--;
 	if (hip04_cpu_table[cluster][cpu] == 1) {
 		/* A power_up request went ahead of us. */
-		spin_unlock(&boot_lock);
+		raw_spin_unlock(&boot_lock);
 		return;
 	} else if (hip04_cpu_table[cluster][cpu] > 1) {
 		pr_err("Cluster %d CPU%d boots multiple times\n", cluster, cpu);
@@ -174,7 +174,7 @@ static void hip04_cpu_die(unsigned int l
 	}
 
 	last_man = hip04_cluster_is_down(cluster);
-	spin_unlock(&boot_lock);
+	raw_spin_unlock(&boot_lock);
 	if (last_man) {
 		/* Since it's Cortex A15, disable L2 prefetching. */
 		asm volatile(
@@ -203,7 +203,7 @@ static int hip04_cpu_kill(unsigned int l
 	       cpu >= HIP04_MAX_CPUS_PER_CLUSTER);
 
 	count = TIMEOUT_MSEC / POLL_MSEC;
-	spin_lock_irq(&boot_lock);
+	raw_spin_lock_irq(&boot_lock);
 	for (tries = 0; tries < count; tries++) {
 		if (hip04_cpu_table[cluster][cpu])
 			goto err;
@@ -211,10 +211,10 @@ static int hip04_cpu_kill(unsigned int l
 		data = readl_relaxed(sysctrl + SC_CPU_RESET_STATUS(cluster));
 		if (data & CORE_WFI_STATUS(cpu))
 			break;
-		spin_unlock_irq(&boot_lock);
+		raw_spin_unlock_irq(&boot_lock);
 		/* Wait for clean L2 when the whole cluster is down. */
 		msleep(POLL_MSEC);
-		spin_lock_irq(&boot_lock);
+		raw_spin_lock_irq(&boot_lock);
 	}
 	if (tries >= count)
 		goto err;
@@ -231,10 +231,10 @@ static int hip04_cpu_kill(unsigned int l
 		goto err;
 	if (hip04_cluster_is_down(cluster))
 		hip04_set_snoop_filter(cluster, 0);
-	spin_unlock_irq(&boot_lock);
+	raw_spin_unlock_irq(&boot_lock);
 	return 1;
 err:
-	spin_unlock_irq(&boot_lock);
+	raw_spin_unlock_irq(&boot_lock);
 	return 0;
 }
 #endif
Index: linux-4.9.20-rt16/arch/arm/mach-omap2/omap-smp.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm/mach-omap2/omap-smp.c
+++ linux-4.9.20-rt16/arch/arm/mach-omap2/omap-smp.c
@@ -64,7 +64,7 @@ static const struct omap_smp_config omap
 	.startup_addr = omap5_secondary_startup,
 };
 
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
 
 void __iomem *omap4_get_scu_base(void)
 {
@@ -131,8 +131,8 @@ static void omap4_secondary_init(unsigne
 	/*
 	 * Synchronise with the boot thread.
 	 */
-	spin_lock(&boot_lock);
-	spin_unlock(&boot_lock);
+	raw_spin_lock(&boot_lock);
+	raw_spin_unlock(&boot_lock);
 }
 
 static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle)
@@ -146,7 +146,7 @@ static int omap4_boot_secondary(unsigned
 	 * Set synchronisation state between this boot processor
 	 * and the secondary one
 	 */
-	spin_lock(&boot_lock);
+	raw_spin_lock(&boot_lock);
 
 	/*
 	 * Update the AuxCoreBoot0 with boot state for secondary core.
@@ -223,7 +223,7 @@ static int omap4_boot_secondary(unsigned
 	 * Now the secondary core is starting up let it run its
 	 * calibrations, then wait for it to finish
 	 */
-	spin_unlock(&boot_lock);
+	raw_spin_unlock(&boot_lock);
 
 	return 0;
 }
Index: linux-4.9.20-rt16/arch/arm/mach-prima2/platsmp.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm/mach-prima2/platsmp.c
+++ linux-4.9.20-rt16/arch/arm/mach-prima2/platsmp.c
@@ -22,7 +22,7 @@
 
 static void __iomem *clk_base;
 
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
 
 static void sirfsoc_secondary_init(unsigned int cpu)
 {
@@ -36,8 +36,8 @@ static void sirfsoc_secondary_init(unsig
 	/*
 	 * Synchronise with the boot thread.
 	 */
-	spin_lock(&boot_lock);
-	spin_unlock(&boot_lock);
+	raw_spin_lock(&boot_lock);
+	raw_spin_unlock(&boot_lock);
 }
 
 static const struct of_device_id clk_ids[]  = {
@@ -75,7 +75,7 @@ static int sirfsoc_boot_secondary(unsign
 	/* make sure write buffer is drained */
 	mb();
 
-	spin_lock(&boot_lock);
+	raw_spin_lock(&boot_lock);
 
 	/*
 	 * The secondary processor is waiting to be released from
@@ -107,7 +107,7 @@ static int sirfsoc_boot_secondary(unsign
 	 * now the secondary core is starting up let it run its
 	 * calibrations, then wait for it to finish
 	 */
-	spin_unlock(&boot_lock);
+	raw_spin_unlock(&boot_lock);
 
 	return pen_release != -1 ? -ENOSYS : 0;
 }
Index: linux-4.9.20-rt16/arch/arm/mach-qcom/platsmp.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm/mach-qcom/platsmp.c
+++ linux-4.9.20-rt16/arch/arm/mach-qcom/platsmp.c
@@ -46,7 +46,7 @@
 
 extern void secondary_startup_arm(void);
 
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
 
 #ifdef CONFIG_HOTPLUG_CPU
 static void qcom_cpu_die(unsigned int cpu)
@@ -60,8 +60,8 @@ static void qcom_secondary_init(unsigned
 	/*
 	 * Synchronise with the boot thread.
 	 */
-	spin_lock(&boot_lock);
-	spin_unlock(&boot_lock);
+	raw_spin_lock(&boot_lock);
+	raw_spin_unlock(&boot_lock);
 }
 
 static int scss_release_secondary(unsigned int cpu)
@@ -284,7 +284,7 @@ static int qcom_boot_secondary(unsigned
 	 * set synchronisation state between this boot processor
 	 * and the secondary one
 	 */
-	spin_lock(&boot_lock);
+	raw_spin_lock(&boot_lock);
 
 	/*
 	 * Send the secondary CPU a soft interrupt, thereby causing
@@ -297,7 +297,7 @@ static int qcom_boot_secondary(unsigned
 	 * now the secondary core is starting up let it run its
 	 * calibrations, then wait for it to finish
 	 */
-	spin_unlock(&boot_lock);
+	raw_spin_unlock(&boot_lock);
 
 	return ret;
 }
Index: linux-4.9.20-rt16/arch/arm/mach-spear/platsmp.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm/mach-spear/platsmp.c
+++ linux-4.9.20-rt16/arch/arm/mach-spear/platsmp.c
@@ -32,7 +32,7 @@ static void write_pen_release(int val)
 	sync_cache_w(&pen_release);
 }
 
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
 
 static void __iomem *scu_base = IOMEM(VA_SCU_BASE);
 
@@ -47,8 +47,8 @@ static void spear13xx_secondary_init(uns
 	/*
 	 * Synchronise with the boot thread.
 	 */
-	spin_lock(&boot_lock);
-	spin_unlock(&boot_lock);
+	raw_spin_lock(&boot_lock);
+	raw_spin_unlock(&boot_lock);
 }
 
 static int spear13xx_boot_secondary(unsigned int cpu, struct task_struct *idle)
@@ -59,7 +59,7 @@ static int spear13xx_boot_secondary(unsi
 	 * set synchronisation state between this boot processor
 	 * and the secondary one
 	 */
-	spin_lock(&boot_lock);
+	raw_spin_lock(&boot_lock);
 
 	/*
 	 * The secondary processor is waiting to be released from
@@ -84,7 +84,7 @@ static int spear13xx_boot_secondary(unsi
 	 * now the secondary core is starting up let it run its
 	 * calibrations, then wait for it to finish
 	 */
-	spin_unlock(&boot_lock);
+	raw_spin_unlock(&boot_lock);
 
 	return pen_release != -1 ? -ENOSYS : 0;
 }
Index: linux-4.9.20-rt16/arch/arm/mach-sti/platsmp.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm/mach-sti/platsmp.c
+++ linux-4.9.20-rt16/arch/arm/mach-sti/platsmp.c
@@ -35,7 +35,7 @@ static void write_pen_release(int val)
 	sync_cache_w(&pen_release);
 }
 
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
 
 static void sti_secondary_init(unsigned int cpu)
 {
@@ -48,8 +48,8 @@ static void sti_secondary_init(unsigned
 	/*
 	 * Synchronise with the boot thread.
 	 */
-	spin_lock(&boot_lock);
-	spin_unlock(&boot_lock);
+	raw_spin_lock(&boot_lock);
+	raw_spin_unlock(&boot_lock);
 }
 
 static int sti_boot_secondary(unsigned int cpu, struct task_struct *idle)
@@ -60,7 +60,7 @@ static int sti_boot_secondary(unsigned i
 	 * set synchronisation state between this boot processor
 	 * and the secondary one
 	 */
-	spin_lock(&boot_lock);
+	raw_spin_lock(&boot_lock);
 
 	/*
 	 * The secondary processor is waiting to be released from
@@ -91,7 +91,7 @@ static int sti_boot_secondary(unsigned i
 	 * now the secondary core is starting up let it run its
 	 * calibrations, then wait for it to finish
 	 */
-	spin_unlock(&boot_lock);
+	raw_spin_unlock(&boot_lock);
 
 	return pen_release != -1 ? -ENOSYS : 0;
 }
Index: linux-4.9.20-rt16/arch/arm/mm/fault.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm/mm/fault.c
+++ linux-4.9.20-rt16/arch/arm/mm/fault.c
@@ -430,6 +430,9 @@ do_translation_fault(unsigned long addr,
 	if (addr < TASK_SIZE)
 		return do_page_fault(addr, fsr, regs);
 
+	if (interrupts_enabled(regs))
+		local_irq_enable();
+
 	if (user_mode(regs))
 		goto bad_area;
 
@@ -497,6 +500,9 @@ do_translation_fault(unsigned long addr,
 static int
 do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 {
+	if (interrupts_enabled(regs))
+		local_irq_enable();
+
 	do_bad_area(addr, fsr, regs);
 	return 0;
 }
Index: linux-4.9.20-rt16/arch/arm/mm/highmem.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm/mm/highmem.c
+++ linux-4.9.20-rt16/arch/arm/mm/highmem.c
@@ -34,6 +34,11 @@ static inline pte_t get_fixmap_pte(unsig
 	return *ptep;
 }
 
+static unsigned int fixmap_idx(int type)
+{
+	return FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id();
+}
+
 void *kmap(struct page *page)
 {
 	might_sleep();
@@ -54,12 +59,13 @@ EXPORT_SYMBOL(kunmap);
 
 void *kmap_atomic(struct page *page)
 {
+	pte_t pte = mk_pte(page, kmap_prot);
 	unsigned int idx;
 	unsigned long vaddr;
 	void *kmap;
 	int type;
 
-	preempt_disable();
+	preempt_disable_nort();
 	pagefault_disable();
 	if (!PageHighMem(page))
 		return page_address(page);
@@ -79,7 +85,7 @@ void *kmap_atomic(struct page *page)
 
 	type = kmap_atomic_idx_push();
 
-	idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id();
+	idx = fixmap_idx(type);
 	vaddr = __fix_to_virt(idx);
 #ifdef CONFIG_DEBUG_HIGHMEM
 	/*
@@ -93,7 +99,10 @@ void *kmap_atomic(struct page *page)
 	 * in place, so the contained TLB flush ensures the TLB is updated
 	 * with the new mapping.
 	 */
-	set_fixmap_pte(idx, mk_pte(page, kmap_prot));
+#ifdef CONFIG_PREEMPT_RT_FULL
+	current->kmap_pte[type] = pte;
+#endif
+	set_fixmap_pte(idx, pte);
 
 	return (void *)vaddr;
 }
@@ -106,44 +115,75 @@ void __kunmap_atomic(void *kvaddr)
 
 	if (kvaddr >= (void *)FIXADDR_START) {
 		type = kmap_atomic_idx();
-		idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id();
+		idx = fixmap_idx(type);
 
 		if (cache_is_vivt())
 			__cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE);
+#ifdef CONFIG_PREEMPT_RT_FULL
+		current->kmap_pte[type] = __pte(0);
+#endif
 #ifdef CONFIG_DEBUG_HIGHMEM
 		BUG_ON(vaddr != __fix_to_virt(idx));
-		set_fixmap_pte(idx, __pte(0));
 #else
 		(void) idx;  /* to kill a warning */
 #endif
+		set_fixmap_pte(idx, __pte(0));
 		kmap_atomic_idx_pop();
 	} else if (vaddr >= PKMAP_ADDR(0) && vaddr < PKMAP_ADDR(LAST_PKMAP)) {
 		/* this address was obtained through kmap_high_get() */
 		kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)]));
 	}
 	pagefault_enable();
-	preempt_enable();
+	preempt_enable_nort();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
 
 void *kmap_atomic_pfn(unsigned long pfn)
 {
+	pte_t pte = pfn_pte(pfn, kmap_prot);
 	unsigned long vaddr;
 	int idx, type;
 	struct page *page = pfn_to_page(pfn);
 
-	preempt_disable();
+	preempt_disable_nort();
 	pagefault_disable();
 	if (!PageHighMem(page))
 		return page_address(page);
 
 	type = kmap_atomic_idx_push();
-	idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id();
+	idx = fixmap_idx(type);
 	vaddr = __fix_to_virt(idx);
 #ifdef CONFIG_DEBUG_HIGHMEM
 	BUG_ON(!pte_none(get_fixmap_pte(vaddr)));
 #endif
-	set_fixmap_pte(idx, pfn_pte(pfn, kmap_prot));
+#ifdef CONFIG_PREEMPT_RT_FULL
+	current->kmap_pte[type] = pte;
+#endif
+	set_fixmap_pte(idx, pte);
 
 	return (void *)vaddr;
 }
+#if defined CONFIG_PREEMPT_RT_FULL
+void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p)
+{
+	int i;
+
+	/*
+	 * Clear @prev's kmap_atomic mappings
+	 */
+	for (i = 0; i < prev_p->kmap_idx; i++) {
+		int idx = fixmap_idx(i);
+
+		set_fixmap_pte(idx, __pte(0));
+	}
+	/*
+	 * Restore @next_p's kmap_atomic mappings
+	 */
+	for (i = 0; i < next_p->kmap_idx; i++) {
+		int idx = fixmap_idx(i);
+
+		if (!pte_none(next_p->kmap_pte[i]))
+			set_fixmap_pte(idx, next_p->kmap_pte[i]);
+	}
+}
+#endif
Index: linux-4.9.20-rt16/arch/arm/plat-versatile/platsmp.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm/plat-versatile/platsmp.c
+++ linux-4.9.20-rt16/arch/arm/plat-versatile/platsmp.c
@@ -32,7 +32,7 @@ static void write_pen_release(int val)
 	sync_cache_w(&pen_release);
 }
 
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
 
 void versatile_secondary_init(unsigned int cpu)
 {
@@ -45,8 +45,8 @@ void versatile_secondary_init(unsigned i
 	/*
 	 * Synchronise with the boot thread.
 	 */
-	spin_lock(&boot_lock);
-	spin_unlock(&boot_lock);
+	raw_spin_lock(&boot_lock);
+	raw_spin_unlock(&boot_lock);
 }
 
 int versatile_boot_secondary(unsigned int cpu, struct task_struct *idle)
@@ -57,7 +57,7 @@ int versatile_boot_secondary(unsigned in
 	 * Set synchronisation state between this boot processor
 	 * and the secondary one
 	 */
-	spin_lock(&boot_lock);
+	raw_spin_lock(&boot_lock);
 
 	/*
 	 * This is really belt and braces; we hold unintended secondary
@@ -87,7 +87,7 @@ int versatile_boot_secondary(unsigned in
 	 * now the secondary core is starting up let it run its
 	 * calibrations, then wait for it to finish
 	 */
-	spin_unlock(&boot_lock);
+	raw_spin_unlock(&boot_lock);
 
 	return pen_release != -1 ? -ENOSYS : 0;
 }
Index: linux-4.9.20-rt16/arch/arm64/Kconfig
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm64/Kconfig
+++ linux-4.9.20-rt16/arch/arm64/Kconfig
@@ -91,6 +91,7 @@ config ARM64
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
+	select HAVE_PREEMPT_LAZY
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RCU_TABLE_FREE
 	select HAVE_SYSCALL_TRACEPOINTS
@@ -704,7 +705,7 @@ config XEN_DOM0
 
 config XEN
 	bool "Xen guest support on ARM64"
-	depends on ARM64 && OF
+	depends on ARM64 && OF && !PREEMPT_RT_FULL
 	select SWIOTLB_XEN
 	select PARAVIRT
 	help
Index: linux-4.9.20-rt16/arch/arm64/include/asm/thread_info.h
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm64/include/asm/thread_info.h
+++ linux-4.9.20-rt16/arch/arm64/include/asm/thread_info.h
@@ -49,6 +49,7 @@ struct thread_info {
 	mm_segment_t		addr_limit;	/* address limit */
 	struct task_struct	*task;		/* main task structure */
 	int			preempt_count;	/* 0 => preemptable, <0 => bug */
+	int			preempt_lazy_count; /* 0 => preemptable, <0 => bug */
 	int			cpu;		/* cpu */
 };
 
@@ -112,6 +113,7 @@ static inline struct thread_info *curren
 #define TIF_NEED_RESCHED	1
 #define TIF_NOTIFY_RESUME	2	/* callback before returning to user */
 #define TIF_FOREIGN_FPSTATE	3	/* CPU's FP state is not current's */
+#define TIF_NEED_RESCHED_LAZY	4
 #define TIF_NOHZ		7
 #define TIF_SYSCALL_TRACE	8
 #define TIF_SYSCALL_AUDIT	9
@@ -127,6 +129,7 @@ static inline struct thread_info *curren
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
 #define _TIF_FOREIGN_FPSTATE	(1 << TIF_FOREIGN_FPSTATE)
+#define _TIF_NEED_RESCHED_LAZY	(1 << TIF_NEED_RESCHED_LAZY)
 #define _TIF_NOHZ		(1 << TIF_NOHZ)
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
@@ -135,7 +138,9 @@ static inline struct thread_info *curren
 #define _TIF_32BIT		(1 << TIF_32BIT)
 
 #define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
-				 _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE)
+				 _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \
+				 _TIF_NEED_RESCHED_LAZY)
+#define _TIF_NEED_RESCHED_MASK	(_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)
 
 #define _TIF_SYSCALL_WORK	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
 				 _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \
Index: linux-4.9.20-rt16/arch/arm64/kernel/asm-offsets.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm64/kernel/asm-offsets.c
+++ linux-4.9.20-rt16/arch/arm64/kernel/asm-offsets.c
@@ -38,6 +38,7 @@ int main(void)
   BLANK();
   DEFINE(TI_FLAGS,		offsetof(struct thread_info, flags));
   DEFINE(TI_PREEMPT,		offsetof(struct thread_info, preempt_count));
+  DEFINE(TI_PREEMPT_LAZY,	offsetof(struct thread_info, preempt_lazy_count));
   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));
Index: linux-4.9.20-rt16/arch/arm64/kernel/entry.S
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm64/kernel/entry.S
+++ linux-4.9.20-rt16/arch/arm64/kernel/entry.S
@@ -430,11 +430,16 @@ el1_irq:
 
 #ifdef CONFIG_PREEMPT
 	ldr	w24, [tsk, #TI_PREEMPT]		// get preempt count
-	cbnz	w24, 1f				// preempt count != 0
+	cbnz	w24, 2f				// preempt count != 0
 	ldr	x0, [tsk, #TI_FLAGS]		// get flags
-	tbz	x0, #TIF_NEED_RESCHED, 1f	// needs rescheduling?
-	bl	el1_preempt
+	tbnz	x0, #TIF_NEED_RESCHED, 1f	// needs rescheduling?
+
+	ldr	w24, [tsk, #TI_PREEMPT_LAZY]	// get preempt lazy count
+	cbnz	w24, 2f				// preempt lazy count != 0
+	tbz	x0, #TIF_NEED_RESCHED_LAZY, 2f	// needs rescheduling?
 1:
+	bl	el1_preempt
+2:
 #endif
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_on
@@ -448,6 +453,7 @@ el1_preempt:
 1:	bl	preempt_schedule_irq		// irq en/disable is done inside
 	ldr	x0, [tsk, #TI_FLAGS]		// get new tasks TI_FLAGS
 	tbnz	x0, #TIF_NEED_RESCHED, 1b	// needs rescheduling?
+	tbnz	x0, #TIF_NEED_RESCHED_LAZY, 1b	// needs rescheduling?
 	ret	x24
 #endif
 
Index: linux-4.9.20-rt16/arch/arm64/kernel/signal.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/arm64/kernel/signal.c
+++ linux-4.9.20-rt16/arch/arm64/kernel/signal.c
@@ -409,7 +409,7 @@ asmlinkage void do_notify_resume(struct
 	 */
 	trace_hardirqs_off();
 	do {
-		if (thread_flags & _TIF_NEED_RESCHED) {
+		if (thread_flags & _TIF_NEED_RESCHED_MASK) {
 			schedule();
 		} else {
 			local_irq_enable();
Index: linux-4.9.20-rt16/arch/mips/Kconfig
===================================================================
--- linux-4.9.20-rt16.orig/arch/mips/Kconfig
+++ linux-4.9.20-rt16/arch/mips/Kconfig
@@ -2516,7 +2516,7 @@ config MIPS_ASID_BITS_VARIABLE
 #
 config HIGHMEM
 	bool "High Memory Support"
-	depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !CPU_MIPS32_3_5_EVA
+	depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !CPU_MIPS32_3_5_EVA && !PREEMPT_RT_FULL
 
 config CPU_SUPPORTS_HIGHMEM
 	bool
Index: linux-4.9.20-rt16/arch/powerpc/Kconfig
===================================================================
--- linux-4.9.20-rt16.orig/arch/powerpc/Kconfig
+++ linux-4.9.20-rt16/arch/powerpc/Kconfig
@@ -52,10 +52,11 @@ config LOCKDEP_SUPPORT
 
 config RWSEM_GENERIC_SPINLOCK
 	bool
+	default y if PREEMPT_RT_FULL
 
 config RWSEM_XCHGADD_ALGORITHM
 	bool
-	default y
+	default y if !PREEMPT_RT_FULL
 
 config GENERIC_LOCKBREAK
 	bool
@@ -134,6 +135,7 @@ config PPC
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select GENERIC_STRNCPY_FROM_USER
 	select GENERIC_STRNLEN_USER
+	select HAVE_PREEMPT_LAZY
 	select HAVE_MOD_ARCH_SPECIFIC
 	select MODULES_USE_ELF_RELA
 	select CLONE_BACKWARDS
@@ -321,7 +323,7 @@ menu "Kernel options"
 
 config HIGHMEM
 	bool "High memory support"
-	depends on PPC32
+	depends on PPC32 && !PREEMPT_RT_FULL
 
 source kernel/Kconfig.hz
 source kernel/Kconfig.preempt
Index: linux-4.9.20-rt16/arch/powerpc/include/asm/thread_info.h
===================================================================
--- linux-4.9.20-rt16.orig/arch/powerpc/include/asm/thread_info.h
+++ linux-4.9.20-rt16/arch/powerpc/include/asm/thread_info.h
@@ -43,6 +43,8 @@ struct thread_info {
 	int		cpu;			/* cpu we're on */
 	int		preempt_count;		/* 0 => preemptable,
 						   <0 => BUG */
+	int		preempt_lazy_count;	/* 0 => preemptable,
+						   <0 => BUG */
 	unsigned long	local_flags;		/* private flags for thread */
 #ifdef CONFIG_LIVEPATCH
 	unsigned long *livepatch_sp;
@@ -88,8 +90,7 @@ static inline struct thread_info *curren
 #define TIF_SYSCALL_TRACE	0	/* syscall trace active */
 #define TIF_SIGPENDING		1	/* signal pending */
 #define TIF_NEED_RESCHED	2	/* rescheduling necessary */
-#define TIF_POLLING_NRFLAG	3	/* true if poll_idle() is polling
-					   TIF_NEED_RESCHED */
+#define TIF_NEED_RESCHED_LAZY	3	/* lazy rescheduling necessary */
 #define TIF_32BIT		4	/* 32 bit binary */
 #define TIF_RESTORE_TM		5	/* need to restore TM FP/VEC/VSX */
 #define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
@@ -107,6 +108,8 @@ static inline struct thread_info *curren
 #if defined(CONFIG_PPC64)
 #define TIF_ELF2ABI		18	/* function descriptors must die! */
 #endif
+#define TIF_POLLING_NRFLAG	19	/* true if poll_idle() is polling
+					   TIF_NEED_RESCHED */
 
 /* as above, but as bit values */
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
@@ -125,14 +128,16 @@ static inline struct thread_info *curren
 #define _TIF_SYSCALL_TRACEPOINT	(1<<TIF_SYSCALL_TRACEPOINT)
 #define _TIF_EMULATE_STACK_STORE	(1<<TIF_EMULATE_STACK_STORE)
 #define _TIF_NOHZ		(1<<TIF_NOHZ)
+#define _TIF_NEED_RESCHED_LAZY	(1<<TIF_NEED_RESCHED_LAZY)
 #define _TIF_SYSCALL_DOTRACE	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
 				 _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \
 				 _TIF_NOHZ)
 
 #define _TIF_USER_WORK_MASK	(_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
 				 _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
-				 _TIF_RESTORE_TM)
+				 _TIF_RESTORE_TM | _TIF_NEED_RESCHED_LAZY)
 #define _TIF_PERSYSCALL_MASK	(_TIF_RESTOREALL|_TIF_NOERROR)
+#define _TIF_NEED_RESCHED_MASK	(_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)
 
 /* Bits in local_flags */
 /* Don't move TLF_NAPPING without adjusting the code in entry_32.S */
Index: linux-4.9.20-rt16/arch/powerpc/kernel/asm-offsets.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/powerpc/kernel/asm-offsets.c
+++ linux-4.9.20-rt16/arch/powerpc/kernel/asm-offsets.c
@@ -156,6 +156,7 @@ int main(void)
 	DEFINE(TI_FLAGS, offsetof(struct thread_info, flags));
 	DEFINE(TI_LOCAL_FLAGS, offsetof(struct thread_info, local_flags));
 	DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count));
+	DEFINE(TI_PREEMPT_LAZY, offsetof(struct thread_info, preempt_lazy_count));
 	DEFINE(TI_TASK, offsetof(struct thread_info, task));
 	DEFINE(TI_CPU, offsetof(struct thread_info, cpu));
 
Index: linux-4.9.20-rt16/arch/powerpc/kernel/entry_32.S
===================================================================
--- linux-4.9.20-rt16.orig/arch/powerpc/kernel/entry_32.S
+++ linux-4.9.20-rt16/arch/powerpc/kernel/entry_32.S
@@ -835,7 +835,14 @@ resume_kernel:
 	cmpwi	0,r0,0		/* if non-zero, just restore regs and return */
 	bne	restore
 	andi.	r8,r8,_TIF_NEED_RESCHED
+	bne+	1f
+	lwz	r0,TI_PREEMPT_LAZY(r9)
+	cmpwi	0,r0,0		/* if non-zero, just restore regs and return */
+	bne	restore
+	lwz	r0,TI_FLAGS(r9)
+	andi.	r0,r0,_TIF_NEED_RESCHED_LAZY
 	beq+	restore
+1:
 	lwz	r3,_MSR(r1)
 	andi.	r0,r3,MSR_EE	/* interrupts off? */
 	beq	restore		/* don't schedule if so */
@@ -846,11 +853,11 @@ resume_kernel:
 	 */
 	bl	trace_hardirqs_off
 #endif
-1:	bl	preempt_schedule_irq
+2:	bl	preempt_schedule_irq
 	CURRENT_THREAD_INFO(r9, r1)
 	lwz	r3,TI_FLAGS(r9)
-	andi.	r0,r3,_TIF_NEED_RESCHED
-	bne-	1b
+	andi.	r0,r3,_TIF_NEED_RESCHED_MASK
+	bne-	2b
 #ifdef CONFIG_TRACE_IRQFLAGS
 	/* And now, to properly rebalance the above, we tell lockdep they
 	 * are being turned back on, which will happen when we return
@@ -1171,7 +1178,7 @@ global_dbcr0:
 #endif /* !(CONFIG_4xx || CONFIG_BOOKE) */
 
 do_work:			/* r10 contains MSR_KERNEL here */
-	andi.	r0,r9,_TIF_NEED_RESCHED
+	andi.	r0,r9,_TIF_NEED_RESCHED_MASK
 	beq	do_user_signal
 
 do_resched:			/* r10 contains MSR_KERNEL here */
@@ -1192,7 +1199,7 @@ recheck:
 	MTMSRD(r10)		/* disable interrupts */
 	CURRENT_THREAD_INFO(r9, r1)
 	lwz	r9,TI_FLAGS(r9)
-	andi.	r0,r9,_TIF_NEED_RESCHED
+	andi.	r0,r9,_TIF_NEED_RESCHED_MASK
 	bne-	do_resched
 	andi.	r0,r9,_TIF_USER_WORK_MASK
 	beq	restore_user
Index: linux-4.9.20-rt16/arch/powerpc/kernel/entry_64.S
===================================================================
--- linux-4.9.20-rt16.orig/arch/powerpc/kernel/entry_64.S
+++ linux-4.9.20-rt16/arch/powerpc/kernel/entry_64.S
@@ -656,7 +656,7 @@ _GLOBAL(ret_from_except_lite)
 	bl	restore_math
 	b	restore
 #endif
-1:	andi.	r0,r4,_TIF_NEED_RESCHED
+1:	andi.	r0,r4,_TIF_NEED_RESCHED_MASK
 	beq	2f
 	bl	restore_interrupts
 	SCHEDULE_USER
@@ -718,10 +718,18 @@ resume_kernel:
 
 #ifdef CONFIG_PREEMPT
 	/* Check if we need to preempt */
+	lwz	r8,TI_PREEMPT(r9)
+	cmpwi	0,r8,0		/* if non-zero, just restore regs and return */
+	bne	restore
 	andi.	r0,r4,_TIF_NEED_RESCHED
+	bne+	check_count
+
+	andi.	r0,r4,_TIF_NEED_RESCHED_LAZY
 	beq+	restore
+	lwz	r8,TI_PREEMPT_LAZY(r9)
+
 	/* Check that preempt_count() == 0 and interrupts are enabled */
-	lwz	r8,TI_PREEMPT(r9)
+check_count:
 	cmpwi	cr1,r8,0
 	ld	r0,SOFTE(r1)
 	cmpdi	r0,0
@@ -738,7 +746,7 @@ resume_kernel:
 	/* Re-test flags and eventually loop */
 	CURRENT_THREAD_INFO(r9, r1)
 	ld	r4,TI_FLAGS(r9)
-	andi.	r0,r4,_TIF_NEED_RESCHED
+	andi.	r0,r4,_TIF_NEED_RESCHED_MASK
 	bne	1b
 
 	/*
Index: linux-4.9.20-rt16/arch/powerpc/kernel/irq.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/powerpc/kernel/irq.c
+++ linux-4.9.20-rt16/arch/powerpc/kernel/irq.c
@@ -651,6 +651,7 @@ void irq_ctx_init(void)
 	}
 }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 void do_softirq_own_stack(void)
 {
 	struct thread_info *curtp, *irqtp;
@@ -668,6 +669,7 @@ void do_softirq_own_stack(void)
 	if (irqtp->flags)
 		set_bits(irqtp->flags, &curtp->flags);
 }
+#endif
 
 irq_hw_number_t virq_to_hw(unsigned int virq)
 {
Index: linux-4.9.20-rt16/arch/powerpc/kernel/misc_32.S
===================================================================
--- linux-4.9.20-rt16.orig/arch/powerpc/kernel/misc_32.S
+++ linux-4.9.20-rt16/arch/powerpc/kernel/misc_32.S
@@ -41,6 +41,7 @@
  * We store the saved ksp_limit in the unused part
  * of the STACK_FRAME_OVERHEAD
  */
+#ifndef CONFIG_PREEMPT_RT_FULL
 _GLOBAL(call_do_softirq)
 	mflr	r0
 	stw	r0,4(r1)
@@ -57,6 +58,7 @@ _GLOBAL(call_do_softirq)
 	stw	r10,THREAD+KSP_LIMIT(r2)
 	mtlr	r0
 	blr
+#endif
 
 /*
  * void call_do_irq(struct pt_regs *regs, struct thread_info *irqtp);
Index: linux-4.9.20-rt16/arch/powerpc/kernel/misc_64.S
===================================================================
--- linux-4.9.20-rt16.orig/arch/powerpc/kernel/misc_64.S
+++ linux-4.9.20-rt16/arch/powerpc/kernel/misc_64.S
@@ -31,6 +31,7 @@
 
 	.text
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 _GLOBAL(call_do_softirq)
 	mflr	r0
 	std	r0,16(r1)
@@ -41,6 +42,7 @@ _GLOBAL(call_do_softirq)
 	ld	r0,16(r1)
 	mtlr	r0
 	blr
+#endif
 
 _GLOBAL(call_do_irq)
 	mflr	r0
Index: linux-4.9.20-rt16/arch/powerpc/kvm/Kconfig
===================================================================
--- linux-4.9.20-rt16.orig/arch/powerpc/kvm/Kconfig
+++ linux-4.9.20-rt16/arch/powerpc/kvm/Kconfig
@@ -175,6 +175,7 @@ config KVM_E500MC
 config KVM_MPIC
 	bool "KVM in-kernel MPIC emulation"
 	depends on KVM && E500
+	depends on !PREEMPT_RT_FULL
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_IRQFD
 	select HAVE_KVM_IRQ_ROUTING
Index: linux-4.9.20-rt16/arch/powerpc/platforms/ps3/device-init.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/powerpc/platforms/ps3/device-init.c
+++ linux-4.9.20-rt16/arch/powerpc/platforms/ps3/device-init.c
@@ -752,7 +752,7 @@ static int ps3_notification_read_write(s
 	}
 	pr_debug("%s:%u: notification %s issued\n", __func__, __LINE__, op);
 
-	res = wait_event_interruptible(dev->done.wait,
+	res = swait_event_interruptible(dev->done.wait,
 				       dev->done.done || kthread_should_stop());
 	if (kthread_should_stop())
 		res = -EINTR;
Index: linux-4.9.20-rt16/arch/sh/kernel/irq.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/sh/kernel/irq.c
+++ linux-4.9.20-rt16/arch/sh/kernel/irq.c
@@ -147,6 +147,7 @@ void irq_ctx_exit(int cpu)
 	hardirq_ctx[cpu] = NULL;
 }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 void do_softirq_own_stack(void)
 {
 	struct thread_info *curctx;
@@ -174,6 +175,7 @@ void do_softirq_own_stack(void)
 		  "r5", "r6", "r7", "r8", "r9", "r15", "t", "pr"
 	);
 }
+#endif
 #else
 static inline void handle_one_irq(unsigned int irq)
 {
Index: linux-4.9.20-rt16/arch/sparc/Kconfig
===================================================================
--- linux-4.9.20-rt16.orig/arch/sparc/Kconfig
+++ linux-4.9.20-rt16/arch/sparc/Kconfig
@@ -194,12 +194,10 @@ config NR_CPUS
 source kernel/Kconfig.hz
 
 config RWSEM_GENERIC_SPINLOCK
-	bool
-	default y if SPARC32
+	def_bool PREEMPT_RT_FULL
 
 config RWSEM_XCHGADD_ALGORITHM
-	bool
-	default y if SPARC64
+	def_bool !RWSEM_GENERIC_SPINLOCK && !PREEMPT_RT_FULL
 
 config GENERIC_HWEIGHT
 	bool
Index: linux-4.9.20-rt16/arch/sparc/kernel/irq_64.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/sparc/kernel/irq_64.c
+++ linux-4.9.20-rt16/arch/sparc/kernel/irq_64.c
@@ -854,6 +854,7 @@ void __irq_entry handler_irq(int pil, st
 	set_irq_regs(old_regs);
 }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 void do_softirq_own_stack(void)
 {
 	void *orig_sp, *sp = softirq_stack[smp_processor_id()];
@@ -868,6 +869,7 @@ void do_softirq_own_stack(void)
 	__asm__ __volatile__("mov %0, %%sp"
 			     : : "r" (orig_sp));
 }
+#endif
 
 #ifdef CONFIG_HOTPLUG_CPU
 void fixup_irqs(void)
Index: linux-4.9.20-rt16/arch/x86/Kconfig
===================================================================
--- linux-4.9.20-rt16.orig/arch/x86/Kconfig
+++ linux-4.9.20-rt16/arch/x86/Kconfig
@@ -17,6 +17,7 @@ config X86_64
 ### Arch settings
 config X86
 	def_bool y
+	select HAVE_PREEMPT_LAZY
 	select ACPI_LEGACY_TABLES_LOOKUP	if ACPI
 	select ACPI_SYSTEM_POWER_STATES_SUPPORT	if ACPI
 	select ANON_INODES
@@ -232,8 +233,11 @@ config ARCH_MAY_HAVE_PC_FDC
 	def_bool y
 	depends on ISA_DMA_API
 
+config RWSEM_GENERIC_SPINLOCK
+	def_bool PREEMPT_RT_FULL
+
 config RWSEM_XCHGADD_ALGORITHM
-	def_bool y
+	def_bool !RWSEM_GENERIC_SPINLOCK && !PREEMPT_RT_FULL
 
 config GENERIC_CALIBRATE_DELAY
 	def_bool y
@@ -897,7 +901,7 @@ config IOMMU_HELPER
 config MAXSMP
 	bool "Enable Maximum number of SMP Processors and NUMA Nodes"
 	depends on X86_64 && SMP && DEBUG_KERNEL
-	select CPUMASK_OFFSTACK
+	select CPUMASK_OFFSTACK if !PREEMPT_RT_FULL
 	---help---
 	  Enable maximum number of CPUS and NUMA Nodes for this architecture.
 	  If unsure, say N.
Index: linux-4.9.20-rt16/arch/x86/crypto/aesni-intel_glue.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/x86/crypto/aesni-intel_glue.c
+++ linux-4.9.20-rt16/arch/x86/crypto/aesni-intel_glue.c
@@ -372,14 +372,14 @@ static int ecb_encrypt(struct blkcipher_
 	err = blkcipher_walk_virt(desc, &walk);
 	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
 
-	kernel_fpu_begin();
 	while ((nbytes = walk.nbytes)) {
+		kernel_fpu_begin();
 		aesni_ecb_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr,
-			      nbytes & AES_BLOCK_MASK);
+				nbytes & AES_BLOCK_MASK);
+		kernel_fpu_end();
 		nbytes &= AES_BLOCK_SIZE - 1;
 		err = blkcipher_walk_done(desc, &walk, nbytes);
 	}
-	kernel_fpu_end();
 
 	return err;
 }
@@ -396,14 +396,14 @@ static int ecb_decrypt(struct blkcipher_
 	err = blkcipher_walk_virt(desc, &walk);
 	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
 
-	kernel_fpu_begin();
 	while ((nbytes = walk.nbytes)) {
+		kernel_fpu_begin();
 		aesni_ecb_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr,
 			      nbytes & AES_BLOCK_MASK);
+		kernel_fpu_end();
 		nbytes &= AES_BLOCK_SIZE - 1;
 		err = blkcipher_walk_done(desc, &walk, nbytes);
 	}
-	kernel_fpu_end();
 
 	return err;
 }
@@ -420,14 +420,14 @@ static int cbc_encrypt(struct blkcipher_
 	err = blkcipher_walk_virt(desc, &walk);
 	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
 
-	kernel_fpu_begin();
 	while ((nbytes = walk.nbytes)) {
+		kernel_fpu_begin();
 		aesni_cbc_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr,
 			      nbytes & AES_BLOCK_MASK, walk.iv);
+		kernel_fpu_end();
 		nbytes &= AES_BLOCK_SIZE - 1;
 		err = blkcipher_walk_done(desc, &walk, nbytes);
 	}
-	kernel_fpu_end();
 
 	return err;
 }
@@ -444,14 +444,14 @@ static int cbc_decrypt(struct blkcipher_
 	err = blkcipher_walk_virt(desc, &walk);
 	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
 
-	kernel_fpu_begin();
 	while ((nbytes = walk.nbytes)) {
+		kernel_fpu_begin();
 		aesni_cbc_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr,
 			      nbytes & AES_BLOCK_MASK, walk.iv);
+		kernel_fpu_end();
 		nbytes &= AES_BLOCK_SIZE - 1;
 		err = blkcipher_walk_done(desc, &walk, nbytes);
 	}
-	kernel_fpu_end();
 
 	return err;
 }
@@ -503,18 +503,20 @@ static int ctr_crypt(struct blkcipher_de
 	err = blkcipher_walk_virt_block(desc, &walk, AES_BLOCK_SIZE);
 	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
 
-	kernel_fpu_begin();
 	while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) {
+		kernel_fpu_begin();
 		aesni_ctr_enc_tfm(ctx, walk.dst.virt.addr, walk.src.virt.addr,
 			              nbytes & AES_BLOCK_MASK, walk.iv);
+		kernel_fpu_end();
 		nbytes &= AES_BLOCK_SIZE - 1;
 		err = blkcipher_walk_done(desc, &walk, nbytes);
 	}
 	if (walk.nbytes) {
+		kernel_fpu_begin();
 		ctr_crypt_final(ctx, &walk);
+		kernel_fpu_end();
 		err = blkcipher_walk_done(desc, &walk, 0);
 	}
-	kernel_fpu_end();
 
 	return err;
 }
Index: linux-4.9.20-rt16/arch/x86/crypto/cast5_avx_glue.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/x86/crypto/cast5_avx_glue.c
+++ linux-4.9.20-rt16/arch/x86/crypto/cast5_avx_glue.c
@@ -59,7 +59,7 @@ static inline void cast5_fpu_end(bool fp
 static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk,
 		     bool enc)
 {
-	bool fpu_enabled = false;
+	bool fpu_enabled;
 	struct cast5_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
 	const unsigned int bsize = CAST5_BLOCK_SIZE;
 	unsigned int nbytes;
@@ -75,7 +75,7 @@ static int ecb_crypt(struct blkcipher_de
 		u8 *wsrc = walk->src.virt.addr;
 		u8 *wdst = walk->dst.virt.addr;
 
-		fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes);
+		fpu_enabled = cast5_fpu_begin(false, nbytes);
 
 		/* Process multi-block batch */
 		if (nbytes >= bsize * CAST5_PARALLEL_BLOCKS) {
@@ -103,10 +103,9 @@ static int ecb_crypt(struct blkcipher_de
 		} while (nbytes >= bsize);
 
 done:
+		cast5_fpu_end(fpu_enabled);
 		err = blkcipher_walk_done(desc, walk, nbytes);
 	}
-
-	cast5_fpu_end(fpu_enabled);
 	return err;
 }
 
@@ -227,7 +226,7 @@ done:
 static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		       struct scatterlist *src, unsigned int nbytes)
 {
-	bool fpu_enabled = false;
+	bool fpu_enabled;
 	struct blkcipher_walk walk;
 	int err;
 
@@ -236,12 +235,11 @@ static int cbc_decrypt(struct blkcipher_
 	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	while ((nbytes = walk.nbytes)) {
-		fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes);
+		fpu_enabled = cast5_fpu_begin(false, nbytes);
 		nbytes = __cbc_decrypt(desc, &walk);
+		cast5_fpu_end(fpu_enabled);
 		err = blkcipher_walk_done(desc, &walk, nbytes);
 	}
-
-	cast5_fpu_end(fpu_enabled);
 	return err;
 }
 
@@ -311,7 +309,7 @@ done:
 static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		     struct scatterlist *src, unsigned int nbytes)
 {
-	bool fpu_enabled = false;
+	bool fpu_enabled;
 	struct blkcipher_walk walk;
 	int err;
 
@@ -320,13 +318,12 @@ static int ctr_crypt(struct blkcipher_de
 	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
 
 	while ((nbytes = walk.nbytes) >= CAST5_BLOCK_SIZE) {
-		fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes);
+		fpu_enabled = cast5_fpu_begin(false, nbytes);
 		nbytes = __ctr_crypt(desc, &walk);
+		cast5_fpu_end(fpu_enabled);
 		err = blkcipher_walk_done(desc, &walk, nbytes);
 	}
 
-	cast5_fpu_end(fpu_enabled);
-
 	if (walk.nbytes) {
 		ctr_crypt_final(desc, &walk);
 		err = blkcipher_walk_done(desc, &walk, 0);
Index: linux-4.9.20-rt16/arch/x86/crypto/glue_helper.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/x86/crypto/glue_helper.c
+++ linux-4.9.20-rt16/arch/x86/crypto/glue_helper.c
@@ -39,7 +39,7 @@ static int __glue_ecb_crypt_128bit(const
 	void *ctx = crypto_blkcipher_ctx(desc->tfm);
 	const unsigned int bsize = 128 / 8;
 	unsigned int nbytes, i, func_bytes;
-	bool fpu_enabled = false;
+	bool fpu_enabled;
 	int err;
 
 	err = blkcipher_walk_virt(desc, walk);
@@ -49,7 +49,7 @@ static int __glue_ecb_crypt_128bit(const
 		u8 *wdst = walk->dst.virt.addr;
 
 		fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
-					     desc, fpu_enabled, nbytes);
+					     desc, false, nbytes);
 
 		for (i = 0; i < gctx->num_funcs; i++) {
 			func_bytes = bsize * gctx->funcs[i].num_blocks;
@@ -71,10 +71,10 @@ static int __glue_ecb_crypt_128bit(const
 		}
 
 done:
+		glue_fpu_end(fpu_enabled);
 		err = blkcipher_walk_done(desc, walk, nbytes);
 	}
 
-	glue_fpu_end(fpu_enabled);
 	return err;
 }
 
@@ -194,7 +194,7 @@ int glue_cbc_decrypt_128bit(const struct
 			    struct scatterlist *src, unsigned int nbytes)
 {
 	const unsigned int bsize = 128 / 8;
-	bool fpu_enabled = false;
+	bool fpu_enabled;
 	struct blkcipher_walk walk;
 	int err;
 
@@ -203,12 +203,12 @@ int glue_cbc_decrypt_128bit(const struct
 
 	while ((nbytes = walk.nbytes)) {
 		fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
-					     desc, fpu_enabled, nbytes);
+					     desc, false, nbytes);
 		nbytes = __glue_cbc_decrypt_128bit(gctx, desc, &walk);
+		glue_fpu_end(fpu_enabled);
 		err = blkcipher_walk_done(desc, &walk, nbytes);
 	}
 
-	glue_fpu_end(fpu_enabled);
 	return err;
 }
 EXPORT_SYMBOL_GPL(glue_cbc_decrypt_128bit);
@@ -277,7 +277,7 @@ int glue_ctr_crypt_128bit(const struct c
 			  struct scatterlist *src, unsigned int nbytes)
 {
 	const unsigned int bsize = 128 / 8;
-	bool fpu_enabled = false;
+	bool fpu_enabled;
 	struct blkcipher_walk walk;
 	int err;
 
@@ -286,13 +286,12 @@ int glue_ctr_crypt_128bit(const struct c
 
 	while ((nbytes = walk.nbytes) >= bsize) {
 		fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
-					     desc, fpu_enabled, nbytes);
+					     desc, false, nbytes);
 		nbytes = __glue_ctr_crypt_128bit(gctx, desc, &walk);
+		glue_fpu_end(fpu_enabled);
 		err = blkcipher_walk_done(desc, &walk, nbytes);
 	}
 
-	glue_fpu_end(fpu_enabled);
-
 	if (walk.nbytes) {
 		glue_ctr_crypt_final_128bit(
 			gctx->funcs[gctx->num_funcs - 1].fn_u.ctr, desc, &walk);
@@ -347,7 +346,7 @@ int glue_xts_crypt_128bit(const struct c
 			  void *tweak_ctx, void *crypt_ctx)
 {
 	const unsigned int bsize = 128 / 8;
-	bool fpu_enabled = false;
+	bool fpu_enabled;
 	struct blkcipher_walk walk;
 	int err;
 
@@ -360,21 +359,21 @@ int glue_xts_crypt_128bit(const struct c
 
 	/* set minimum length to bsize, for tweak_fn */
 	fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
-				     desc, fpu_enabled,
+				     desc, false,
 				     nbytes < bsize ? bsize : nbytes);
-
 	/* calculate first value of T */
 	tweak_fn(tweak_ctx, walk.iv, walk.iv);
+	glue_fpu_end(fpu_enabled);
 
 	while (nbytes) {
+		fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
+				desc, false, nbytes);
 		nbytes = __glue_xts_crypt_128bit(gctx, crypt_ctx, desc, &walk);
 
+		glue_fpu_end(fpu_enabled);
 		err = blkcipher_walk_done(desc, &walk, nbytes);
 		nbytes = walk.nbytes;
 	}
-
-	glue_fpu_end(fpu_enabled);
-
 	return err;
 }
 EXPORT_SYMBOL_GPL(glue_xts_crypt_128bit);
Index: linux-4.9.20-rt16/arch/x86/entry/common.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/x86/entry/common.c
+++ linux-4.9.20-rt16/arch/x86/entry/common.c
@@ -129,7 +129,7 @@ static long syscall_trace_enter(struct p
 
 #define EXIT_TO_USERMODE_LOOP_FLAGS				\
 	(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE |	\
-	 _TIF_NEED_RESCHED | _TIF_USER_RETURN_NOTIFY)
+	 _TIF_NEED_RESCHED_MASK | _TIF_USER_RETURN_NOTIFY)
 
 static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
 {
@@ -145,9 +145,16 @@ static void exit_to_usermode_loop(struct
 		/* We have work to do. */
 		local_irq_enable();
 
-		if (cached_flags & _TIF_NEED_RESCHED)
+		if (cached_flags & _TIF_NEED_RESCHED_MASK)
 			schedule();
 
+#ifdef ARCH_RT_DELAYS_SIGNAL_SEND
+		if (unlikely(current->forced_info.si_signo)) {
+			struct task_struct *t = current;
+			force_sig_info(t->forced_info.si_signo, &t->forced_info, t);
+			t->forced_info.si_signo = 0;
+		}
+#endif
 		if (cached_flags & _TIF_UPROBE)
 			uprobe_notify_resume(regs);
 
Index: linux-4.9.20-rt16/arch/x86/entry/entry_32.S
===================================================================
--- linux-4.9.20-rt16.orig/arch/x86/entry/entry_32.S
+++ linux-4.9.20-rt16/arch/x86/entry/entry_32.S
@@ -308,8 +308,25 @@ END(ret_from_exception)
 ENTRY(resume_kernel)
 	DISABLE_INTERRUPTS(CLBR_ANY)
 need_resched:
+	# preempt count == 0 + NEED_RS set?
 	cmpl	$0, PER_CPU_VAR(__preempt_count)
+#ifndef CONFIG_PREEMPT_LAZY
 	jnz	restore_all
+#else
+	jz test_int_off
+
+	# atleast preempt count == 0 ?
+	cmpl $_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count)
+	jne restore_all
+
+	movl    PER_CPU_VAR(current_task), %ebp
+	cmpl $0,TASK_TI_preempt_lazy_count(%ebp)	# non-zero preempt_lazy_count ?
+	jnz restore_all
+
+	testl $_TIF_NEED_RESCHED_LAZY, TASK_TI_flags(%ebp)
+	jz restore_all
+test_int_off:
+#endif
 	testl	$X86_EFLAGS_IF, PT_EFLAGS(%esp)	# interrupts off (exception path) ?
 	jz	restore_all
 	call	preempt_schedule_irq
Index: linux-4.9.20-rt16/arch/x86/entry/entry_64.S
===================================================================
--- linux-4.9.20-rt16.orig/arch/x86/entry/entry_64.S
+++ linux-4.9.20-rt16/arch/x86/entry/entry_64.S
@@ -546,7 +546,23 @@ retint_kernel:
 	bt	$9, EFLAGS(%rsp)		/* were interrupts off? */
 	jnc	1f
 0:	cmpl	$0, PER_CPU_VAR(__preempt_count)
+#ifndef CONFIG_PREEMPT_LAZY
 	jnz	1f
+#else
+	jz	do_preempt_schedule_irq
+
+	# atleast preempt count == 0 ?
+	cmpl $_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count)
+	jnz	1f
+
+	movq	PER_CPU_VAR(current_task), %rcx
+	cmpl	$0, TASK_TI_preempt_lazy_count(%rcx)
+	jnz	1f
+
+	bt	$TIF_NEED_RESCHED_LAZY,TASK_TI_flags(%rcx)
+	jnc	1f
+do_preempt_schedule_irq:
+#endif
 	call	preempt_schedule_irq
 	jmp	0b
 1:
@@ -894,6 +910,7 @@ bad_gs:
 	jmp	2b
 	.previous
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /* Call softirq on interrupt stack. Interrupts are off. */
 ENTRY(do_softirq_own_stack)
 	pushq	%rbp
@@ -906,6 +923,7 @@ ENTRY(do_softirq_own_stack)
 	decl	PER_CPU_VAR(irq_count)
 	ret
 END(do_softirq_own_stack)
+#endif
 
 #ifdef CONFIG_XEN
 idtentry xen_hypervisor_callback xen_do_hypervisor_callback has_error_code=0
Index: linux-4.9.20-rt16/arch/x86/include/asm/preempt.h
===================================================================
--- linux-4.9.20-rt16.orig/arch/x86/include/asm/preempt.h
+++ linux-4.9.20-rt16/arch/x86/include/asm/preempt.h
@@ -79,17 +79,46 @@ static __always_inline void __preempt_co
  * a decrement which hits zero means we have no preempt_count and should
  * reschedule.
  */
-static __always_inline bool __preempt_count_dec_and_test(void)
+static __always_inline bool ____preempt_count_dec_and_test(void)
 {
 	GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), e);
 }
 
+static __always_inline bool __preempt_count_dec_and_test(void)
+{
+	if (____preempt_count_dec_and_test())
+		return true;
+#ifdef CONFIG_PREEMPT_LAZY
+	if (current_thread_info()->preempt_lazy_count)
+		return false;
+	return test_thread_flag(TIF_NEED_RESCHED_LAZY);
+#else
+	return false;
+#endif
+}
+
 /*
  * Returns true when we need to resched and can (barring IRQ state).
  */
 static __always_inline bool should_resched(int preempt_offset)
 {
+#ifdef CONFIG_PREEMPT_LAZY
+	u32 tmp;
+
+	tmp = raw_cpu_read_4(__preempt_count);
+	if (tmp == preempt_offset)
+		return true;
+
+	/* preempt count == 0 ? */
+	tmp &= ~PREEMPT_NEED_RESCHED;
+	if (tmp)
+		return false;
+	if (current_thread_info()->preempt_lazy_count)
+		return false;
+	return test_thread_flag(TIF_NEED_RESCHED_LAZY);
+#else
 	return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset);
+#endif
 }
 
 #ifdef CONFIG_PREEMPT
Index: linux-4.9.20-rt16/arch/x86/include/asm/signal.h
===================================================================
--- linux-4.9.20-rt16.orig/arch/x86/include/asm/signal.h
+++ linux-4.9.20-rt16/arch/x86/include/asm/signal.h
@@ -27,6 +27,19 @@ typedef struct {
 #define SA_IA32_ABI	0x02000000u
 #define SA_X32_ABI	0x01000000u
 
+/*
+ * Because some traps use the IST stack, we must keep preemption
+ * disabled while calling do_trap(), but do_trap() may call
+ * force_sig_info() which will grab the signal spin_locks for the
+ * task, which in PREEMPT_RT_FULL are mutexes.  By defining
+ * ARCH_RT_DELAYS_SIGNAL_SEND the force_sig_info() will set
+ * TIF_NOTIFY_RESUME and set up the signal to be sent on exit of the
+ * trap.
+ */
+#if defined(CONFIG_PREEMPT_RT_FULL)
+#define ARCH_RT_DELAYS_SIGNAL_SEND
+#endif
+
 #ifndef CONFIG_COMPAT
 typedef sigset_t compat_sigset_t;
 #endif
Index: linux-4.9.20-rt16/arch/x86/include/asm/stackprotector.h
===================================================================
--- linux-4.9.20-rt16.orig/arch/x86/include/asm/stackprotector.h
+++ linux-4.9.20-rt16/arch/x86/include/asm/stackprotector.h
@@ -59,7 +59,7 @@
  */
 static __always_inline void boot_init_stack_canary(void)
 {
-	u64 canary;
+	u64 uninitialized_var(canary);
 	u64 tsc;
 
 #ifdef CONFIG_X86_64
@@ -70,8 +70,15 @@ static __always_inline void boot_init_st
 	 * of randomness. The TSC only matters for very early init,
 	 * there it already has some randomness on most systems. Later
 	 * on during the bootup the random pool has true entropy too.
+	 *
+	 * For preempt-rt we need to weaken the randomness a bit, as
+	 * we can't call into the random generator from atomic context
+	 * due to locking constraints. We just leave canary
+	 * uninitialized and use the TSC based randomness on top of it.
 	 */
+#ifndef CONFIG_PREEMPT_RT_FULL
 	get_random_bytes(&canary, sizeof(canary));
+#endif
 	tsc = rdtsc();
 	canary += tsc + (tsc << 32UL);
 
Index: linux-4.9.20-rt16/arch/x86/include/asm/thread_info.h
===================================================================
--- linux-4.9.20-rt16.orig/arch/x86/include/asm/thread_info.h
+++ linux-4.9.20-rt16/arch/x86/include/asm/thread_info.h
@@ -54,11 +54,14 @@ struct task_struct;
 
 struct thread_info {
 	unsigned long		flags;		/* low level flags */
+	int                     preempt_lazy_count;     /* 0 => lazy preemptable
+							   <0 => BUG */
 };
 
 #define INIT_THREAD_INFO(tsk)			\
 {						\
 	.flags		= 0,			\
+	.preempt_lazy_count = 0,		\
 }
 
 #define init_stack		(init_thread_union.stack)
@@ -67,6 +70,10 @@ struct thread_info {
 
 #include <asm/asm-offsets.h>
 
+#define GET_THREAD_INFO(reg) \
+	_ASM_MOV PER_CPU_VAR(cpu_current_top_of_stack),reg ; \
+	_ASM_SUB $(THREAD_SIZE),reg ;
+
 #endif
 
 /*
@@ -85,6 +92,7 @@ struct thread_info {
 #define TIF_SYSCALL_EMU		6	/* syscall emulation active */
 #define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
 #define TIF_SECCOMP		8	/* secure computing */
+#define TIF_NEED_RESCHED_LAZY	9	/* lazy rescheduling necessary */
 #define TIF_USER_RETURN_NOTIFY	11	/* notify kernel of userspace return */
 #define TIF_UPROBE		12	/* breakpointed or singlestepping */
 #define TIF_NOTSC		16	/* TSC is not accessible in userland */
@@ -108,6 +116,7 @@ struct thread_info {
 #define _TIF_SYSCALL_EMU	(1 << TIF_SYSCALL_EMU)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
+#define _TIF_NEED_RESCHED_LAZY	(1 << TIF_NEED_RESCHED_LAZY)
 #define _TIF_USER_RETURN_NOTIFY	(1 << TIF_USER_RETURN_NOTIFY)
 #define _TIF_UPROBE		(1 << TIF_UPROBE)
 #define _TIF_NOTSC		(1 << TIF_NOTSC)
@@ -143,6 +152,8 @@ struct thread_info {
 #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY)
 #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW)
 
+#define _TIF_NEED_RESCHED_MASK	(_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)
+
 #define STACK_WARN		(THREAD_SIZE/8)
 
 /*
Index: linux-4.9.20-rt16/arch/x86/include/asm/uv/uv_bau.h
===================================================================
--- linux-4.9.20-rt16.orig/arch/x86/include/asm/uv/uv_bau.h
+++ linux-4.9.20-rt16/arch/x86/include/asm/uv/uv_bau.h
@@ -624,9 +624,9 @@ struct bau_control {
 	cycles_t		send_message;
 	cycles_t		period_end;
 	cycles_t		period_time;
-	spinlock_t		uvhub_lock;
-	spinlock_t		queue_lock;
-	spinlock_t		disable_lock;
+	raw_spinlock_t		uvhub_lock;
+	raw_spinlock_t		queue_lock;
+	raw_spinlock_t		disable_lock;
 	/* tunables */
 	int			max_concurr;
 	int			max_concurr_const;
@@ -815,15 +815,15 @@ static inline int atom_asr(short i, stru
  * to be lowered below the current 'v'.  atomic_add_unless can only stop
  * on equal.
  */
-static inline int atomic_inc_unless_ge(spinlock_t *lock, atomic_t *v, int u)
+static inline int atomic_inc_unless_ge(raw_spinlock_t *lock, atomic_t *v, int u)
 {
-	spin_lock(lock);
+	raw_spin_lock(lock);
 	if (atomic_read(v) >= u) {
-		spin_unlock(lock);
+		raw_spin_unlock(lock);
 		return 0;
 	}
 	atomic_inc(v);
-	spin_unlock(lock);
+	raw_spin_unlock(lock);
 	return 1;
 }
 
Index: linux-4.9.20-rt16/arch/x86/kernel/acpi/boot.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/x86/kernel/acpi/boot.c
+++ linux-4.9.20-rt16/arch/x86/kernel/acpi/boot.c
@@ -87,7 +87,9 @@ static u64 acpi_lapic_addr __initdata =
  *		->ioapic_mutex
  *			->ioapic_lock
  */
+#ifdef CONFIG_X86_IO_APIC
 static DEFINE_MUTEX(acpi_ioapic_lock);
+#endif
 
 /* --------------------------------------------------------------------------
                               Boot-time Configuration
Index: linux-4.9.20-rt16/arch/x86/kernel/apic/io_apic.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/x86/kernel/apic/io_apic.c
+++ linux-4.9.20-rt16/arch/x86/kernel/apic/io_apic.c
@@ -1712,7 +1712,8 @@ static bool io_apic_level_ack_pending(st
 static inline bool ioapic_irqd_mask(struct irq_data *data)
 {
 	/* If we are moving the irq we need to mask it */
-	if (unlikely(irqd_is_setaffinity_pending(data))) {
+	if (unlikely(irqd_is_setaffinity_pending(data) &&
+		     !irqd_irq_inprogress(data))) {
 		mask_ioapic_irq(data);
 		return true;
 	}
Index: linux-4.9.20-rt16/arch/x86/kernel/asm-offsets.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/x86/kernel/asm-offsets.c
+++ linux-4.9.20-rt16/arch/x86/kernel/asm-offsets.c
@@ -36,6 +36,7 @@ void common(void) {
 
 	BLANK();
 	OFFSET(TASK_TI_flags, task_struct, thread_info.flags);
+	OFFSET(TASK_TI_preempt_lazy_count, task_struct, thread_info.preempt_lazy_count);
 	OFFSET(TASK_addr_limit, task_struct, thread.addr_limit);
 
 	BLANK();
@@ -91,4 +92,5 @@ void common(void) {
 
 	BLANK();
 	DEFINE(PTREGS_SIZE, sizeof(struct pt_regs));
+	DEFINE(_PREEMPT_ENABLED, PREEMPT_ENABLED);
 }
Index: linux-4.9.20-rt16/arch/x86/kernel/cpu/mcheck/mce.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/x86/kernel/cpu/mcheck/mce.c
+++ linux-4.9.20-rt16/arch/x86/kernel/cpu/mcheck/mce.c
@@ -41,6 +41,8 @@
 #include <linux/debugfs.h>
 #include <linux/irq_work.h>
 #include <linux/export.h>
+#include <linux/jiffies.h>
+#include <linux/swork.h>
 #include <linux/jump_label.h>
 
 #include <asm/processor.h>
@@ -1306,7 +1308,7 @@ void mce_log_therm_throt_event(__u64 sta
 static unsigned long check_interval = INITIAL_CHECK_INTERVAL;
 
 static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */
-static DEFINE_PER_CPU(struct timer_list, mce_timer);
+static DEFINE_PER_CPU(struct hrtimer, mce_timer);
 
 static unsigned long mce_adjust_timer_default(unsigned long interval)
 {
@@ -1315,32 +1317,18 @@ static unsigned long mce_adjust_timer_de
 
 static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default;
 
-static void __restart_timer(struct timer_list *t, unsigned long interval)
+static enum hrtimer_restart __restart_timer(struct hrtimer *timer, unsigned long interval)
 {
-	unsigned long when = jiffies + interval;
-	unsigned long flags;
-
-	local_irq_save(flags);
-
-	if (timer_pending(t)) {
-		if (time_before(when, t->expires))
-			mod_timer(t, when);
-	} else {
-		t->expires = round_jiffies(when);
-		add_timer_on(t, smp_processor_id());
-	}
-
-	local_irq_restore(flags);
+	if (!interval)
+		return HRTIMER_NORESTART;
+	hrtimer_forward_now(timer, ns_to_ktime(jiffies_to_nsecs(interval)));
+	return HRTIMER_RESTART;
 }
 
-static void mce_timer_fn(unsigned long data)
+static enum hrtimer_restart mce_timer_fn(struct hrtimer *timer)
 {
-	struct timer_list *t = this_cpu_ptr(&mce_timer);
-	int cpu = smp_processor_id();
 	unsigned long iv;
 
-	WARN_ON(cpu != data);
-
 	iv = __this_cpu_read(mce_next_interval);
 
 	if (mce_available(this_cpu_ptr(&cpu_info))) {
@@ -1363,7 +1351,7 @@ static void mce_timer_fn(unsigned long d
 
 done:
 	__this_cpu_write(mce_next_interval, iv);
-	__restart_timer(t, iv);
+	return __restart_timer(timer, iv);
 }
 
 /*
@@ -1371,7 +1359,7 @@ done:
  */
 void mce_timer_kick(unsigned long interval)
 {
-	struct timer_list *t = this_cpu_ptr(&mce_timer);
+	struct hrtimer *t = this_cpu_ptr(&mce_timer);
 	unsigned long iv = __this_cpu_read(mce_next_interval);
 
 	__restart_timer(t, interval);
@@ -1386,7 +1374,7 @@ static void mce_timer_delete_all(void)
 	int cpu;
 
 	for_each_online_cpu(cpu)
-		del_timer_sync(&per_cpu(mce_timer, cpu));
+		hrtimer_cancel(&per_cpu(mce_timer, cpu));
 }
 
 static void mce_do_trigger(struct work_struct *work)
@@ -1396,6 +1384,56 @@ static void mce_do_trigger(struct work_s
 
 static DECLARE_WORK(mce_trigger_work, mce_do_trigger);
 
+static void __mce_notify_work(struct swork_event *event)
+{
+	/* Not more than two messages every minute */
+	static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2);
+
+	/* wake processes polling /dev/mcelog */
+	wake_up_interruptible(&mce_chrdev_wait);
+
+	/*
+	 * There is no risk of missing notifications because
+	 * work_pending is always cleared before the function is
+	 * executed.
+	 */
+	if (mce_helper[0] && !work_pending(&mce_trigger_work))
+		schedule_work(&mce_trigger_work);
+
+	if (__ratelimit(&ratelimit))
+		pr_info(HW_ERR "Machine check events logged\n");
+}
+
+#ifdef CONFIG_PREEMPT_RT_FULL
+static bool notify_work_ready __read_mostly;
+static struct swork_event notify_work;
+
+static int mce_notify_work_init(void)
+{
+	int err;
+
+	err = swork_get();
+	if (err)
+		return err;
+
+	INIT_SWORK(&notify_work, __mce_notify_work);
+	notify_work_ready = true;
+	return 0;
+}
+
+static void mce_notify_work(void)
+{
+	if (notify_work_ready)
+		swork_queue(&notify_work);
+}
+#else
+static void mce_notify_work(void)
+{
+	__mce_notify_work(NULL);
+}
+static inline int mce_notify_work_init(void) { return 0; }
+#endif
+
 /*
  * Notify the user(s) about new machine check events.
  * Can be called from interrupt context, but not from machine check/NMI
@@ -1403,19 +1441,8 @@ static DECLARE_WORK(mce_trigger_work, mc
  */
 int mce_notify_irq(void)
 {
-	/* Not more than two messages every minute */
-	static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2);
-
 	if (test_and_clear_bit(0, &mce_need_notify)) {
-		/* wake processes polling /dev/mcelog */
-		wake_up_interruptible(&mce_chrdev_wait);
-
-		if (mce_helper[0])
-			schedule_work(&mce_trigger_work);
-
-		if (__ratelimit(&ratelimit))
-			pr_info(HW_ERR "Machine check events logged\n");
-
+		mce_notify_work();
 		return 1;
 	}
 	return 0;
@@ -1721,7 +1748,7 @@ static void __mcheck_cpu_clear_vendor(st
 	}
 }
 
-static void mce_start_timer(unsigned int cpu, struct timer_list *t)
+static void mce_start_timer(unsigned int cpu, struct hrtimer *t)
 {
 	unsigned long iv = check_interval * HZ;
 
@@ -1730,16 +1757,17 @@ static void mce_start_timer(unsigned int
 
 	per_cpu(mce_next_interval, cpu) = iv;
 
-	t->expires = round_jiffies(jiffies + iv);
-	add_timer_on(t, cpu);
+	hrtimer_start_range_ns(t, ns_to_ktime(jiffies_to_usecs(iv) * 1000ULL),
+			0, HRTIMER_MODE_REL_PINNED);
 }
 
 static void __mcheck_cpu_init_timer(void)
 {
-	struct timer_list *t = this_cpu_ptr(&mce_timer);
+	struct hrtimer *t = this_cpu_ptr(&mce_timer);
 	unsigned int cpu = smp_processor_id();
 
-	setup_pinned_timer(t, mce_timer_fn, cpu);
+	hrtimer_init(t, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	t->function = mce_timer_fn;
 	mce_start_timer(cpu, t);
 }
 
@@ -2464,6 +2492,8 @@ static void mce_disable_cpu(void *h)
 	if (!mce_available(raw_cpu_ptr(&cpu_info)))
 		return;
 
+	hrtimer_cancel(this_cpu_ptr(&mce_timer));
+
 	if (!(action & CPU_TASKS_FROZEN))
 		cmci_clear();
 
@@ -2486,6 +2516,7 @@ static void mce_reenable_cpu(void *h)
 		if (b->init)
 			wrmsrl(msr_ops.ctl(i), b->ctl);
 	}
+	__mcheck_cpu_init_timer();
 }
 
 /* Get notified when a cpu comes on/off. Be hotplug friendly. */
@@ -2493,7 +2524,6 @@ static int
 mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (unsigned long)hcpu;
-	struct timer_list *t = &per_cpu(mce_timer, cpu);
 
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_ONLINE:
@@ -2513,11 +2543,9 @@ mce_cpu_callback(struct notifier_block *
 		break;
 	case CPU_DOWN_PREPARE:
 		smp_call_function_single(cpu, mce_disable_cpu, &action, 1);
-		del_timer_sync(t);
 		break;
 	case CPU_DOWN_FAILED:
 		smp_call_function_single(cpu, mce_reenable_cpu, &action, 1);
-		mce_start_timer(cpu, t);
 		break;
 	}
 
@@ -2556,6 +2584,10 @@ static __init int mcheck_init_device(voi
 		goto err_out;
 	}
 
+	err = mce_notify_work_init();
+	if (err)
+		goto err_out;
+
 	if (!zalloc_cpumask_var(&mce_device_initialized, GFP_KERNEL)) {
 		err = -ENOMEM;
 		goto err_out;
Index: linux-4.9.20-rt16/arch/x86/kernel/irq_32.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/x86/kernel/irq_32.c
+++ linux-4.9.20-rt16/arch/x86/kernel/irq_32.c
@@ -127,6 +127,7 @@ void irq_ctx_init(int cpu)
 	       cpu, per_cpu(hardirq_stack, cpu),  per_cpu(softirq_stack, cpu));
 }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 void do_softirq_own_stack(void)
 {
 	struct irq_stack *irqstk;
@@ -143,6 +144,7 @@ void do_softirq_own_stack(void)
 
 	call_on_stack(__do_softirq, isp);
 }
+#endif
 
 bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
 {
Index: linux-4.9.20-rt16/arch/x86/kernel/process_32.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/x86/kernel/process_32.c
+++ linux-4.9.20-rt16/arch/x86/kernel/process_32.c
@@ -35,6 +35,7 @@
 #include <linux/uaccess.h>
 #include <linux/io.h>
 #include <linux/kdebug.h>
+#include <linux/highmem.h>
 
 #include <asm/pgtable.h>
 #include <asm/ldt.h>
@@ -195,6 +196,35 @@ start_thread(struct pt_regs *regs, unsig
 }
 EXPORT_SYMBOL_GPL(start_thread);
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p)
+{
+	int i;
+
+	/*
+	 * Clear @prev's kmap_atomic mappings
+	 */
+	for (i = 0; i < prev_p->kmap_idx; i++) {
+		int idx = i + KM_TYPE_NR * smp_processor_id();
+		pte_t *ptep = kmap_pte - idx;
+
+		kpte_clear_flush(ptep, __fix_to_virt(FIX_KMAP_BEGIN + idx));
+	}
+	/*
+	 * Restore @next_p's kmap_atomic mappings
+	 */
+	for (i = 0; i < next_p->kmap_idx; i++) {
+		int idx = i + KM_TYPE_NR * smp_processor_id();
+
+		if (!pte_none(next_p->kmap_pte[i]))
+			set_pte(kmap_pte - idx, next_p->kmap_pte[i]);
+	}
+}
+#else
+static inline void
+switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) { }
+#endif
+
 
 /*
  *	switch_to(x,y) should switch tasks from x to y.
@@ -271,6 +301,8 @@ __switch_to(struct task_struct *prev_p,
 		     task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT))
 		__switch_to_xtra(prev_p, next_p, tss);
 
+	switch_kmaps(prev_p, next_p);
+
 	/*
 	 * Leave lazy mode, flushing any hypercalls made here.
 	 * This must be done before restoring TLS segments so
Index: linux-4.9.20-rt16/arch/x86/kvm/lapic.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/x86/kvm/lapic.c
+++ linux-4.9.20-rt16/arch/x86/kvm/lapic.c
@@ -1939,6 +1939,7 @@ int kvm_create_lapic(struct kvm_vcpu *vc
 	hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
 		     HRTIMER_MODE_ABS_PINNED);
 	apic->lapic_timer.timer.function = apic_timer_fn;
+	apic->lapic_timer.timer.irqsafe = 1;
 
 	/*
 	 * APIC is created enabled. This will prevent kvm_lapic_set_base from
Index: linux-4.9.20-rt16/arch/x86/kvm/x86.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/x86/kvm/x86.c
+++ linux-4.9.20-rt16/arch/x86/kvm/x86.c
@@ -5969,6 +5969,13 @@ int kvm_arch_init(void *opaque)
 		goto out;
 	}
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
+		printk(KERN_ERR "RT requires X86_FEATURE_CONSTANT_TSC\n");
+		return -EOPNOTSUPP;
+	}
+#endif
+
 	r = kvm_mmu_module_init();
 	if (r)
 		goto out_free_percpu;
Index: linux-4.9.20-rt16/arch/x86/mm/highmem_32.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/x86/mm/highmem_32.c
+++ linux-4.9.20-rt16/arch/x86/mm/highmem_32.c
@@ -32,10 +32,11 @@ EXPORT_SYMBOL(kunmap);
  */
 void *kmap_atomic_prot(struct page *page, pgprot_t prot)
 {
+	pte_t pte = mk_pte(page, prot);
 	unsigned long vaddr;
 	int idx, type;
 
-	preempt_disable();
+	preempt_disable_nort();
 	pagefault_disable();
 
 	if (!PageHighMem(page))
@@ -45,7 +46,10 @@ void *kmap_atomic_prot(struct page *page
 	idx = type + KM_TYPE_NR*smp_processor_id();
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
 	BUG_ON(!pte_none(*(kmap_pte-idx)));
-	set_pte(kmap_pte-idx, mk_pte(page, prot));
+#ifdef CONFIG_PREEMPT_RT_FULL
+	current->kmap_pte[type] = pte;
+#endif
+	set_pte(kmap_pte-idx, pte);
 	arch_flush_lazy_mmu_mode();
 
 	return (void *)vaddr;
@@ -88,6 +92,9 @@ void __kunmap_atomic(void *kvaddr)
 		 * is a bad idea also, in case the page changes cacheability
 		 * attributes or becomes a protected page in a hypervisor.
 		 */
+#ifdef CONFIG_PREEMPT_RT_FULL
+		current->kmap_pte[type] = __pte(0);
+#endif
 		kpte_clear_flush(kmap_pte-idx, vaddr);
 		kmap_atomic_idx_pop();
 		arch_flush_lazy_mmu_mode();
@@ -100,7 +107,7 @@ void __kunmap_atomic(void *kvaddr)
 #endif
 
 	pagefault_enable();
-	preempt_enable();
+	preempt_enable_nort();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
 
Index: linux-4.9.20-rt16/arch/x86/mm/iomap_32.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/x86/mm/iomap_32.c
+++ linux-4.9.20-rt16/arch/x86/mm/iomap_32.c
@@ -56,6 +56,7 @@ EXPORT_SYMBOL_GPL(iomap_free);
 
 void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot)
 {
+	pte_t pte = pfn_pte(pfn, prot);
 	unsigned long vaddr;
 	int idx, type;
 
@@ -65,7 +66,12 @@ void *kmap_atomic_prot_pfn(unsigned long
 	type = kmap_atomic_idx_push();
 	idx = type + KM_TYPE_NR * smp_processor_id();
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-	set_pte(kmap_pte - idx, pfn_pte(pfn, prot));
+	WARN_ON(!pte_none(*(kmap_pte - idx)));
+
+#ifdef CONFIG_PREEMPT_RT_FULL
+	current->kmap_pte[type] = pte;
+#endif
+	set_pte(kmap_pte - idx, pte);
 	arch_flush_lazy_mmu_mode();
 
 	return (void *)vaddr;
@@ -113,6 +119,9 @@ iounmap_atomic(void __iomem *kvaddr)
 		 * is a bad idea also, in case the page changes cacheability
 		 * attributes or becomes a protected page in a hypervisor.
 		 */
+#ifdef CONFIG_PREEMPT_RT_FULL
+		current->kmap_pte[type] = __pte(0);
+#endif
 		kpte_clear_flush(kmap_pte-idx, vaddr);
 		kmap_atomic_idx_pop();
 	}
Index: linux-4.9.20-rt16/arch/x86/mm/pageattr.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/x86/mm/pageattr.c
+++ linux-4.9.20-rt16/arch/x86/mm/pageattr.c
@@ -214,7 +214,15 @@ static void cpa_flush_array(unsigned lon
 			    int in_flags, struct page **pages)
 {
 	unsigned int i, level;
+#ifdef CONFIG_PREEMPT
+	/*
+	 * Avoid wbinvd() because it causes latencies on all CPUs,
+	 * regardless of any CPU isolation that may be in effect.
+	 */
+	unsigned long do_wbinvd = 0;
+#else
 	unsigned long do_wbinvd = cache && numpages >= 1024; /* 4M threshold */
+#endif
 
 	BUG_ON(irqs_disabled());
 
Index: linux-4.9.20-rt16/arch/x86/platform/uv/tlb_uv.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/x86/platform/uv/tlb_uv.c
+++ linux-4.9.20-rt16/arch/x86/platform/uv/tlb_uv.c
@@ -748,9 +748,9 @@ static void destination_plugged(struct b
 
 		quiesce_local_uvhub(hmaster);
 
-		spin_lock(&hmaster->queue_lock);
+		raw_spin_lock(&hmaster->queue_lock);
 		reset_with_ipi(&bau_desc->distribution, bcp);
-		spin_unlock(&hmaster->queue_lock);
+		raw_spin_unlock(&hmaster->queue_lock);
 
 		end_uvhub_quiesce(hmaster);
 
@@ -770,9 +770,9 @@ static void destination_timeout(struct b
 
 		quiesce_local_uvhub(hmaster);
 
-		spin_lock(&hmaster->queue_lock);
+		raw_spin_lock(&hmaster->queue_lock);
 		reset_with_ipi(&bau_desc->distribution, bcp);
-		spin_unlock(&hmaster->queue_lock);
+		raw_spin_unlock(&hmaster->queue_lock);
 
 		end_uvhub_quiesce(hmaster);
 
@@ -793,7 +793,7 @@ static void disable_for_period(struct ba
 	cycles_t tm1;
 
 	hmaster = bcp->uvhub_master;
-	spin_lock(&hmaster->disable_lock);
+	raw_spin_lock(&hmaster->disable_lock);
 	if (!bcp->baudisabled) {
 		stat->s_bau_disabled++;
 		tm1 = get_cycles();
@@ -806,7 +806,7 @@ static void disable_for_period(struct ba
 			}
 		}
 	}
-	spin_unlock(&hmaster->disable_lock);
+	raw_spin_unlock(&hmaster->disable_lock);
 }
 
 static void count_max_concurr(int stat, struct bau_control *bcp,
@@ -869,7 +869,7 @@ static void record_send_stats(cycles_t t
  */
 static void uv1_throttle(struct bau_control *hmaster, struct ptc_stats *stat)
 {
-	spinlock_t *lock = &hmaster->uvhub_lock;
+	raw_spinlock_t *lock = &hmaster->uvhub_lock;
 	atomic_t *v;
 
 	v = &hmaster->active_descriptor_count;
@@ -1002,7 +1002,7 @@ static int check_enable(struct bau_contr
 	struct bau_control *hmaster;
 
 	hmaster = bcp->uvhub_master;
-	spin_lock(&hmaster->disable_lock);
+	raw_spin_lock(&hmaster->disable_lock);
 	if (bcp->baudisabled && (get_cycles() >= bcp->set_bau_on_time)) {
 		stat->s_bau_reenabled++;
 		for_each_present_cpu(tcpu) {
@@ -1014,10 +1014,10 @@ static int check_enable(struct bau_contr
 				tbcp->period_giveups = 0;
 			}
 		}
-		spin_unlock(&hmaster->disable_lock);
+		raw_spin_unlock(&hmaster->disable_lock);
 		return 0;
 	}
-	spin_unlock(&hmaster->disable_lock);
+	raw_spin_unlock(&hmaster->disable_lock);
 	return -1;
 }
 
@@ -1940,9 +1940,9 @@ static void __init init_per_cpu_tunables
 		bcp->cong_reps			= congested_reps;
 		bcp->disabled_period		= sec_2_cycles(disabled_period);
 		bcp->giveup_limit		= giveup_limit;
-		spin_lock_init(&bcp->queue_lock);
-		spin_lock_init(&bcp->uvhub_lock);
-		spin_lock_init(&bcp->disable_lock);
+		raw_spin_lock_init(&bcp->queue_lock);
+		raw_spin_lock_init(&bcp->uvhub_lock);
+		raw_spin_lock_init(&bcp->disable_lock);
 	}
 }
 
Index: linux-4.9.20-rt16/arch/x86/platform/uv/uv_time.c
===================================================================
--- linux-4.9.20-rt16.orig/arch/x86/platform/uv/uv_time.c
+++ linux-4.9.20-rt16/arch/x86/platform/uv/uv_time.c
@@ -57,7 +57,7 @@ static DEFINE_PER_CPU(struct clock_event
 
 /* There is one of these allocated per node */
 struct uv_rtc_timer_head {
-	spinlock_t	lock;
+	raw_spinlock_t	lock;
 	/* next cpu waiting for timer, local node relative: */
 	int		next_cpu;
 	/* number of cpus on this node: */
@@ -177,7 +177,7 @@ static __init int uv_rtc_allocate_timers
 				uv_rtc_deallocate_timers();
 				return -ENOMEM;
 			}
-			spin_lock_init(&head->lock);
+			raw_spin_lock_init(&head->lock);
 			head->ncpus = uv_blade_nr_possible_cpus(bid);
 			head->next_cpu = -1;
 			blade_info[bid] = head;
@@ -231,7 +231,7 @@ static int uv_rtc_set_timer(int cpu, u64
 	unsigned long flags;
 	int next_cpu;
 
-	spin_lock_irqsave(&head->lock, flags);
+	raw_spin_lock_irqsave(&head->lock, flags);
 
 	next_cpu = head->next_cpu;
 	*t = expires;
@@ -243,12 +243,12 @@ static int uv_rtc_set_timer(int cpu, u64
 		if (uv_setup_intr(cpu, expires)) {
 			*t = ULLONG_MAX;
 			uv_rtc_find_next_timer(head, pnode);
-			spin_unlock_irqrestore(&head->lock, flags);
+			raw_spin_unlock_irqrestore(&head->lock, flags);
 			return -ETIME;
 		}
 	}
 
-	spin_unlock_irqrestore(&head->lock, flags);
+	raw_spin_unlock_irqrestore(&head->lock, flags);
 	return 0;
 }
 
@@ -267,7 +267,7 @@ static int uv_rtc_unset_timer(int cpu, i
 	unsigned long flags;
 	int rc = 0;
 
-	spin_lock_irqsave(&head->lock, flags);
+	raw_spin_lock_irqsave(&head->lock, flags);
 
 	if ((head->next_cpu == bcpu && uv_read_rtc(NULL) >= *t) || force)
 		rc = 1;
@@ -279,7 +279,7 @@ static int uv_rtc_unset_timer(int cpu, i
 			uv_rtc_find_next_timer(head, pnode);
 	}
 
-	spin_unlock_irqrestore(&head->lock, flags);
+	raw_spin_unlock_irqrestore(&head->lock, flags);
 
 	return rc;
 }
@@ -299,13 +299,18 @@ static int uv_rtc_unset_timer(int cpu, i
 static cycle_t uv_read_rtc(struct clocksource *cs)
 {
 	unsigned long offset;
+	cycle_t cycles;
 
+	preempt_disable();
 	if (uv_get_min_hub_revision_id() == 1)
 		offset = 0;
 	else
 		offset = (uv_blade_processor_id() * L1_CACHE_BYTES) % PAGE_SIZE;
 
-	return (cycle_t)uv_read_local_mmr(UVH_RTC | offset);
+	cycles = (cycle_t)uv_read_local_mmr(UVH_RTC | offset);
+	preempt_enable();
+
+	return cycles;
 }
 
 /*
Index: linux-4.9.20-rt16/block/blk-core.c
===================================================================
--- linux-4.9.20-rt16.orig/block/blk-core.c
+++ linux-4.9.20-rt16/block/blk-core.c
@@ -125,6 +125,9 @@ void blk_rq_init(struct request_queue *q
 
 	INIT_LIST_HEAD(&rq->queuelist);
 	INIT_LIST_HEAD(&rq->timeout_list);
+#ifdef CONFIG_PREEMPT_RT_FULL
+	INIT_WORK(&rq->work, __blk_mq_complete_request_remote_work);
+#endif
 	rq->cpu = -1;
 	rq->q = q;
 	rq->__sector = (sector_t) -1;
@@ -233,7 +236,7 @@ EXPORT_SYMBOL(blk_start_queue_async);
  **/
 void blk_start_queue(struct request_queue *q)
 {
-	WARN_ON(!irqs_disabled());
+	WARN_ON_NONRT(!irqs_disabled());
 
 	queue_flag_clear(QUEUE_FLAG_STOPPED, q);
 	__blk_run_queue(q);
@@ -659,7 +662,7 @@ int blk_queue_enter(struct request_queue
 		if (nowait)
 			return -EBUSY;
 
-		ret = wait_event_interruptible(q->mq_freeze_wq,
+		ret = swait_event_interruptible(q->mq_freeze_wq,
 				!atomic_read(&q->mq_freeze_depth) ||
 				blk_queue_dying(q));
 		if (blk_queue_dying(q))
@@ -679,7 +682,7 @@ static void blk_queue_usage_counter_rele
 	struct request_queue *q =
 		container_of(ref, struct request_queue, q_usage_counter);
 
-	wake_up_all(&q->mq_freeze_wq);
+	swake_up_all(&q->mq_freeze_wq);
 }
 
 static void blk_rq_timed_out_timer(unsigned long data)
@@ -748,7 +751,7 @@ struct request_queue *blk_alloc_queue_no
 	q->bypass_depth = 1;
 	__set_bit(QUEUE_FLAG_BYPASS, &q->queue_flags);
 
-	init_waitqueue_head(&q->mq_freeze_wq);
+	init_swait_queue_head(&q->mq_freeze_wq);
 
 	/*
 	 * Init percpu_ref in atomic mode so that it's faster to shutdown.
@@ -3200,7 +3203,7 @@ static void queue_unplugged(struct reque
 		blk_run_queue_async(q);
 	else
 		__blk_run_queue(q);
-	spin_unlock(q->queue_lock);
+	spin_unlock_irq(q->queue_lock);
 }
 
 static void flush_plug_callbacks(struct blk_plug *plug, bool from_schedule)
@@ -3248,7 +3251,6 @@ EXPORT_SYMBOL(blk_check_plugged);
 void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
 {
 	struct request_queue *q;
-	unsigned long flags;
 	struct request *rq;
 	LIST_HEAD(list);
 	unsigned int depth;
@@ -3268,11 +3270,6 @@ void blk_flush_plug_list(struct blk_plug
 	q = NULL;
 	depth = 0;
 
-	/*
-	 * Save and disable interrupts here, to avoid doing it for every
-	 * queue lock we have to take.
-	 */
-	local_irq_save(flags);
 	while (!list_empty(&list)) {
 		rq = list_entry_rq(list.next);
 		list_del_init(&rq->queuelist);
@@ -3285,7 +3282,7 @@ void blk_flush_plug_list(struct blk_plug
 				queue_unplugged(q, depth, from_schedule);
 			q = rq->q;
 			depth = 0;
-			spin_lock(q->queue_lock);
+			spin_lock_irq(q->queue_lock);
 		}
 
 		/*
@@ -3312,8 +3309,6 @@ void blk_flush_plug_list(struct blk_plug
 	 */
 	if (q)
 		queue_unplugged(q, depth, from_schedule);
-
-	local_irq_restore(flags);
 }
 
 void blk_finish_plug(struct blk_plug *plug)
Index: linux-4.9.20-rt16/block/blk-ioc.c
===================================================================
--- linux-4.9.20-rt16.orig/block/blk-ioc.c
+++ linux-4.9.20-rt16/block/blk-ioc.c
@@ -7,6 +7,7 @@
 #include <linux/bio.h>
 #include <linux/blkdev.h>
 #include <linux/slab.h>
+#include <linux/delay.h>
 
 #include "blk.h"
 
@@ -109,7 +110,7 @@ static void ioc_release_fn(struct work_s
 			spin_unlock(q->queue_lock);
 		} else {
 			spin_unlock_irqrestore(&ioc->lock, flags);
-			cpu_relax();
+			cpu_chill();
 			spin_lock_irqsave_nested(&ioc->lock, flags, 1);
 		}
 	}
@@ -187,7 +188,7 @@ retry:
 			spin_unlock(icq->q->queue_lock);
 		} else {
 			spin_unlock_irqrestore(&ioc->lock, flags);
-			cpu_relax();
+			cpu_chill();
 			goto retry;
 		}
 	}
Index: linux-4.9.20-rt16/block/blk-mq.c
===================================================================
--- linux-4.9.20-rt16.orig/block/blk-mq.c
+++ linux-4.9.20-rt16/block/blk-mq.c
@@ -72,7 +72,7 @@ EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_st
 
 static void blk_mq_freeze_queue_wait(struct request_queue *q)
 {
-	wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter));
+	swait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter));
 }
 
 /*
@@ -110,7 +110,7 @@ void blk_mq_unfreeze_queue(struct reques
 	WARN_ON_ONCE(freeze_depth < 0);
 	if (!freeze_depth) {
 		percpu_ref_reinit(&q->q_usage_counter);
-		wake_up_all(&q->mq_freeze_wq);
+		swake_up_all(&q->mq_freeze_wq);
 	}
 }
 EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);
@@ -129,7 +129,7 @@ void blk_mq_wake_waiters(struct request_
 	 * dying, we need to ensure that processes currently waiting on
 	 * the queue are notified as well.
 	 */
-	wake_up_all(&q->mq_freeze_wq);
+	swake_up_all(&q->mq_freeze_wq);
 }
 
 bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
@@ -177,6 +177,9 @@ static void blk_mq_rq_ctx_init(struct re
 	rq->resid_len = 0;
 	rq->sense = NULL;
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+	INIT_WORK(&rq->work, __blk_mq_complete_request_remote_work);
+#endif
 	INIT_LIST_HEAD(&rq->timeout_list);
 	rq->timeout = 0;
 
@@ -345,6 +348,17 @@ void blk_mq_end_request(struct request *
 }
 EXPORT_SYMBOL(blk_mq_end_request);
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+
+void __blk_mq_complete_request_remote_work(struct work_struct *work)
+{
+	struct request *rq = container_of(work, struct request, work);
+
+	rq->q->softirq_done_fn(rq);
+}
+
+#else
+
 static void __blk_mq_complete_request_remote(void *data)
 {
 	struct request *rq = data;
@@ -352,6 +366,8 @@ static void __blk_mq_complete_request_re
 	rq->q->softirq_done_fn(rq);
 }
 
+#endif
+
 static void blk_mq_ipi_complete_request(struct request *rq)
 {
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
@@ -363,19 +379,23 @@ static void blk_mq_ipi_complete_request(
 		return;
 	}
 
-	cpu = get_cpu();
+	cpu = get_cpu_light();
 	if (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags))
 		shared = cpus_share_cache(cpu, ctx->cpu);
 
 	if (cpu != ctx->cpu && !shared && cpu_online(ctx->cpu)) {
+#ifdef CONFIG_PREEMPT_RT_FULL
+		schedule_work_on(ctx->cpu, &rq->work);
+#else
 		rq->csd.func = __blk_mq_complete_request_remote;
 		rq->csd.info = rq;
 		rq->csd.flags = 0;
 		smp_call_function_single_async(ctx->cpu, &rq->csd);
+#endif
 	} else {
 		rq->q->softirq_done_fn(rq);
 	}
-	put_cpu();
+	put_cpu_light();
 }
 
 static void __blk_mq_complete_request(struct request *rq)
@@ -906,14 +926,14 @@ void blk_mq_run_hw_queue(struct blk_mq_h
 		return;
 
 	if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) {
-		int cpu = get_cpu();
+		int cpu = get_cpu_light();
 		if (cpumask_test_cpu(cpu, hctx->cpumask)) {
 			__blk_mq_run_hw_queue(hctx);
-			put_cpu();
+			put_cpu_light();
 			return;
 		}
 
-		put_cpu();
+		put_cpu_light();
 	}
 
 	kblockd_schedule_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work);
Index: linux-4.9.20-rt16/block/blk-mq.h
===================================================================
--- linux-4.9.20-rt16.orig/block/blk-mq.h
+++ linux-4.9.20-rt16/block/blk-mq.h
@@ -72,12 +72,12 @@ static inline struct blk_mq_ctx *__blk_m
  */
 static inline struct blk_mq_ctx *blk_mq_get_ctx(struct request_queue *q)
 {
-	return __blk_mq_get_ctx(q, get_cpu());
+	return __blk_mq_get_ctx(q, get_cpu_light());
 }
 
 static inline void blk_mq_put_ctx(struct blk_mq_ctx *ctx)
 {
-	put_cpu();
+	put_cpu_light();
 }
 
 struct blk_mq_alloc_data {
Index: linux-4.9.20-rt16/block/blk-softirq.c
===================================================================
--- linux-4.9.20-rt16.orig/block/blk-softirq.c
+++ linux-4.9.20-rt16/block/blk-softirq.c
@@ -51,6 +51,7 @@ static void trigger_softirq(void *data)
 		raise_softirq_irqoff(BLOCK_SOFTIRQ);
 
 	local_irq_restore(flags);
+	preempt_check_resched_rt();
 }
 
 /*
@@ -89,6 +90,7 @@ static int blk_softirq_cpu_dead(unsigned
 			 this_cpu_ptr(&blk_cpu_done));
 	raise_softirq_irqoff(BLOCK_SOFTIRQ);
 	local_irq_enable();
+	preempt_check_resched_rt();
 
 	return 0;
 }
@@ -141,6 +143,7 @@ do_local:
 		goto do_local;
 
 	local_irq_restore(flags);
+	preempt_check_resched_rt();
 }
 
 /**
Index: linux-4.9.20-rt16/block/bounce.c
===================================================================
--- linux-4.9.20-rt16.orig/block/bounce.c
+++ linux-4.9.20-rt16/block/bounce.c
@@ -55,11 +55,11 @@ static void bounce_copy_vec(struct bio_v
 	unsigned long flags;
 	unsigned char *vto;
 
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 	vto = kmap_atomic(to->bv_page);
 	memcpy(vto + to->bv_offset, vfrom, to->bv_len);
 	kunmap_atomic(vto);
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 }
 
 #else /* CONFIG_HIGHMEM */
Index: linux-4.9.20-rt16/crypto/algapi.c
===================================================================
--- linux-4.9.20-rt16.orig/crypto/algapi.c
+++ linux-4.9.20-rt16/crypto/algapi.c
@@ -719,13 +719,13 @@ EXPORT_SYMBOL_GPL(crypto_spawn_tfm2);
 
 int crypto_register_notifier(struct notifier_block *nb)
 {
-	return blocking_notifier_chain_register(&crypto_chain, nb);
+	return srcu_notifier_chain_register(&crypto_chain, nb);
 }
 EXPORT_SYMBOL_GPL(crypto_register_notifier);
 
 int crypto_unregister_notifier(struct notifier_block *nb)
 {
-	return blocking_notifier_chain_unregister(&crypto_chain, nb);
+	return srcu_notifier_chain_unregister(&crypto_chain, nb);
 }
 EXPORT_SYMBOL_GPL(crypto_unregister_notifier);
 
Index: linux-4.9.20-rt16/crypto/api.c
===================================================================
--- linux-4.9.20-rt16.orig/crypto/api.c
+++ linux-4.9.20-rt16/crypto/api.c
@@ -31,7 +31,7 @@ EXPORT_SYMBOL_GPL(crypto_alg_list);
 DECLARE_RWSEM(crypto_alg_sem);
 EXPORT_SYMBOL_GPL(crypto_alg_sem);
 
-BLOCKING_NOTIFIER_HEAD(crypto_chain);
+SRCU_NOTIFIER_HEAD(crypto_chain);
 EXPORT_SYMBOL_GPL(crypto_chain);
 
 static struct crypto_alg *crypto_larval_wait(struct crypto_alg *alg);
@@ -236,10 +236,10 @@ int crypto_probing_notify(unsigned long
 {
 	int ok;
 
-	ok = blocking_notifier_call_chain(&crypto_chain, val, v);
+	ok = srcu_notifier_call_chain(&crypto_chain, val, v);
 	if (ok == NOTIFY_DONE) {
 		request_module("cryptomgr");
-		ok = blocking_notifier_call_chain(&crypto_chain, val, v);
+		ok = srcu_notifier_call_chain(&crypto_chain, val, v);
 	}
 
 	return ok;
Index: linux-4.9.20-rt16/crypto/internal.h
===================================================================
--- linux-4.9.20-rt16.orig/crypto/internal.h
+++ linux-4.9.20-rt16/crypto/internal.h
@@ -47,7 +47,7 @@ struct crypto_larval {
 
 extern struct list_head crypto_alg_list;
 extern struct rw_semaphore crypto_alg_sem;
-extern struct blocking_notifier_head crypto_chain;
+extern struct srcu_notifier_head crypto_chain;
 
 #ifdef CONFIG_PROC_FS
 void __init crypto_init_proc(void);
@@ -146,7 +146,7 @@ static inline int crypto_is_moribund(str
 
 static inline void crypto_notify(unsigned long val, void *v)
 {
-	blocking_notifier_call_chain(&crypto_chain, val, v);
+	srcu_notifier_call_chain(&crypto_chain, val, v);
 }
 
 #endif	/* _CRYPTO_INTERNAL_H */
Index: linux-4.9.20-rt16/drivers/acpi/acpica/acglobal.h
===================================================================
--- linux-4.9.20-rt16.orig/drivers/acpi/acpica/acglobal.h
+++ linux-4.9.20-rt16/drivers/acpi/acpica/acglobal.h
@@ -116,7 +116,7 @@ ACPI_GLOBAL(u8, acpi_gbl_global_lock_pen
  * interrupt level
  */
 ACPI_GLOBAL(acpi_spinlock, acpi_gbl_gpe_lock);	/* For GPE data structs and registers */
-ACPI_GLOBAL(acpi_spinlock, acpi_gbl_hardware_lock);	/* For ACPI H/W except GPE registers */
+ACPI_GLOBAL(acpi_raw_spinlock, acpi_gbl_hardware_lock);	/* For ACPI H/W except GPE registers */
 ACPI_GLOBAL(acpi_spinlock, acpi_gbl_reference_count_lock);
 
 /* Mutex for _OSI support */
Index: linux-4.9.20-rt16/drivers/acpi/acpica/hwregs.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/acpi/acpica/hwregs.c
+++ linux-4.9.20-rt16/drivers/acpi/acpica/hwregs.c
@@ -363,14 +363,14 @@ acpi_status acpi_hw_clear_acpi_status(vo
 			  ACPI_BITMASK_ALL_FIXED_STATUS,
 			  ACPI_FORMAT_UINT64(acpi_gbl_xpm1a_status.address)));
 
-	lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock);
+	raw_spin_lock_irqsave(acpi_gbl_hardware_lock, lock_flags);
 
 	/* Clear the fixed events in PM1 A/B */
 
 	status = acpi_hw_register_write(ACPI_REGISTER_PM1_STATUS,
 					ACPI_BITMASK_ALL_FIXED_STATUS);
 
-	acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags);
+	raw_spin_unlock_irqrestore(acpi_gbl_hardware_lock, lock_flags);
 
 	if (ACPI_FAILURE(status)) {
 		goto exit;
Index: linux-4.9.20-rt16/drivers/acpi/acpica/hwxface.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/acpi/acpica/hwxface.c
+++ linux-4.9.20-rt16/drivers/acpi/acpica/hwxface.c
@@ -373,7 +373,7 @@ acpi_status acpi_write_bit_register(u32
 		return_ACPI_STATUS(AE_BAD_PARAMETER);
 	}
 
-	lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock);
+	raw_spin_lock_irqsave(acpi_gbl_hardware_lock, lock_flags);
 
 	/*
 	 * At this point, we know that the parent register is one of the
@@ -434,7 +434,7 @@ acpi_status acpi_write_bit_register(u32
 
 unlock_and_exit:
 
-	acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags);
+	raw_spin_unlock_irqrestore(acpi_gbl_hardware_lock, lock_flags);
 	return_ACPI_STATUS(status);
 }
 
Index: linux-4.9.20-rt16/drivers/acpi/acpica/utmutex.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/acpi/acpica/utmutex.c
+++ linux-4.9.20-rt16/drivers/acpi/acpica/utmutex.c
@@ -88,7 +88,7 @@ acpi_status acpi_ut_mutex_initialize(voi
 		return_ACPI_STATUS (status);
 	}
 
-	status = acpi_os_create_lock (&acpi_gbl_hardware_lock);
+	status = acpi_os_create_raw_lock (&acpi_gbl_hardware_lock);
 	if (ACPI_FAILURE (status)) {
 		return_ACPI_STATUS (status);
 	}
@@ -145,7 +145,7 @@ void acpi_ut_mutex_terminate(void)
 	/* Delete the spinlocks */
 
 	acpi_os_delete_lock(acpi_gbl_gpe_lock);
-	acpi_os_delete_lock(acpi_gbl_hardware_lock);
+	acpi_os_delete_raw_lock(acpi_gbl_hardware_lock);
 	acpi_os_delete_lock(acpi_gbl_reference_count_lock);
 
 	/* Delete the reader/writer lock */
Index: linux-4.9.20-rt16/drivers/ata/libata-sff.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/ata/libata-sff.c
+++ linux-4.9.20-rt16/drivers/ata/libata-sff.c
@@ -678,9 +678,9 @@ unsigned int ata_sff_data_xfer_noirq(str
 	unsigned long flags;
 	unsigned int consumed;
 
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 	consumed = ata_sff_data_xfer32(dev, buf, buflen, rw);
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 
 	return consumed;
 }
@@ -719,7 +719,7 @@ static void ata_pio_sector(struct ata_qu
 		unsigned long flags;
 
 		/* FIXME: use a bounce buffer */
-		local_irq_save(flags);
+		local_irq_save_nort(flags);
 		buf = kmap_atomic(page);
 
 		/* do the actual data transfer */
@@ -727,7 +727,7 @@ static void ata_pio_sector(struct ata_qu
 				       do_write);
 
 		kunmap_atomic(buf);
-		local_irq_restore(flags);
+		local_irq_restore_nort(flags);
 	} else {
 		buf = page_address(page);
 		ap->ops->sff_data_xfer(qc->dev, buf + offset, qc->sect_size,
@@ -864,7 +864,7 @@ next_sg:
 		unsigned long flags;
 
 		/* FIXME: use bounce buffer */
-		local_irq_save(flags);
+		local_irq_save_nort(flags);
 		buf = kmap_atomic(page);
 
 		/* do the actual data transfer */
@@ -872,7 +872,7 @@ next_sg:
 								count, rw);
 
 		kunmap_atomic(buf);
-		local_irq_restore(flags);
+		local_irq_restore_nort(flags);
 	} else {
 		buf = page_address(page);
 		consumed = ap->ops->sff_data_xfer(dev,  buf + offset,
Index: linux-4.9.20-rt16/drivers/block/zram/zcomp.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/block/zram/zcomp.c
+++ linux-4.9.20-rt16/drivers/block/zram/zcomp.c
@@ -118,12 +118,19 @@ ssize_t zcomp_available_show(const char
 
 struct zcomp_strm *zcomp_stream_get(struct zcomp *comp)
 {
-	return *get_cpu_ptr(comp->stream);
+	struct zcomp_strm *zstrm;
+
+	zstrm = *this_cpu_ptr(comp->stream);
+	spin_lock(&zstrm->zcomp_lock);
+	return zstrm;
 }
 
 void zcomp_stream_put(struct zcomp *comp)
 {
-	put_cpu_ptr(comp->stream);
+	struct zcomp_strm *zstrm;
+
+	zstrm = *this_cpu_ptr(comp->stream);
+	spin_unlock(&zstrm->zcomp_lock);
 }
 
 int zcomp_compress(struct zcomp_strm *zstrm,
@@ -174,6 +181,7 @@ static int __zcomp_cpu_notifier(struct z
 			pr_err("Can't allocate a compression stream\n");
 			return NOTIFY_BAD;
 		}
+		spin_lock_init(&zstrm->zcomp_lock);
 		*per_cpu_ptr(comp->stream, cpu) = zstrm;
 		break;
 	case CPU_DEAD:
Index: linux-4.9.20-rt16/drivers/block/zram/zcomp.h
===================================================================
--- linux-4.9.20-rt16.orig/drivers/block/zram/zcomp.h
+++ linux-4.9.20-rt16/drivers/block/zram/zcomp.h
@@ -14,6 +14,7 @@ struct zcomp_strm {
 	/* compression/decompression buffer */
 	void *buffer;
 	struct crypto_comp *tfm;
+	spinlock_t zcomp_lock;
 };
 
 /* dynamic per-device compression frontend */
Index: linux-4.9.20-rt16/drivers/block/zram/zram_drv.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/block/zram/zram_drv.c
+++ linux-4.9.20-rt16/drivers/block/zram/zram_drv.c
@@ -528,6 +528,8 @@ static struct zram_meta *zram_meta_alloc
 		goto out_error;
 	}
 
+	zram_meta_init_table_locks(meta, disksize);
+
 	return meta;
 
 out_error:
@@ -575,28 +577,28 @@ static int zram_decompress_page(struct z
 	struct zram_meta *meta = zram->meta;
 	unsigned long handle;
 	unsigned int size;
+	struct zcomp_strm *zstrm;
 
-	bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
+	zram_lock_table(&meta->table[index]);
 	handle = meta->table[index].handle;
 	size = zram_get_obj_size(meta, index);
 
 	if (!handle || zram_test_flag(meta, index, ZRAM_ZERO)) {
-		bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+		zram_unlock_table(&meta->table[index]);
 		memset(mem, 0, PAGE_SIZE);
 		return 0;
 	}
 
+	zstrm = zcomp_stream_get(zram->comp);
 	cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_RO);
 	if (size == PAGE_SIZE) {
 		memcpy(mem, cmem, PAGE_SIZE);
 	} else {
-		struct zcomp_strm *zstrm = zcomp_stream_get(zram->comp);
-
 		ret = zcomp_decompress(zstrm, cmem, size, mem);
-		zcomp_stream_put(zram->comp);
 	}
 	zs_unmap_object(meta->mem_pool, handle);
-	bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+	zcomp_stream_put(zram->comp);
+	zram_unlock_table(&meta->table[index]);
 
 	/* Should NEVER happen. Return bio error if it does. */
 	if (unlikely(ret)) {
@@ -616,14 +618,14 @@ static int zram_bvec_read(struct zram *z
 	struct zram_meta *meta = zram->meta;
 	page = bvec->bv_page;
 
-	bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
+	zram_lock_table(&meta->table[index]);
 	if (unlikely(!meta->table[index].handle) ||
 			zram_test_flag(meta, index, ZRAM_ZERO)) {
-		bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+		zram_unlock_table(&meta->table[index]);
 		handle_zero_page(bvec);
 		return 0;
 	}
-	bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+	zram_unlock_table(&meta->table[index]);
 
 	if (is_partial_io(bvec))
 		/* Use  a temporary buffer to decompress the page */
@@ -700,10 +702,10 @@ compress_again:
 		if (user_mem)
 			kunmap_atomic(user_mem);
 		/* Free memory associated with this sector now. */
-		bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
+		zram_lock_table(&meta->table[index]);
 		zram_free_page(zram, index);
 		zram_set_flag(meta, index, ZRAM_ZERO);
-		bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+		zram_unlock_table(&meta->table[index]);
 
 		atomic64_inc(&zram->stats.zero_pages);
 		ret = 0;
@@ -794,12 +796,12 @@ compress_again:
 	 * Free memory associated with this sector
 	 * before overwriting unused sectors.
 	 */
-	bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
+	zram_lock_table(&meta->table[index]);
 	zram_free_page(zram, index);
 
 	meta->table[index].handle = handle;
 	zram_set_obj_size(meta, index, clen);
-	bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+	zram_unlock_table(&meta->table[index]);
 
 	/* Update stats */
 	atomic64_add(clen, &zram->stats.compr_data_size);
@@ -842,9 +844,9 @@ static void zram_bio_discard(struct zram
 	}
 
 	while (n >= PAGE_SIZE) {
-		bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
+		zram_lock_table(&meta->table[index]);
 		zram_free_page(zram, index);
-		bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+		zram_unlock_table(&meta->table[index]);
 		atomic64_inc(&zram->stats.notify_free);
 		index++;
 		n -= PAGE_SIZE;
@@ -973,9 +975,9 @@ static void zram_slot_free_notify(struct
 	zram = bdev->bd_disk->private_data;
 	meta = zram->meta;
 
-	bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value);
+	zram_lock_table(&meta->table[index]);
 	zram_free_page(zram, index);
-	bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+	zram_unlock_table(&meta->table[index]);
 	atomic64_inc(&zram->stats.notify_free);
 }
 
Index: linux-4.9.20-rt16/drivers/block/zram/zram_drv.h
===================================================================
--- linux-4.9.20-rt16.orig/drivers/block/zram/zram_drv.h
+++ linux-4.9.20-rt16/drivers/block/zram/zram_drv.h
@@ -73,6 +73,9 @@ enum zram_pageflags {
 struct zram_table_entry {
 	unsigned long handle;
 	unsigned long value;
+#ifdef CONFIG_PREEMPT_RT_BASE
+	spinlock_t lock;
+#endif
 };
 
 struct zram_stats {
@@ -120,4 +123,42 @@ struct zram {
 	 */
 	bool claim; /* Protected by bdev->bd_mutex */
 };
+
+#ifndef CONFIG_PREEMPT_RT_BASE
+static inline void zram_lock_table(struct zram_table_entry *table)
+{
+	bit_spin_lock(ZRAM_ACCESS, &table->value);
+}
+
+static inline void zram_unlock_table(struct zram_table_entry *table)
+{
+	bit_spin_unlock(ZRAM_ACCESS, &table->value);
+}
+
+static inline void zram_meta_init_table_locks(struct zram_meta *meta, u64 disksize) { }
+#else /* CONFIG_PREEMPT_RT_BASE */
+static inline void zram_lock_table(struct zram_table_entry *table)
+{
+	spin_lock(&table->lock);
+	__set_bit(ZRAM_ACCESS, &table->value);
+}
+
+static inline void zram_unlock_table(struct zram_table_entry *table)
+{
+	__clear_bit(ZRAM_ACCESS, &table->value);
+	spin_unlock(&table->lock);
+}
+
+static inline void zram_meta_init_table_locks(struct zram_meta *meta, u64 disksize)
+{
+        size_t num_pages = disksize >> PAGE_SHIFT;
+        size_t index;
+
+        for (index = 0; index < num_pages; index++) {
+		spinlock_t *lock = &meta->table[index].lock;
+		spin_lock_init(lock);
+        }
+}
+#endif /* CONFIG_PREEMPT_RT_BASE */
+
 #endif
Index: linux-4.9.20-rt16/drivers/char/random.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/char/random.c
+++ linux-4.9.20-rt16/drivers/char/random.c
@@ -262,6 +262,7 @@
 #include <linux/syscalls.h>
 #include <linux/completion.h>
 #include <linux/uuid.h>
+#include <linux/locallock.h>
 #include <crypto/chacha20.h>
 
 #include <asm/processor.h>
@@ -1028,8 +1029,6 @@ static void add_timer_randomness(struct
 	} sample;
 	long delta, delta2, delta3;
 
-	preempt_disable();
-
 	sample.jiffies = jiffies;
 	sample.cycles = random_get_entropy();
 	sample.num = num;
@@ -1070,7 +1069,6 @@ static void add_timer_randomness(struct
 		 */
 		credit_entropy_bits(r, min_t(int, fls(delta>>1), 11));
 	}
-	preempt_enable();
 }
 
 void add_input_randomness(unsigned int type, unsigned int code,
@@ -1123,28 +1121,27 @@ static __u32 get_reg(struct fast_pool *f
 	return *(ptr + f->reg_idx++);
 }
 
-void add_interrupt_randomness(int irq, int irq_flags)
+void add_interrupt_randomness(int irq, int irq_flags, __u64 ip)
 {
 	struct entropy_store	*r;
 	struct fast_pool	*fast_pool = this_cpu_ptr(&irq_randomness);
-	struct pt_regs		*regs = get_irq_regs();
 	unsigned long		now = jiffies;
 	cycles_t		cycles = random_get_entropy();
 	__u32			c_high, j_high;
-	__u64			ip;
 	unsigned long		seed;
 	int			credit = 0;
 
 	if (cycles == 0)
-		cycles = get_reg(fast_pool, regs);
+		cycles = get_reg(fast_pool, NULL);
 	c_high = (sizeof(cycles) > 4) ? cycles >> 32 : 0;
 	j_high = (sizeof(now) > 4) ? now >> 32 : 0;
 	fast_pool->pool[0] ^= cycles ^ j_high ^ irq;
 	fast_pool->pool[1] ^= now ^ c_high;
-	ip = regs ? instruction_pointer(regs) : _RET_IP_;
+	if (!ip)
+		ip = _RET_IP_;
 	fast_pool->pool[2] ^= ip;
 	fast_pool->pool[3] ^= (sizeof(ip) > 4) ? ip >> 32 :
-		get_reg(fast_pool, regs);
+		get_reg(fast_pool, NULL);
 
 	fast_mix(fast_pool);
 	add_interrupt_bench(cycles);
@@ -2056,6 +2053,7 @@ struct batched_entropy {
  * goal of being quite fast and not depleting entropy.
  */
 static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_long);
+static DEFINE_LOCAL_IRQ_LOCK(batched_entropy_long_lock);
 unsigned long get_random_long(void)
 {
 	unsigned long ret;
@@ -2064,13 +2062,13 @@ unsigned long get_random_long(void)
 	if (arch_get_random_long(&ret))
 		return ret;
 
-	batch = &get_cpu_var(batched_entropy_long);
+	batch = &get_locked_var(batched_entropy_long_lock, batched_entropy_long);
 	if (batch->position % ARRAY_SIZE(batch->entropy_long) == 0) {
 		extract_crng((u8 *)batch->entropy_long);
 		batch->position = 0;
 	}
 	ret = batch->entropy_long[batch->position++];
-	put_cpu_var(batched_entropy_long);
+	put_locked_var(batched_entropy_long_lock, batched_entropy_long);
 	return ret;
 }
 EXPORT_SYMBOL(get_random_long);
@@ -2082,6 +2080,8 @@ unsigned int get_random_int(void)
 }
 #else
 static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_int);
+static DEFINE_LOCAL_IRQ_LOCK(batched_entropy_int_lock);
+
 unsigned int get_random_int(void)
 {
 	unsigned int ret;
@@ -2090,13 +2090,13 @@ unsigned int get_random_int(void)
 	if (arch_get_random_int(&ret))
 		return ret;
 
-	batch = &get_cpu_var(batched_entropy_int);
+	batch = &get_locked_var(batched_entropy_int_lock, batched_entropy_int);
 	if (batch->position % ARRAY_SIZE(batch->entropy_int) == 0) {
 		extract_crng((u8 *)batch->entropy_int);
 		batch->position = 0;
 	}
 	ret = batch->entropy_int[batch->position++];
-	put_cpu_var(batched_entropy_int);
+	put_locked_var(batched_entropy_int_lock, batched_entropy_int);
 	return ret;
 }
 #endif
Index: linux-4.9.20-rt16/drivers/clocksource/tcb_clksrc.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/clocksource/tcb_clksrc.c
+++ linux-4.9.20-rt16/drivers/clocksource/tcb_clksrc.c
@@ -23,8 +23,7 @@
  *     this 32 bit free-running counter. the second channel is not used.
  *
  *   - The third channel may be used to provide a 16-bit clockevent
- *     source, used in either periodic or oneshot mode.  This runs
- *     at 32 KiHZ, and can handle delays of up to two seconds.
+ *     source, used in either periodic or oneshot mode.
  *
  * A boot clocksource and clockevent source are also currently needed,
  * unless the relevant platforms (ARM/AT91, AVR32/AT32) are changed so
@@ -74,6 +73,8 @@ static struct clocksource clksrc = {
 struct tc_clkevt_device {
 	struct clock_event_device	clkevt;
 	struct clk			*clk;
+	bool				clk_enabled;
+	u32				freq;
 	void __iomem			*regs;
 };
 
@@ -82,15 +83,26 @@ static struct tc_clkevt_device *to_tc_cl
 	return container_of(clkevt, struct tc_clkevt_device, clkevt);
 }
 
-/* For now, we always use the 32K clock ... this optimizes for NO_HZ,
- * because using one of the divided clocks would usually mean the
- * tick rate can never be less than several dozen Hz (vs 0.5 Hz).
- *
- * A divided clock could be good for high resolution timers, since
- * 30.5 usec resolution can seem "low".
- */
 static u32 timer_clock;
 
+static void tc_clk_disable(struct clock_event_device *d)
+{
+	struct tc_clkevt_device *tcd = to_tc_clkevt(d);
+
+	clk_disable(tcd->clk);
+	tcd->clk_enabled = false;
+}
+
+static void tc_clk_enable(struct clock_event_device *d)
+{
+	struct tc_clkevt_device *tcd = to_tc_clkevt(d);
+
+	if (tcd->clk_enabled)
+		return;
+	clk_enable(tcd->clk);
+	tcd->clk_enabled = true;
+}
+
 static int tc_shutdown(struct clock_event_device *d)
 {
 	struct tc_clkevt_device *tcd = to_tc_clkevt(d);
@@ -98,8 +110,14 @@ static int tc_shutdown(struct clock_even
 
 	__raw_writel(0xff, regs + ATMEL_TC_REG(2, IDR));
 	__raw_writel(ATMEL_TC_CLKDIS, regs + ATMEL_TC_REG(2, CCR));
+	return 0;
+}
+
+static int tc_shutdown_clk_off(struct clock_event_device *d)
+{
+	tc_shutdown(d);
 	if (!clockevent_state_detached(d))
-		clk_disable(tcd->clk);
+		tc_clk_disable(d);
 
 	return 0;
 }
@@ -112,9 +130,9 @@ static int tc_set_oneshot(struct clock_e
 	if (clockevent_state_oneshot(d) || clockevent_state_periodic(d))
 		tc_shutdown(d);
 
-	clk_enable(tcd->clk);
+	tc_clk_enable(d);
 
-	/* slow clock, count up to RC, then irq and stop */
+	/* count up to RC, then irq and stop */
 	__raw_writel(timer_clock | ATMEL_TC_CPCSTOP | ATMEL_TC_WAVE |
 		     ATMEL_TC_WAVESEL_UP_AUTO, regs + ATMEL_TC_REG(2, CMR));
 	__raw_writel(ATMEL_TC_CPCS, regs + ATMEL_TC_REG(2, IER));
@@ -134,12 +152,12 @@ static int tc_set_periodic(struct clock_
 	/* By not making the gentime core emulate periodic mode on top
 	 * of oneshot, we get lower overhead and improved accuracy.
 	 */
-	clk_enable(tcd->clk);
+	tc_clk_enable(d);
 
-	/* slow clock, count up to RC, then irq and restart */
+	/* count up to RC, then irq and restart */
 	__raw_writel(timer_clock | ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP_AUTO,
 		     regs + ATMEL_TC_REG(2, CMR));
-	__raw_writel((32768 + HZ / 2) / HZ, tcaddr + ATMEL_TC_REG(2, RC));
+	__raw_writel((tcd->freq + HZ / 2) / HZ, tcaddr + ATMEL_TC_REG(2, RC));
 
 	/* Enable clock and interrupts on RC compare */
 	__raw_writel(ATMEL_TC_CPCS, regs + ATMEL_TC_REG(2, IER));
@@ -166,9 +184,13 @@ static struct tc_clkevt_device clkevt =
 		.features		= CLOCK_EVT_FEAT_PERIODIC |
 					  CLOCK_EVT_FEAT_ONESHOT,
 		/* Should be lower than at91rm9200's system timer */
+#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK
 		.rating			= 125,
+#else
+		.rating			= 200,
+#endif
 		.set_next_event		= tc_next_event,
-		.set_state_shutdown	= tc_shutdown,
+		.set_state_shutdown	= tc_shutdown_clk_off,
 		.set_state_periodic	= tc_set_periodic,
 		.set_state_oneshot	= tc_set_oneshot,
 	},
@@ -188,8 +210,9 @@ static irqreturn_t ch2_irq(int irq, void
 	return IRQ_NONE;
 }
 
-static int __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx)
+static int __init setup_clkevents(struct atmel_tc *tc, int divisor_idx)
 {
+	unsigned divisor = atmel_tc_divisors[divisor_idx];
 	int ret;
 	struct clk *t2_clk = tc->clk[2];
 	int irq = tc->irq[2];
@@ -210,7 +233,11 @@ static int __init setup_clkevents(struct
 	clkevt.regs = tc->regs;
 	clkevt.clk = t2_clk;
 
-	timer_clock = clk32k_divisor_idx;
+	timer_clock = divisor_idx;
+	if (!divisor)
+		clkevt.freq = 32768;
+	else
+		clkevt.freq = clk_get_rate(t2_clk) / divisor;
 
 	clkevt.clkevt.cpumask = cpumask_of(0);
 
@@ -221,7 +248,7 @@ static int __init setup_clkevents(struct
 		return ret;
 	}
 
-	clockevents_config_and_register(&clkevt.clkevt, 32768, 1, 0xffff);
+	clockevents_config_and_register(&clkevt.clkevt, clkevt.freq, 1, 0xffff);
 
 	return ret;
 }
@@ -358,7 +385,11 @@ static int __init tcb_clksrc_init(void)
 		goto err_disable_t1;
 
 	/* channel 2:  periodic and oneshot timer support */
+#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK
 	ret = setup_clkevents(tc, clk32k_divisor_idx);
+#else
+	ret = setup_clkevents(tc, best_divisor_idx);
+#endif
 	if (ret)
 		goto err_unregister_clksrc;
 
Index: linux-4.9.20-rt16/drivers/clocksource/timer-atmel-pit.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/clocksource/timer-atmel-pit.c
+++ linux-4.9.20-rt16/drivers/clocksource/timer-atmel-pit.c
@@ -46,6 +46,7 @@ struct pit_data {
 	u32		cycle;
 	u32		cnt;
 	unsigned int	irq;
+	bool		irq_requested;
 	struct clk	*mck;
 };
 
@@ -96,15 +97,29 @@ static int pit_clkevt_shutdown(struct cl
 
 	/* disable irq, leaving the clocksource active */
 	pit_write(data->base, AT91_PIT_MR, (data->cycle - 1) | AT91_PIT_PITEN);
+	if (data->irq_requested) {
+		free_irq(data->irq, data);
+		data->irq_requested = false;
+	}
 	return 0;
 }
 
+static irqreturn_t at91sam926x_pit_interrupt(int irq, void *dev_id);
 /*
  * Clockevent device:  interrupts every 1/HZ (== pit_cycles * MCK/16)
  */
 static int pit_clkevt_set_periodic(struct clock_event_device *dev)
 {
 	struct pit_data *data = clkevt_to_pit_data(dev);
+	int ret;
+
+	ret = request_irq(data->irq, at91sam926x_pit_interrupt,
+			  IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL,
+			  "at91_tick", data);
+	if (ret)
+		panic(pr_fmt("Unable to setup IRQ\n"));
+
+	data->irq_requested = true;
 
 	/* update clocksource counter */
 	data->cnt += data->cycle * PIT_PICNT(pit_read(data->base, AT91_PIT_PIVR));
@@ -230,15 +245,6 @@ static int __init at91sam926x_pit_dt_ini
 		return ret;
 	}
 
-	/* Set up irq handler */
-	ret = request_irq(data->irq, at91sam926x_pit_interrupt,
-			  IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL,
-			  "at91_tick", data);
-	if (ret) {
-		pr_err("Unable to setup IRQ\n");
-		return ret;
-	}
-
 	/* Set up and register clockevents */
 	data->clkevt.name = "pit";
 	data->clkevt.features = CLOCK_EVT_FEAT_PERIODIC;
Index: linux-4.9.20-rt16/drivers/clocksource/timer-atmel-st.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/clocksource/timer-atmel-st.c
+++ linux-4.9.20-rt16/drivers/clocksource/timer-atmel-st.c
@@ -115,18 +115,29 @@ static void clkdev32k_disable_and_flush_
 	last_crtr = read_CRTR();
 }
 
+static int atmel_st_irq;
+
 static int clkevt32k_shutdown(struct clock_event_device *evt)
 {
 	clkdev32k_disable_and_flush_irq();
 	irqmask = 0;
 	regmap_write(regmap_st, AT91_ST_IER, irqmask);
+	free_irq(atmel_st_irq, regmap_st);
 	return 0;
 }
 
 static int clkevt32k_set_oneshot(struct clock_event_device *dev)
 {
+	int ret;
+
 	clkdev32k_disable_and_flush_irq();
 
+	ret = request_irq(atmel_st_irq, at91rm9200_timer_interrupt,
+			  IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL,
+			  "at91_tick", regmap_st);
+	if (ret)
+		panic(pr_fmt("Unable to setup IRQ\n"));
+
 	/*
 	 * ALM for oneshot irqs, set by next_event()
 	 * before 32 seconds have passed.
@@ -139,8 +150,16 @@ static int clkevt32k_set_oneshot(struct
 
 static int clkevt32k_set_periodic(struct clock_event_device *dev)
 {
+	int ret;
+
 	clkdev32k_disable_and_flush_irq();
 
+	ret = request_irq(atmel_st_irq, at91rm9200_timer_interrupt,
+			  IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL,
+			  "at91_tick", regmap_st);
+	if (ret)
+		panic(pr_fmt("Unable to setup IRQ\n"));
+
 	/* PIT for periodic irqs; fixed rate of 1/HZ */
 	irqmask = AT91_ST_PITS;
 	regmap_write(regmap_st, AT91_ST_PIMR, timer_latch);
@@ -198,7 +217,7 @@ static int __init atmel_st_timer_init(st
 {
 	struct clk *sclk;
 	unsigned int sclk_rate, val;
-	int irq, ret;
+	int ret;
 
 	regmap_st = syscon_node_to_regmap(node);
 	if (IS_ERR(regmap_st)) {
@@ -212,21 +231,12 @@ static int __init atmel_st_timer_init(st
 	regmap_read(regmap_st, AT91_ST_SR, &val);
 
 	/* Get the interrupts property */
-	irq  = irq_of_parse_and_map(node, 0);
-	if (!irq) {
+	atmel_st_irq  = irq_of_parse_and_map(node, 0);
+	if (!atmel_st_irq) {
 		pr_err("Unable to get IRQ from DT\n");
 		return -EINVAL;
 	}
 
-	/* Make IRQs happen for the system timer */
-	ret = request_irq(irq, at91rm9200_timer_interrupt,
-			  IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL,
-			  "at91_tick", regmap_st);
-	if (ret) {
-		pr_err("Unable to setup IRQ\n");
-		return ret;
-	}
-
 	sclk = of_clk_get(node, 0);
 	if (IS_ERR(sclk)) {
 		pr_err("Unable to get slow clock\n");
Index: linux-4.9.20-rt16/drivers/connector/cn_proc.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/connector/cn_proc.c
+++ linux-4.9.20-rt16/drivers/connector/cn_proc.c
@@ -32,6 +32,7 @@
 #include <linux/pid_namespace.h>
 
 #include <linux/cn_proc.h>
+#include <linux/locallock.h>
 
 /*
  * Size of a cn_msg followed by a proc_event structure.  Since the
@@ -54,10 +55,11 @@ static struct cb_id cn_proc_event_id = {
 
 /* proc_event_counts is used as the sequence number of the netlink message */
 static DEFINE_PER_CPU(__u32, proc_event_counts) = { 0 };
+static DEFINE_LOCAL_IRQ_LOCK(send_msg_lock);
 
 static inline void send_msg(struct cn_msg *msg)
 {
-	preempt_disable();
+	local_lock(send_msg_lock);
 
 	msg->seq = __this_cpu_inc_return(proc_event_counts) - 1;
 	((struct proc_event *)msg->data)->cpu = smp_processor_id();
@@ -70,7 +72,7 @@ static inline void send_msg(struct cn_ms
 	 */
 	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_NOWAIT);
 
-	preempt_enable();
+	local_unlock(send_msg_lock);
 }
 
 void proc_fork_connector(struct task_struct *task)
Index: linux-4.9.20-rt16/drivers/cpufreq/Kconfig.x86
===================================================================
--- linux-4.9.20-rt16.orig/drivers/cpufreq/Kconfig.x86
+++ linux-4.9.20-rt16/drivers/cpufreq/Kconfig.x86
@@ -124,7 +124,7 @@ config X86_POWERNOW_K7_ACPI
 
 config X86_POWERNOW_K8
 	tristate "AMD Opteron/Athlon64 PowerNow!"
-	depends on ACPI && ACPI_PROCESSOR && X86_ACPI_CPUFREQ
+	depends on ACPI && ACPI_PROCESSOR && X86_ACPI_CPUFREQ && !PREEMPT_RT_BASE
 	help
 	  This adds the CPUFreq driver for K8/early Opteron/Athlon64 processors.
 	  Support for K10 and newer processors is now in acpi-cpufreq.
Index: linux-4.9.20-rt16/drivers/gpu/drm/i915/i915_gem_execbuffer.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ linux-4.9.20-rt16/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1489,7 +1489,9 @@ execbuf_submit(struct i915_execbuffer_pa
 	if (ret)
 		return ret;
 
+#ifndef CONFIG_PREEMPT_RT_BASE
 	trace_i915_gem_ring_dispatch(params->request, params->dispatch_flags);
+#endif
 
 	i915_gem_execbuffer_move_to_active(vmas, params->request);
 
Index: linux-4.9.20-rt16/drivers/gpu/drm/i915/i915_gem_shrinker.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ linux-4.9.20-rt16/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -40,7 +40,7 @@ static bool mutex_is_locked_by(struct mu
 	if (!mutex_is_locked(mutex))
 		return false;
 
-#if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_MUTEX_SPIN_ON_OWNER)
+#if (defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_MUTEX_SPIN_ON_OWNER)) && !defined(CONFIG_PREEMPT_RT_BASE)
 	return mutex->owner == task;
 #else
 	/* Since UP may be pre-empted, we cannot assume that we own the lock */
Index: linux-4.9.20-rt16/drivers/gpu/drm/i915/i915_irq.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/gpu/drm/i915/i915_irq.c
+++ linux-4.9.20-rt16/drivers/gpu/drm/i915/i915_irq.c
@@ -812,6 +812,7 @@ static int i915_get_crtc_scanoutpos(stru
 	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
 
 	/* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */
+	preempt_disable_rt();
 
 	/* Get optional system timestamp before query. */
 	if (stime)
@@ -863,6 +864,7 @@ static int i915_get_crtc_scanoutpos(stru
 		*etime = ktime_get();
 
 	/* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */
+	preempt_enable_rt();
 
 	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
 
Index: linux-4.9.20-rt16/drivers/gpu/drm/i915/intel_display.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/gpu/drm/i915/intel_display.c
+++ linux-4.9.20-rt16/drivers/gpu/drm/i915/intel_display.c
@@ -12134,7 +12134,7 @@ void intel_check_page_flip(struct drm_i9
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_flip_work *work;
 
-	WARN_ON(!in_interrupt());
+	WARN_ON_NONRT(!in_interrupt());
 
 	if (crtc == NULL)
 		return;
Index: linux-4.9.20-rt16/drivers/gpu/drm/i915/intel_sprite.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/gpu/drm/i915/intel_sprite.c
+++ linux-4.9.20-rt16/drivers/gpu/drm/i915/intel_sprite.c
@@ -35,6 +35,7 @@
 #include <drm/drm_rect.h>
 #include <drm/drm_atomic.h>
 #include <drm/drm_plane_helper.h>
+#include <linux/locallock.h>
 #include "intel_drv.h"
 #include "intel_frontbuffer.h"
 #include <drm/i915_drm.h>
@@ -65,6 +66,8 @@ int intel_usecs_to_scanlines(const struc
 			    1000 * adjusted_mode->crtc_htotal);
 }
 
+static DEFINE_LOCAL_IRQ_LOCK(pipe_update_lock);
+
 /**
  * intel_pipe_update_start() - start update of a set of display registers
  * @crtc: the crtc of which the registers are going to be updated
@@ -98,7 +101,7 @@ void intel_pipe_update_start(struct inte
 	min = vblank_start - intel_usecs_to_scanlines(adjusted_mode, 100);
 	max = vblank_start - 1;
 
-	local_irq_disable();
+	local_lock_irq(pipe_update_lock);
 
 	if (min <= 0 || max <= 0)
 		return;
@@ -128,11 +131,11 @@ void intel_pipe_update_start(struct inte
 			break;
 		}
 
-		local_irq_enable();
+		local_unlock_irq(pipe_update_lock);
 
 		timeout = schedule_timeout(timeout);
 
-		local_irq_disable();
+		local_lock_irq(pipe_update_lock);
 	}
 
 	finish_wait(wq, &wait);
@@ -202,7 +205,7 @@ void intel_pipe_update_end(struct intel_
 		crtc->base.state->event = NULL;
 	}
 
-	local_irq_enable();
+	local_unlock_irq(pipe_update_lock);
 
 	if (crtc->debug.start_vbl_count &&
 	    crtc->debug.start_vbl_count != end_vbl_count) {
Index: linux-4.9.20-rt16/drivers/gpu/drm/msm/msm_gem_shrinker.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/gpu/drm/msm/msm_gem_shrinker.c
+++ linux-4.9.20-rt16/drivers/gpu/drm/msm/msm_gem_shrinker.c
@@ -23,7 +23,7 @@ static bool mutex_is_locked_by(struct mu
 	if (!mutex_is_locked(mutex))
 		return false;
 
-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_MUTEXES)
+#if (defined(CONFIG_SMP) || defined(CONFIG_DEBUG_MUTEXES)) && !defined(CONFIG_PREEMPT_RT_BASE)
 	return mutex->owner == task;
 #else
 	/* Since UP may be pre-empted, we cannot assume that we own the lock */
Index: linux-4.9.20-rt16/drivers/gpu/drm/radeon/radeon_display.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/gpu/drm/radeon/radeon_display.c
+++ linux-4.9.20-rt16/drivers/gpu/drm/radeon/radeon_display.c
@@ -1845,6 +1845,7 @@ int radeon_get_crtc_scanoutpos(struct dr
 	struct radeon_device *rdev = dev->dev_private;
 
 	/* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */
+	preempt_disable_rt();
 
 	/* Get optional system timestamp before query. */
 	if (stime)
@@ -1937,6 +1938,7 @@ int radeon_get_crtc_scanoutpos(struct dr
 		*etime = ktime_get();
 
 	/* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */
+	preempt_enable_rt();
 
 	/* Decode into vertical and horizontal scanout position. */
 	*vpos = position & 0x1fff;
Index: linux-4.9.20-rt16/drivers/hv/vmbus_drv.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/hv/vmbus_drv.c
+++ linux-4.9.20-rt16/drivers/hv/vmbus_drv.c
@@ -761,6 +761,8 @@ static void vmbus_isr(void)
 	void *page_addr;
 	struct hv_message *msg;
 	union hv_synic_event_flags *event;
+	struct pt_regs *regs = get_irq_regs();
+	u64 ip = regs ? instruction_pointer(regs) : 0;
 	bool handled = false;
 
 	page_addr = hv_context.synic_event_page[cpu];
@@ -808,7 +810,7 @@ static void vmbus_isr(void)
 			tasklet_schedule(hv_context.msg_dpc[cpu]);
 	}
 
-	add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0);
+	add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0, ip);
 }
 
 
Index: linux-4.9.20-rt16/drivers/ide/alim15x3.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/ide/alim15x3.c
+++ linux-4.9.20-rt16/drivers/ide/alim15x3.c
@@ -234,7 +234,7 @@ static int init_chipset_ali15x3(struct p
 
 	isa_dev = pci_get_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1533, NULL);
 
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 
 	if (m5229_revision < 0xC2) {
 		/*
@@ -325,7 +325,7 @@ out:
 	}
 	pci_dev_put(north);
 	pci_dev_put(isa_dev);
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 	return 0;
 }
 
Index: linux-4.9.20-rt16/drivers/ide/hpt366.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/ide/hpt366.c
+++ linux-4.9.20-rt16/drivers/ide/hpt366.c
@@ -1236,7 +1236,7 @@ static int init_dma_hpt366(ide_hwif_t *h
 
 	dma_old = inb(base + 2);
 
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 
 	dma_new = dma_old;
 	pci_read_config_byte(dev, hwif->channel ? 0x4b : 0x43, &masterdma);
@@ -1247,7 +1247,7 @@ static int init_dma_hpt366(ide_hwif_t *h
 	if (dma_new != dma_old)
 		outb(dma_new, base + 2);
 
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 
 	printk(KERN_INFO "    %s: BM-DMA at 0x%04lx-0x%04lx\n",
 			 hwif->name, base, base + 7);
Index: linux-4.9.20-rt16/drivers/ide/ide-io-std.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/ide/ide-io-std.c
+++ linux-4.9.20-rt16/drivers/ide/ide-io-std.c
@@ -175,7 +175,7 @@ void ide_input_data(ide_drive_t *drive,
 		unsigned long uninitialized_var(flags);
 
 		if ((io_32bit & 2) && !mmio) {
-			local_irq_save(flags);
+			local_irq_save_nort(flags);
 			ata_vlb_sync(io_ports->nsect_addr);
 		}
 
@@ -186,7 +186,7 @@ void ide_input_data(ide_drive_t *drive,
 			insl(data_addr, buf, words);
 
 		if ((io_32bit & 2) && !mmio)
-			local_irq_restore(flags);
+			local_irq_restore_nort(flags);
 
 		if (((len + 1) & 3) < 2)
 			return;
@@ -219,7 +219,7 @@ void ide_output_data(ide_drive_t *drive,
 		unsigned long uninitialized_var(flags);
 
 		if ((io_32bit & 2) && !mmio) {
-			local_irq_save(flags);
+			local_irq_save_nort(flags);
 			ata_vlb_sync(io_ports->nsect_addr);
 		}
 
@@ -230,7 +230,7 @@ void ide_output_data(ide_drive_t *drive,
 			outsl(data_addr, buf, words);
 
 		if ((io_32bit & 2) && !mmio)
-			local_irq_restore(flags);
+			local_irq_restore_nort(flags);
 
 		if (((len + 1) & 3) < 2)
 			return;
Index: linux-4.9.20-rt16/drivers/ide/ide-io.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/ide/ide-io.c
+++ linux-4.9.20-rt16/drivers/ide/ide-io.c
@@ -659,7 +659,7 @@ void ide_timer_expiry (unsigned long dat
 		/* disable_irq_nosync ?? */
 		disable_irq(hwif->irq);
 		/* local CPU only, as if we were handling an interrupt */
-		local_irq_disable();
+		local_irq_disable_nort();
 		if (hwif->polling) {
 			startstop = handler(drive);
 		} else if (drive_is_ready(drive)) {
Index: linux-4.9.20-rt16/drivers/ide/ide-iops.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/ide/ide-iops.c
+++ linux-4.9.20-rt16/drivers/ide/ide-iops.c
@@ -129,12 +129,12 @@ int __ide_wait_stat(ide_drive_t *drive,
 				if ((stat & ATA_BUSY) == 0)
 					break;
 
-				local_irq_restore(flags);
+				local_irq_restore_nort(flags);
 				*rstat = stat;
 				return -EBUSY;
 			}
 		}
-		local_irq_restore(flags);
+		local_irq_restore_nort(flags);
 	}
 	/*
 	 * Allow status to settle, then read it again.
Index: linux-4.9.20-rt16/drivers/ide/ide-probe.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/ide/ide-probe.c
+++ linux-4.9.20-rt16/drivers/ide/ide-probe.c
@@ -196,10 +196,10 @@ static void do_identify(ide_drive_t *dri
 	int bswap = 1;
 
 	/* local CPU only; some systems need this */
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 	/* read 512 bytes of id info */
 	hwif->tp_ops->input_data(drive, NULL, id, SECTOR_SIZE);
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 
 	drive->dev_flags |= IDE_DFLAG_ID_READ;
 #ifdef DEBUG
Index: linux-4.9.20-rt16/drivers/ide/ide-taskfile.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/ide/ide-taskfile.c
+++ linux-4.9.20-rt16/drivers/ide/ide-taskfile.c
@@ -250,7 +250,7 @@ void ide_pio_bytes(ide_drive_t *drive, s
 
 		page_is_high = PageHighMem(page);
 		if (page_is_high)
-			local_irq_save(flags);
+			local_irq_save_nort(flags);
 
 		buf = kmap_atomic(page) + offset;
 
@@ -271,7 +271,7 @@ void ide_pio_bytes(ide_drive_t *drive, s
 		kunmap_atomic(buf);
 
 		if (page_is_high)
-			local_irq_restore(flags);
+			local_irq_restore_nort(flags);
 
 		len -= nr_bytes;
 	}
@@ -414,7 +414,7 @@ static ide_startstop_t pre_task_out_intr
 	}
 
 	if ((drive->dev_flags & IDE_DFLAG_UNMASK) == 0)
-		local_irq_disable();
+		local_irq_disable_nort();
 
 	ide_set_handler(drive, &task_pio_intr, WAIT_WORSTCASE);
 
Index: linux-4.9.20-rt16/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ linux-4.9.20-rt16/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -902,7 +902,7 @@ void ipoib_mcast_restart_task(struct wor
 
 	ipoib_dbg_mcast(priv, "restarting multicast task\n");
 
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 	netif_addr_lock(dev);
 	spin_lock(&priv->lock);
 
@@ -984,7 +984,7 @@ void ipoib_mcast_restart_task(struct wor
 
 	spin_unlock(&priv->lock);
 	netif_addr_unlock(dev);
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 
 	/*
 	 * make sure the in-flight joins have finished before we attempt
Index: linux-4.9.20-rt16/drivers/input/gameport/gameport.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/input/gameport/gameport.c
+++ linux-4.9.20-rt16/drivers/input/gameport/gameport.c
@@ -91,13 +91,13 @@ static int gameport_measure_speed(struct
 	tx = ~0;
 
 	for (i = 0; i < 50; i++) {
-		local_irq_save(flags);
+		local_irq_save_nort(flags);
 		t1 = ktime_get_ns();
 		for (t = 0; t < 50; t++)
 			gameport_read(gameport);
 		t2 = ktime_get_ns();
 		t3 = ktime_get_ns();
-		local_irq_restore(flags);
+		local_irq_restore_nort(flags);
 		udelay(i * 10);
 		t = (t2 - t1) - (t3 - t2);
 		if (t < tx)
@@ -124,12 +124,12 @@ static int old_gameport_measure_speed(st
 	tx = 1 << 30;
 
 	for(i = 0; i < 50; i++) {
-		local_irq_save(flags);
+		local_irq_save_nort(flags);
 		GET_TIME(t1);
 		for (t = 0; t < 50; t++) gameport_read(gameport);
 		GET_TIME(t2);
 		GET_TIME(t3);
-		local_irq_restore(flags);
+		local_irq_restore_nort(flags);
 		udelay(i * 10);
 		if ((t = DELTA(t2,t1) - DELTA(t3,t2)) < tx) tx = t;
 	}
@@ -148,11 +148,11 @@ static int old_gameport_measure_speed(st
 	tx = 1 << 30;
 
 	for(i = 0; i < 50; i++) {
-		local_irq_save(flags);
+		local_irq_save_nort(flags);
 		t1 = rdtsc();
 		for (t = 0; t < 50; t++) gameport_read(gameport);
 		t2 = rdtsc();
-		local_irq_restore(flags);
+		local_irq_restore_nort(flags);
 		udelay(i * 10);
 		if (t2 - t1 < tx) tx = t2 - t1;
 	}
Index: linux-4.9.20-rt16/drivers/iommu/amd_iommu.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/iommu/amd_iommu.c
+++ linux-4.9.20-rt16/drivers/iommu/amd_iommu.c
@@ -1923,10 +1923,10 @@ static int __attach_device(struct iommu_
 	int ret;
 
 	/*
-	 * Must be called with IRQs disabled. Warn here to detect early
-	 * when its not.
+	 * Must be called with IRQs disabled on a non RT kernel. Warn here to
+	 * detect early when its not.
 	 */
-	WARN_ON(!irqs_disabled());
+	WARN_ON_NONRT(!irqs_disabled());
 
 	/* lock domain */
 	spin_lock(&domain->lock);
@@ -2094,10 +2094,10 @@ static void __detach_device(struct iommu
 	struct protection_domain *domain;
 
 	/*
-	 * Must be called with IRQs disabled. Warn here to detect early
-	 * when its not.
+	 * Must be called with IRQs disabled on a non RT kernel. Warn here to
+	 * detect early when its not.
 	 */
-	WARN_ON(!irqs_disabled());
+	WARN_ON_NONRT(!irqs_disabled());
 
 	if (WARN_ON(!dev_data->domain))
 		return;
Index: linux-4.9.20-rt16/drivers/iommu/intel-iommu.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/iommu/intel-iommu.c
+++ linux-4.9.20-rt16/drivers/iommu/intel-iommu.c
@@ -479,7 +479,7 @@ struct deferred_flush_data {
 	struct deferred_flush_table *tables;
 };
 
-DEFINE_PER_CPU(struct deferred_flush_data, deferred_flush);
+static DEFINE_PER_CPU(struct deferred_flush_data, deferred_flush);
 
 /* bitmap for indexing intel_iommus */
 static int g_num_of_iommus;
@@ -3719,10 +3719,8 @@ static void add_unmap(struct dmar_domain
 	struct intel_iommu *iommu;
 	struct deferred_flush_entry *entry;
 	struct deferred_flush_data *flush_data;
-	unsigned int cpuid;
 
-	cpuid = get_cpu();
-	flush_data = per_cpu_ptr(&deferred_flush, cpuid);
+	flush_data = raw_cpu_ptr(&deferred_flush);
 
 	/* Flush all CPUs' entries to avoid deferring too much.  If
 	 * this becomes a bottleneck, can just flush us, and rely on
@@ -3755,8 +3753,6 @@ static void add_unmap(struct dmar_domain
 	}
 	flush_data->size++;
 	spin_unlock_irqrestore(&flush_data->lock, flags);
-
-	put_cpu();
 }
 
 static void intel_unmap(struct device *dev, dma_addr_t dev_addr, size_t size)
Index: linux-4.9.20-rt16/drivers/iommu/iova.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/iommu/iova.c
+++ linux-4.9.20-rt16/drivers/iommu/iova.c
@@ -22,6 +22,7 @@
 #include <linux/slab.h>
 #include <linux/smp.h>
 #include <linux/bitops.h>
+#include <linux/cpu.h>
 
 static bool iova_rcache_insert(struct iova_domain *iovad,
 			       unsigned long pfn,
@@ -420,10 +421,8 @@ retry:
 
 		/* Try replenishing IOVAs by flushing rcache. */
 		flushed_rcache = true;
-		preempt_disable();
 		for_each_online_cpu(cpu)
 			free_cpu_cached_iovas(cpu, iovad);
-		preempt_enable();
 		goto retry;
 	}
 
@@ -751,7 +750,7 @@ static bool __iova_rcache_insert(struct
 	bool can_insert = false;
 	unsigned long flags;
 
-	cpu_rcache = get_cpu_ptr(rcache->cpu_rcaches);
+	cpu_rcache = raw_cpu_ptr(rcache->cpu_rcaches);
 	spin_lock_irqsave(&cpu_rcache->lock, flags);
 
 	if (!iova_magazine_full(cpu_rcache->loaded)) {
@@ -781,7 +780,6 @@ static bool __iova_rcache_insert(struct
 		iova_magazine_push(cpu_rcache->loaded, iova_pfn);
 
 	spin_unlock_irqrestore(&cpu_rcache->lock, flags);
-	put_cpu_ptr(rcache->cpu_rcaches);
 
 	if (mag_to_free) {
 		iova_magazine_free_pfns(mag_to_free, iovad);
@@ -815,7 +813,7 @@ static unsigned long __iova_rcache_get(s
 	bool has_pfn = false;
 	unsigned long flags;
 
-	cpu_rcache = get_cpu_ptr(rcache->cpu_rcaches);
+	cpu_rcache = raw_cpu_ptr(rcache->cpu_rcaches);
 	spin_lock_irqsave(&cpu_rcache->lock, flags);
 
 	if (!iova_magazine_empty(cpu_rcache->loaded)) {
@@ -837,7 +835,6 @@ static unsigned long __iova_rcache_get(s
 		iova_pfn = iova_magazine_pop(cpu_rcache->loaded, limit_pfn);
 
 	spin_unlock_irqrestore(&cpu_rcache->lock, flags);
-	put_cpu_ptr(rcache->cpu_rcaches);
 
 	return iova_pfn;
 }
Index: linux-4.9.20-rt16/drivers/leds/trigger/Kconfig
===================================================================
--- linux-4.9.20-rt16.orig/drivers/leds/trigger/Kconfig
+++ linux-4.9.20-rt16/drivers/leds/trigger/Kconfig
@@ -69,7 +69,7 @@ config LEDS_TRIGGER_BACKLIGHT
 
 config LEDS_TRIGGER_CPU
 	bool "LED CPU Trigger"
-	depends on LEDS_TRIGGERS
+	depends on LEDS_TRIGGERS && !PREEMPT_RT_BASE
 	help
 	  This allows LEDs to be controlled by active CPUs. This shows
 	  the active CPUs across an array of LEDs so you can see which
Index: linux-4.9.20-rt16/drivers/md/bcache/Kconfig
===================================================================
--- linux-4.9.20-rt16.orig/drivers/md/bcache/Kconfig
+++ linux-4.9.20-rt16/drivers/md/bcache/Kconfig
@@ -1,6 +1,7 @@
 
 config BCACHE
 	tristate "Block device as cache"
+	depends on !PREEMPT_RT_FULL
 	---help---
 	Allows a block device to be used as cache for other devices; uses
 	a btree for indexing and the layout is optimized for SSDs.
Index: linux-4.9.20-rt16/drivers/md/dm-rq.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/md/dm-rq.c
+++ linux-4.9.20-rt16/drivers/md/dm-rq.c
@@ -842,7 +842,7 @@ static void dm_old_request_fn(struct req
 		/* Establish tio->ti before queuing work (map_tio_request) */
 		tio->ti = ti;
 		kthread_queue_work(&md->kworker, &tio->work);
-		BUG_ON(!irqs_disabled());
+		BUG_ON_NONRT(!irqs_disabled());
 	}
 }
 
Index: linux-4.9.20-rt16/drivers/md/raid5.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/md/raid5.c
+++ linux-4.9.20-rt16/drivers/md/raid5.c
@@ -1928,8 +1928,9 @@ static void raid_run_ops(struct stripe_h
 	struct raid5_percpu *percpu;
 	unsigned long cpu;
 
-	cpu = get_cpu();
+	cpu = get_cpu_light();
 	percpu = per_cpu_ptr(conf->percpu, cpu);
+	spin_lock(&percpu->lock);
 	if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) {
 		ops_run_biofill(sh);
 		overlap_clear++;
@@ -1985,7 +1986,8 @@ static void raid_run_ops(struct stripe_h
 			if (test_and_clear_bit(R5_Overlap, &dev->flags))
 				wake_up(&sh->raid_conf->wait_for_overlap);
 		}
-	put_cpu();
+	spin_unlock(&percpu->lock);
+	put_cpu_light();
 }
 
 static struct stripe_head *alloc_stripe(struct kmem_cache *sc, gfp_t gfp,
@@ -6398,6 +6400,7 @@ static int raid456_cpu_up_prepare(unsign
 		       __func__, cpu);
 		return -ENOMEM;
 	}
+	spin_lock_init(&per_cpu_ptr(conf->percpu, cpu)->lock);
 	return 0;
 }
 
@@ -6408,7 +6411,6 @@ static int raid5_alloc_percpu(struct r5c
 	conf->percpu = alloc_percpu(struct raid5_percpu);
 	if (!conf->percpu)
 		return -ENOMEM;
-
 	err = cpuhp_state_add_instance(CPUHP_MD_RAID5_PREPARE, &conf->node);
 	if (!err) {
 		conf->scribble_disks = max(conf->raid_disks,
Index: linux-4.9.20-rt16/drivers/md/raid5.h
===================================================================
--- linux-4.9.20-rt16.orig/drivers/md/raid5.h
+++ linux-4.9.20-rt16/drivers/md/raid5.h
@@ -504,6 +504,7 @@ struct r5conf {
 	int			recovery_disabled;
 	/* per cpu variables */
 	struct raid5_percpu {
+		spinlock_t	lock;		/* Protection for -RT */
 		struct page	*spare_page; /* Used when checking P/Q in raid6 */
 		struct flex_array *scribble;   /* space for constructing buffer
 					      * lists and performing address
Index: linux-4.9.20-rt16/drivers/misc/Kconfig
===================================================================
--- linux-4.9.20-rt16.orig/drivers/misc/Kconfig
+++ linux-4.9.20-rt16/drivers/misc/Kconfig
@@ -54,6 +54,7 @@ config AD525X_DPOT_SPI
 config ATMEL_TCLIB
 	bool "Atmel AT32/AT91 Timer/Counter Library"
 	depends on (AVR32 || ARCH_AT91)
+	default y if PREEMPT_RT_FULL
 	help
 	  Select this if you want a library to allocate the Timer/Counter
 	  blocks found on many Atmel processors.  This facilitates using
@@ -69,8 +70,7 @@ config ATMEL_TCB_CLKSRC
 	  are combined to make a single 32-bit timer.
 
 	  When GENERIC_CLOCKEVENTS is defined, the third timer channel
-	  may be used as a clock event device supporting oneshot mode
-	  (delays of up to two seconds) based on the 32 KiHz clock.
+	  may be used as a clock event device supporting oneshot mode.
 
 config ATMEL_TCB_CLKSRC_BLOCK
 	int
@@ -84,6 +84,15 @@ config ATMEL_TCB_CLKSRC_BLOCK
 	  TC can be used for other purposes, such as PWM generation and
 	  interval timing.
 
+config ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK
+	bool "TC Block use 32 KiHz clock"
+	depends on ATMEL_TCB_CLKSRC
+	default y if !PREEMPT_RT_FULL
+	help
+	  Select this to use 32 KiHz base clock rate as TC block clock
+	  source for clock events.
+
+
 config DUMMY_IRQ
 	tristate "Dummy IRQ handler"
 	default n
Index: linux-4.9.20-rt16/drivers/mmc/host/mmci.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/mmc/host/mmci.c
+++ linux-4.9.20-rt16/drivers/mmc/host/mmci.c
@@ -1147,15 +1147,12 @@ static irqreturn_t mmci_pio_irq(int irq,
 	struct sg_mapping_iter *sg_miter = &host->sg_miter;
 	struct variant_data *variant = host->variant;
 	void __iomem *base = host->base;
-	unsigned long flags;
 	u32 status;
 
 	status = readl(base + MMCISTATUS);
 
 	dev_dbg(mmc_dev(host->mmc), "irq1 (pio) %08x\n", status);
 
-	local_irq_save(flags);
-
 	do {
 		unsigned int remain, len;
 		char *buffer;
@@ -1195,8 +1192,6 @@ static irqreturn_t mmci_pio_irq(int irq,
 
 	sg_miter_stop(sg_miter);
 
-	local_irq_restore(flags);
-
 	/*
 	 * If we have less than the fifo 'half-full' threshold to transfer,
 	 * trigger a PIO interrupt as soon as any data is available.
Index: linux-4.9.20-rt16/drivers/net/ethernet/3com/3c59x.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/net/ethernet/3com/3c59x.c
+++ linux-4.9.20-rt16/drivers/net/ethernet/3com/3c59x.c
@@ -842,9 +842,9 @@ static void poll_vortex(struct net_devic
 {
 	struct vortex_private *vp = netdev_priv(dev);
 	unsigned long flags;
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 	(vp->full_bus_master_rx ? boomerang_interrupt:vortex_interrupt)(dev->irq,dev);
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 }
 #endif
 
@@ -1910,12 +1910,12 @@ static void vortex_tx_timeout(struct net
 			 * Block interrupts because vortex_interrupt does a bare spin_lock()
 			 */
 			unsigned long flags;
-			local_irq_save(flags);
+			local_irq_save_nort(flags);
 			if (vp->full_bus_master_tx)
 				boomerang_interrupt(dev->irq, dev);
 			else
 				vortex_interrupt(dev->irq, dev);
-			local_irq_restore(flags);
+			local_irq_restore_nort(flags);
 		}
 	}
 
Index: linux-4.9.20-rt16/drivers/net/ethernet/realtek/8139too.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/net/ethernet/realtek/8139too.c
+++ linux-4.9.20-rt16/drivers/net/ethernet/realtek/8139too.c
@@ -2233,7 +2233,7 @@ static void rtl8139_poll_controller(stru
 	struct rtl8139_private *tp = netdev_priv(dev);
 	const int irq = tp->pci_dev->irq;
 
-	disable_irq(irq);
+	disable_irq_nosync(irq);
 	rtl8139_interrupt(irq, dev);
 	enable_irq(irq);
 }
Index: linux-4.9.20-rt16/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
+++ linux-4.9.20-rt16/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
@@ -697,7 +697,7 @@ static void ezusb_req_ctx_wait(struct ez
 			while (!ctx->done.done && msecs--)
 				udelay(1000);
 		} else {
-			wait_event_interruptible(ctx->done.wait,
+			swait_event_interruptible(ctx->done.wait,
 						 ctx->done.done);
 		}
 		break;
Index: linux-4.9.20-rt16/drivers/pci/access.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/pci/access.c
+++ linux-4.9.20-rt16/drivers/pci/access.c
@@ -672,7 +672,7 @@ void pci_cfg_access_unlock(struct pci_de
 	WARN_ON(!dev->block_cfg_access);
 
 	dev->block_cfg_access = 0;
-	wake_up_all(&pci_cfg_wait);
+	wake_up_all_locked(&pci_cfg_wait);
 	raw_spin_unlock_irqrestore(&pci_lock, flags);
 }
 EXPORT_SYMBOL_GPL(pci_cfg_access_unlock);
Index: linux-4.9.20-rt16/drivers/pinctrl/qcom/pinctrl-msm.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/pinctrl/qcom/pinctrl-msm.c
+++ linux-4.9.20-rt16/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -61,7 +61,7 @@ struct msm_pinctrl {
 	struct notifier_block restart_nb;
 	int irq;
 
-	spinlock_t lock;
+	raw_spinlock_t lock;
 
 	DECLARE_BITMAP(dual_edge_irqs, MAX_NR_GPIO);
 	DECLARE_BITMAP(enabled_irqs, MAX_NR_GPIO);
@@ -153,14 +153,14 @@ static int msm_pinmux_set_mux(struct pin
 	if (WARN_ON(i == g->nfuncs))
 		return -EINVAL;
 
-	spin_lock_irqsave(&pctrl->lock, flags);
+	raw_spin_lock_irqsave(&pctrl->lock, flags);
 
 	val = readl(pctrl->regs + g->ctl_reg);
 	val &= ~mask;
 	val |= i << g->mux_bit;
 	writel(val, pctrl->regs + g->ctl_reg);
 
-	spin_unlock_irqrestore(&pctrl->lock, flags);
+	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
 
 	return 0;
 }
@@ -323,14 +323,14 @@ static int msm_config_group_set(struct p
 			break;
 		case PIN_CONFIG_OUTPUT:
 			/* set output value */
-			spin_lock_irqsave(&pctrl->lock, flags);
+			raw_spin_lock_irqsave(&pctrl->lock, flags);
 			val = readl(pctrl->regs + g->io_reg);
 			if (arg)
 				val |= BIT(g->out_bit);
 			else
 				val &= ~BIT(g->out_bit);
 			writel(val, pctrl->regs + g->io_reg);
-			spin_unlock_irqrestore(&pctrl->lock, flags);
+			raw_spin_unlock_irqrestore(&pctrl->lock, flags);
 
 			/* enable output */
 			arg = 1;
@@ -351,12 +351,12 @@ static int msm_config_group_set(struct p
 			return -EINVAL;
 		}
 
-		spin_lock_irqsave(&pctrl->lock, flags);
+		raw_spin_lock_irqsave(&pctrl->lock, flags);
 		val = readl(pctrl->regs + g->ctl_reg);
 		val &= ~(mask << bit);
 		val |= arg << bit;
 		writel(val, pctrl->regs + g->ctl_reg);
-		spin_unlock_irqrestore(&pctrl->lock, flags);
+		raw_spin_unlock_irqrestore(&pctrl->lock, flags);
 	}
 
 	return 0;
@@ -384,13 +384,13 @@ static int msm_gpio_direction_input(stru
 
 	g = &pctrl->soc->groups[offset];
 
-	spin_lock_irqsave(&pctrl->lock, flags);
+	raw_spin_lock_irqsave(&pctrl->lock, flags);
 
 	val = readl(pctrl->regs + g->ctl_reg);
 	val &= ~BIT(g->oe_bit);
 	writel(val, pctrl->regs + g->ctl_reg);
 
-	spin_unlock_irqrestore(&pctrl->lock, flags);
+	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
 
 	return 0;
 }
@@ -404,7 +404,7 @@ static int msm_gpio_direction_output(str
 
 	g = &pctrl->soc->groups[offset];
 
-	spin_lock_irqsave(&pctrl->lock, flags);
+	raw_spin_lock_irqsave(&pctrl->lock, flags);
 
 	val = readl(pctrl->regs + g->io_reg);
 	if (value)
@@ -417,7 +417,7 @@ static int msm_gpio_direction_output(str
 	val |= BIT(g->oe_bit);
 	writel(val, pctrl->regs + g->ctl_reg);
 
-	spin_unlock_irqrestore(&pctrl->lock, flags);
+	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
 
 	return 0;
 }
@@ -443,7 +443,7 @@ static void msm_gpio_set(struct gpio_chi
 
 	g = &pctrl->soc->groups[offset];
 
-	spin_lock_irqsave(&pctrl->lock, flags);
+	raw_spin_lock_irqsave(&pctrl->lock, flags);
 
 	val = readl(pctrl->regs + g->io_reg);
 	if (value)
@@ -452,7 +452,7 @@ static void msm_gpio_set(struct gpio_chi
 		val &= ~BIT(g->out_bit);
 	writel(val, pctrl->regs + g->io_reg);
 
-	spin_unlock_irqrestore(&pctrl->lock, flags);
+	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
 }
 
 #ifdef CONFIG_DEBUG_FS
@@ -571,7 +571,7 @@ static void msm_gpio_irq_mask(struct irq
 
 	g = &pctrl->soc->groups[d->hwirq];
 
-	spin_lock_irqsave(&pctrl->lock, flags);
+	raw_spin_lock_irqsave(&pctrl->lock, flags);
 
 	val = readl(pctrl->regs + g->intr_cfg_reg);
 	val &= ~BIT(g->intr_enable_bit);
@@ -579,7 +579,7 @@ static void msm_gpio_irq_mask(struct irq
 
 	clear_bit(d->hwirq, pctrl->enabled_irqs);
 
-	spin_unlock_irqrestore(&pctrl->lock, flags);
+	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
 }
 
 static void msm_gpio_irq_unmask(struct irq_data *d)
@@ -592,7 +592,7 @@ static void msm_gpio_irq_unmask(struct i
 
 	g = &pctrl->soc->groups[d->hwirq];
 
-	spin_lock_irqsave(&pctrl->lock, flags);
+	raw_spin_lock_irqsave(&pctrl->lock, flags);
 
 	val = readl(pctrl->regs + g->intr_cfg_reg);
 	val |= BIT(g->intr_enable_bit);
@@ -600,7 +600,7 @@ static void msm_gpio_irq_unmask(struct i
 
 	set_bit(d->hwirq, pctrl->enabled_irqs);
 
-	spin_unlock_irqrestore(&pctrl->lock, flags);
+	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
 }
 
 static void msm_gpio_irq_ack(struct irq_data *d)
@@ -613,7 +613,7 @@ static void msm_gpio_irq_ack(struct irq_
 
 	g = &pctrl->soc->groups[d->hwirq];
 
-	spin_lock_irqsave(&pctrl->lock, flags);
+	raw_spin_lock_irqsave(&pctrl->lock, flags);
 
 	val = readl(pctrl->regs + g->intr_status_reg);
 	if (g->intr_ack_high)
@@ -625,7 +625,7 @@ static void msm_gpio_irq_ack(struct irq_
 	if (test_bit(d->hwirq, pctrl->dual_edge_irqs))
 		msm_gpio_update_dual_edge_pos(pctrl, g, d);
 
-	spin_unlock_irqrestore(&pctrl->lock, flags);
+	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
 }
 
 static int msm_gpio_irq_set_type(struct irq_data *d, unsigned int type)
@@ -638,7 +638,7 @@ static int msm_gpio_irq_set_type(struct
 
 	g = &pctrl->soc->groups[d->hwirq];
 
-	spin_lock_irqsave(&pctrl->lock, flags);
+	raw_spin_lock_irqsave(&pctrl->lock, flags);
 
 	/*
 	 * For hw without possibility of detecting both edges
@@ -712,7 +712,7 @@ static int msm_gpio_irq_set_type(struct
 	if (test_bit(d->hwirq, pctrl->dual_edge_irqs))
 		msm_gpio_update_dual_edge_pos(pctrl, g, d);
 
-	spin_unlock_irqrestore(&pctrl->lock, flags);
+	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
 
 	if (type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
 		irq_set_handler_locked(d, handle_level_irq);
@@ -728,11 +728,11 @@ static int msm_gpio_irq_set_wake(struct
 	struct msm_pinctrl *pctrl = gpiochip_get_data(gc);
 	unsigned long flags;
 
-	spin_lock_irqsave(&pctrl->lock, flags);
+	raw_spin_lock_irqsave(&pctrl->lock, flags);
 
 	irq_set_irq_wake(pctrl->irq, on);
 
-	spin_unlock_irqrestore(&pctrl->lock, flags);
+	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
 
 	return 0;
 }
@@ -878,7 +878,7 @@ int msm_pinctrl_probe(struct platform_de
 	pctrl->soc = soc_data;
 	pctrl->chip = msm_gpio_template;
 
-	spin_lock_init(&pctrl->lock);
+	raw_spin_lock_init(&pctrl->lock);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	pctrl->regs = devm_ioremap_resource(&pdev->dev, res);
Index: linux-4.9.20-rt16/drivers/scsi/fcoe/fcoe.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/scsi/fcoe/fcoe.c
+++ linux-4.9.20-rt16/drivers/scsi/fcoe/fcoe.c
@@ -1455,11 +1455,11 @@ err2:
 static int fcoe_alloc_paged_crc_eof(struct sk_buff *skb, int tlen)
 {
 	struct fcoe_percpu_s *fps;
-	int rc;
+	int rc, cpu = get_cpu_light();
 
-	fps = &get_cpu_var(fcoe_percpu);
+	fps = &per_cpu(fcoe_percpu, cpu);
 	rc = fcoe_get_paged_crc_eof(skb, tlen, fps);
-	put_cpu_var(fcoe_percpu);
+	put_cpu_light();
 
 	return rc;
 }
@@ -1646,11 +1646,11 @@ static inline int fcoe_filter_frames(str
 		return 0;
 	}
 
-	stats = per_cpu_ptr(lport->stats, get_cpu());
+	stats = per_cpu_ptr(lport->stats, get_cpu_light());
 	stats->InvalidCRCCount++;
 	if (stats->InvalidCRCCount < 5)
 		printk(KERN_WARNING "fcoe: dropping frame with CRC error\n");
-	put_cpu();
+	put_cpu_light();
 	return -EINVAL;
 }
 
@@ -1693,7 +1693,7 @@ static void fcoe_recv_frame(struct sk_bu
 	 */
 	hp = (struct fcoe_hdr *) skb_network_header(skb);
 
-	stats = per_cpu_ptr(lport->stats, get_cpu());
+	stats = per_cpu_ptr(lport->stats, get_cpu_light());
 	if (unlikely(FC_FCOE_DECAPS_VER(hp) != FC_FCOE_VER)) {
 		if (stats->ErrorFrames < 5)
 			printk(KERN_WARNING "fcoe: FCoE version "
@@ -1725,13 +1725,13 @@ static void fcoe_recv_frame(struct sk_bu
 		goto drop;
 
 	if (!fcoe_filter_frames(lport, fp)) {
-		put_cpu();
+		put_cpu_light();
 		fc_exch_recv(lport, fp);
 		return;
 	}
 drop:
 	stats->ErrorFrames++;
-	put_cpu();
+	put_cpu_light();
 	kfree_skb(skb);
 }
 
Index: linux-4.9.20-rt16/drivers/scsi/fcoe/fcoe_ctlr.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/scsi/fcoe/fcoe_ctlr.c
+++ linux-4.9.20-rt16/drivers/scsi/fcoe/fcoe_ctlr.c
@@ -834,7 +834,7 @@ static unsigned long fcoe_ctlr_age_fcfs(
 
 	INIT_LIST_HEAD(&del_list);
 
-	stats = per_cpu_ptr(fip->lp->stats, get_cpu());
+	stats = per_cpu_ptr(fip->lp->stats, get_cpu_light());
 
 	list_for_each_entry_safe(fcf, next, &fip->fcfs, list) {
 		deadline = fcf->time + fcf->fka_period + fcf->fka_period / 2;
@@ -870,7 +870,7 @@ static unsigned long fcoe_ctlr_age_fcfs(
 				sel_time = fcf->time;
 		}
 	}
-	put_cpu();
+	put_cpu_light();
 
 	list_for_each_entry_safe(fcf, next, &del_list, list) {
 		/* Removes fcf from current list */
Index: linux-4.9.20-rt16/drivers/scsi/libfc/fc_exch.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/scsi/libfc/fc_exch.c
+++ linux-4.9.20-rt16/drivers/scsi/libfc/fc_exch.c
@@ -814,10 +814,10 @@ static struct fc_exch *fc_exch_em_alloc(
 	}
 	memset(ep, 0, sizeof(*ep));
 
-	cpu = get_cpu();
+	cpu = get_cpu_light();
 	pool = per_cpu_ptr(mp->pool, cpu);
 	spin_lock_bh(&pool->lock);
-	put_cpu();
+	put_cpu_light();
 
 	/* peek cache of free slot */
 	if (pool->left != FC_XID_UNKNOWN) {
Index: linux-4.9.20-rt16/drivers/scsi/libsas/sas_ata.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/scsi/libsas/sas_ata.c
+++ linux-4.9.20-rt16/drivers/scsi/libsas/sas_ata.c
@@ -190,7 +190,7 @@ static unsigned int sas_ata_qc_issue(str
 	/* TODO: audit callers to ensure they are ready for qc_issue to
 	 * unconditionally re-enable interrupts
 	 */
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 	spin_unlock(ap->lock);
 
 	/* If the device fell off, no sense in issuing commands */
@@ -252,7 +252,7 @@ static unsigned int sas_ata_qc_issue(str
 
  out:
 	spin_lock(ap->lock);
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 	return ret;
 }
 
Index: linux-4.9.20-rt16/drivers/scsi/qla2xxx/qla_inline.h
===================================================================
--- linux-4.9.20-rt16.orig/drivers/scsi/qla2xxx/qla_inline.h
+++ linux-4.9.20-rt16/drivers/scsi/qla2xxx/qla_inline.h
@@ -59,12 +59,12 @@ qla2x00_poll(struct rsp_que *rsp)
 {
 	unsigned long flags;
 	struct qla_hw_data *ha = rsp->hw;
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 	if (IS_P3P_TYPE(ha))
 		qla82xx_poll(0, rsp);
 	else
 		ha->isp_ops->intr_handler(0, rsp);
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 }
 
 static inline uint8_t *
Index: linux-4.9.20-rt16/drivers/scsi/qla2xxx/qla_isr.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/scsi/qla2xxx/qla_isr.c
+++ linux-4.9.20-rt16/drivers/scsi/qla2xxx/qla_isr.c
@@ -3129,7 +3129,11 @@ qla24xx_enable_msix(struct qla_hw_data *
 		* kref_put().
 		*/
 		kref_get(&qentry->irq_notify.kref);
+#ifdef CONFIG_PREEMPT_RT_BASE
+		swork_queue(&qentry->irq_notify.swork);
+#else
 		schedule_work(&qentry->irq_notify.work);
+#endif
 	}
 
 	/*
Index: linux-4.9.20-rt16/drivers/thermal/x86_pkg_temp_thermal.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/thermal/x86_pkg_temp_thermal.c
+++ linux-4.9.20-rt16/drivers/thermal/x86_pkg_temp_thermal.c
@@ -29,6 +29,7 @@
 #include <linux/pm.h>
 #include <linux/thermal.h>
 #include <linux/debugfs.h>
+#include <linux/swork.h>
 #include <asm/cpu_device_id.h>
 #include <asm/mce.h>
 
@@ -353,7 +354,7 @@ static void pkg_temp_thermal_threshold_w
 	}
 }
 
-static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val)
+static void platform_thermal_notify_work(struct swork_event *event)
 {
 	unsigned long flags;
 	int cpu = smp_processor_id();
@@ -370,7 +371,7 @@ static int pkg_temp_thermal_platform_the
 			pkg_work_scheduled[phy_id]) {
 		disable_pkg_thres_interrupt();
 		spin_unlock_irqrestore(&pkg_work_lock, flags);
-		return -EINVAL;
+		return;
 	}
 	pkg_work_scheduled[phy_id] = 1;
 	spin_unlock_irqrestore(&pkg_work_lock, flags);
@@ -379,9 +380,48 @@ static int pkg_temp_thermal_platform_the
 	schedule_delayed_work_on(cpu,
 				&per_cpu(pkg_temp_thermal_threshold_work, cpu),
 				msecs_to_jiffies(notify_delay_ms));
+}
+
+#ifdef CONFIG_PREEMPT_RT_FULL
+static struct swork_event notify_work;
+
+static int thermal_notify_work_init(void)
+{
+	int err;
+
+	err = swork_get();
+	if (err)
+		return err;
+
+	INIT_SWORK(&notify_work, platform_thermal_notify_work);
 	return 0;
 }
 
+static void thermal_notify_work_cleanup(void)
+{
+	swork_put();
+}
+
+static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val)
+{
+	swork_queue(&notify_work);
+	return 0;
+}
+
+#else  /* !CONFIG_PREEMPT_RT_FULL */
+
+static int thermal_notify_work_init(void) { return 0; }
+
+static void thermal_notify_work_cleanup(void) {  }
+
+static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val)
+{
+	platform_thermal_notify_work(NULL);
+
+	return 0;
+}
+#endif /* CONFIG_PREEMPT_RT_FULL */
+
 static int find_siblings_cpu(int cpu)
 {
 	int i;
@@ -585,6 +625,9 @@ static int __init pkg_temp_thermal_init(
 	if (!x86_match_cpu(pkg_temp_thermal_ids))
 		return -ENODEV;
 
+	if (!thermal_notify_work_init())
+		return -ENODEV;
+
 	spin_lock_init(&pkg_work_lock);
 	platform_thermal_package_notify =
 			pkg_temp_thermal_platform_thermal_notify;
@@ -609,7 +652,7 @@ err_ret:
 	kfree(pkg_work_scheduled);
 	platform_thermal_package_notify = NULL;
 	platform_thermal_package_rate_control = NULL;
-
+	thermal_notify_work_cleanup();
 	return -ENODEV;
 }
 
@@ -634,6 +677,7 @@ static void __exit pkg_temp_thermal_exit
 	mutex_unlock(&phy_dev_list_mutex);
 	platform_thermal_package_notify = NULL;
 	platform_thermal_package_rate_control = NULL;
+	thermal_notify_work_cleanup();
 	for_each_online_cpu(i)
 		cancel_delayed_work_sync(
 			&per_cpu(pkg_temp_thermal_threshold_work, i));
Index: linux-4.9.20-rt16/drivers/tty/serial/8250/8250_core.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/tty/serial/8250/8250_core.c
+++ linux-4.9.20-rt16/drivers/tty/serial/8250/8250_core.c
@@ -58,7 +58,16 @@ static struct uart_driver serial8250_reg
 
 static unsigned int skip_txen_test; /* force skip of txen test at init time */
 
-#define PASS_LIMIT	512
+/*
+ * On -rt we can have a more delays, and legitimately
+ * so - so don't drop work spuriously and spam the
+ * syslog:
+ */
+#ifdef CONFIG_PREEMPT_RT_FULL
+# define PASS_LIMIT	1000000
+#else
+# define PASS_LIMIT	512
+#endif
 
 #include <asm/serial.h>
 /*
Index: linux-4.9.20-rt16/drivers/tty/serial/8250/8250_port.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/tty/serial/8250/8250_port.c
+++ linux-4.9.20-rt16/drivers/tty/serial/8250/8250_port.c
@@ -35,6 +35,7 @@
 #include <linux/nmi.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
+#include <linux/kdb.h>
 #include <linux/uaccess.h>
 #include <linux/pm_runtime.h>
 #include <linux/timer.h>
@@ -3144,9 +3145,9 @@ void serial8250_console_write(struct uar
 
 	serial8250_rpm_get(up);
 
-	if (port->sysrq)
+	if (port->sysrq || oops_in_progress)
 		locked = 0;
-	else if (oops_in_progress)
+	else if (in_kdb_printk())
 		locked = spin_trylock_irqsave(&port->lock, flags);
 	else
 		spin_lock_irqsave(&port->lock, flags);
Index: linux-4.9.20-rt16/drivers/tty/serial/amba-pl011.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/tty/serial/amba-pl011.c
+++ linux-4.9.20-rt16/drivers/tty/serial/amba-pl011.c
@@ -2194,13 +2194,19 @@ pl011_console_write(struct console *co,
 
 	clk_enable(uap->clk);
 
-	local_irq_save(flags);
+	/*
+	 * local_irq_save(flags);
+	 *
+	 * This local_irq_save() is nonsense. If we come in via sysrq
+	 * handling then interrupts are already disabled. Aside of
+	 * that the port.sysrq check is racy on SMP regardless.
+	*/
 	if (uap->port.sysrq)
 		locked = 0;
 	else if (oops_in_progress)
-		locked = spin_trylock(&uap->port.lock);
+		locked = spin_trylock_irqsave(&uap->port.lock, flags);
 	else
-		spin_lock(&uap->port.lock);
+		spin_lock_irqsave(&uap->port.lock, flags);
 
 	/*
 	 *	First save the CR then disable the interrupts
@@ -2224,8 +2230,7 @@ pl011_console_write(struct console *co,
 		pl011_write(old_cr, uap, REG_CR);
 
 	if (locked)
-		spin_unlock(&uap->port.lock);
-	local_irq_restore(flags);
+		spin_unlock_irqrestore(&uap->port.lock, flags);
 
 	clk_disable(uap->clk);
 }
Index: linux-4.9.20-rt16/drivers/tty/serial/omap-serial.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/tty/serial/omap-serial.c
+++ linux-4.9.20-rt16/drivers/tty/serial/omap-serial.c
@@ -1257,13 +1257,10 @@ serial_omap_console_write(struct console
 
 	pm_runtime_get_sync(up->dev);
 
-	local_irq_save(flags);
-	if (up->port.sysrq)
-		locked = 0;
-	else if (oops_in_progress)
-		locked = spin_trylock(&up->port.lock);
+	if (up->port.sysrq || oops_in_progress)
+		locked = spin_trylock_irqsave(&up->port.lock, flags);
 	else
-		spin_lock(&up->port.lock);
+		spin_lock_irqsave(&up->port.lock, flags);
 
 	/*
 	 * First save the IER then disable the interrupts
@@ -1292,8 +1289,7 @@ serial_omap_console_write(struct console
 	pm_runtime_mark_last_busy(up->dev);
 	pm_runtime_put_autosuspend(up->dev);
 	if (locked)
-		spin_unlock(&up->port.lock);
-	local_irq_restore(flags);
+		spin_unlock_irqrestore(&up->port.lock, flags);
 }
 
 static int __init
Index: linux-4.9.20-rt16/drivers/usb/core/hcd.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/usb/core/hcd.c
+++ linux-4.9.20-rt16/drivers/usb/core/hcd.c
@@ -1764,9 +1764,9 @@ static void __usb_hcd_giveback_urb(struc
 	 * and no one may trigger the above deadlock situation when
 	 * running complete() in tasklet.
 	 */
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 	urb->complete(urb);
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 
 	usb_anchor_resume_wakeups(anchor);
 	atomic_dec(&urb->use_count);
Index: linux-4.9.20-rt16/drivers/usb/gadget/function/f_fs.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/usb/gadget/function/f_fs.c
+++ linux-4.9.20-rt16/drivers/usb/gadget/function/f_fs.c
@@ -1593,7 +1593,7 @@ static void ffs_data_put(struct ffs_data
 		pr_info("%s(): freeing\n", __func__);
 		ffs_data_clear(ffs);
 		BUG_ON(waitqueue_active(&ffs->ev.waitq) ||
-		       waitqueue_active(&ffs->ep0req_completion.wait));
+		       swait_active(&ffs->ep0req_completion.wait));
 		kfree(ffs->dev_name);
 		kfree(ffs);
 	}
Index: linux-4.9.20-rt16/drivers/usb/gadget/legacy/inode.c
===================================================================
--- linux-4.9.20-rt16.orig/drivers/usb/gadget/legacy/inode.c
+++ linux-4.9.20-rt16/drivers/usb/gadget/legacy/inode.c
@@ -346,7 +346,7 @@ ep_io (struct ep_data *epdata, void *buf
 	spin_unlock_irq (&epdata->dev->lock);
 
 	if (likely (value == 0)) {
-		value = wait_event_interruptible (done.wait, done.done);
+		value = swait_event_interruptible (done.wait, done.done);
 		if (value != 0) {
 			spin_lock_irq (&epdata->dev->lock);
 			if (likely (epdata->ep != NULL)) {
@@ -355,7 +355,7 @@ ep_io (struct ep_data *epdata, void *buf
 				usb_ep_dequeue (epdata->ep, epdata->req);
 				spin_unlock_irq (&epdata->dev->lock);
 
-				wait_event (done.wait, done.done);
+				swait_event (done.wait, done.done);
 				if (epdata->status == -ECONNRESET)
 					epdata->status = -EINTR;
 			} else {
Index: linux-4.9.20-rt16/fs/aio.c
===================================================================
--- linux-4.9.20-rt16.orig/fs/aio.c
+++ linux-4.9.20-rt16/fs/aio.c
@@ -40,6 +40,7 @@
 #include <linux/ramfs.h>
 #include <linux/percpu-refcount.h>
 #include <linux/mount.h>
+#include <linux/swork.h>
 
 #include <asm/kmap_types.h>
 #include <asm/uaccess.h>
@@ -115,7 +116,7 @@ struct kioctx {
 	struct page		**ring_pages;
 	long			nr_pages;
 
-	struct work_struct	free_work;
+	struct swork_event	free_work;
 
 	/*
 	 * signals when all in-flight requests are done
@@ -258,6 +259,7 @@ static int __init aio_setup(void)
 		.mount		= aio_mount,
 		.kill_sb	= kill_anon_super,
 	};
+	BUG_ON(swork_get());
 	aio_mnt = kern_mount(&aio_fs);
 	if (IS_ERR(aio_mnt))
 		panic("Failed to create aio fs mount.");
@@ -581,9 +583,9 @@ static int kiocb_cancel(struct aio_kiocb
 	return cancel(&kiocb->common);
 }
 
-static void free_ioctx(struct work_struct *work)
+static void free_ioctx(struct swork_event *sev)
 {
-	struct kioctx *ctx = container_of(work, struct kioctx, free_work);
+	struct kioctx *ctx = container_of(sev, struct kioctx, free_work);
 
 	pr_debug("freeing %p\n", ctx);
 
@@ -602,8 +604,8 @@ static void free_ioctx_reqs(struct percp
 	if (ctx->rq_wait && atomic_dec_and_test(&ctx->rq_wait->count))
 		complete(&ctx->rq_wait->comp);
 
-	INIT_WORK(&ctx->free_work, free_ioctx);
-	schedule_work(&ctx->free_work);
+	INIT_SWORK(&ctx->free_work, free_ioctx);
+	swork_queue(&ctx->free_work);
 }
 
 /*
@@ -611,9 +613,9 @@ static void free_ioctx_reqs(struct percp
  * and ctx->users has dropped to 0, so we know no more kiocbs can be submitted -
  * now it's safe to cancel any that need to be.
  */
-static void free_ioctx_users(struct percpu_ref *ref)
+static void free_ioctx_users_work(struct swork_event *sev)
 {
-	struct kioctx *ctx = container_of(ref, struct kioctx, users);
+	struct kioctx *ctx = container_of(sev, struct kioctx, free_work);
 	struct aio_kiocb *req;
 
 	spin_lock_irq(&ctx->ctx_lock);
@@ -632,6 +634,14 @@ static void free_ioctx_users(struct perc
 	percpu_ref_put(&ctx->reqs);
 }
 
+static void free_ioctx_users(struct percpu_ref *ref)
+{
+	struct kioctx *ctx = container_of(ref, struct kioctx, users);
+
+	INIT_SWORK(&ctx->free_work, free_ioctx_users_work);
+	swork_queue(&ctx->free_work);
+}
+
 static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm)
 {
 	unsigned i, new_nr;
Index: linux-4.9.20-rt16/fs/autofs4/autofs_i.h
===================================================================
--- linux-4.9.20-rt16.orig/fs/autofs4/autofs_i.h
+++ linux-4.9.20-rt16/fs/autofs4/autofs_i.h
@@ -31,6 +31,7 @@
 #include <linux/sched.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
+#include <linux/delay.h>
 #include <asm/current.h>
 #include <linux/uaccess.h>
 
Index: linux-4.9.20-rt16/fs/autofs4/expire.c
===================================================================
--- linux-4.9.20-rt16.orig/fs/autofs4/expire.c
+++ linux-4.9.20-rt16/fs/autofs4/expire.c
@@ -148,7 +148,7 @@ again:
 			parent = p->d_parent;
 			if (!spin_trylock(&parent->d_lock)) {
 				spin_unlock(&p->d_lock);
-				cpu_relax();
+				cpu_chill();
 				goto relock;
 			}
 			spin_unlock(&p->d_lock);
Index: linux-4.9.20-rt16/fs/buffer.c
===================================================================
--- linux-4.9.20-rt16.orig/fs/buffer.c
+++ linux-4.9.20-rt16/fs/buffer.c
@@ -301,8 +301,7 @@ static void end_buffer_async_read(struct
 	 * decide that the page is now completely done.
 	 */
 	first = page_buffers(page);
-	local_irq_save(flags);
-	bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
+	flags = bh_uptodate_lock_irqsave(first);
 	clear_buffer_async_read(bh);
 	unlock_buffer(bh);
 	tmp = bh;
@@ -315,8 +314,7 @@ static void end_buffer_async_read(struct
 		}
 		tmp = tmp->b_this_page;
 	} while (tmp != bh);
-	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
-	local_irq_restore(flags);
+	bh_uptodate_unlock_irqrestore(first, flags);
 
 	/*
 	 * If none of the buffers had errors and they are all
@@ -328,9 +326,7 @@ static void end_buffer_async_read(struct
 	return;
 
 still_busy:
-	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
-	local_irq_restore(flags);
-	return;
+	bh_uptodate_unlock_irqrestore(first, flags);
 }
 
 /*
@@ -358,8 +354,7 @@ void end_buffer_async_write(struct buffe
 	}
 
 	first = page_buffers(page);
-	local_irq_save(flags);
-	bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
+	flags = bh_uptodate_lock_irqsave(first);
 
 	clear_buffer_async_write(bh);
 	unlock_buffer(bh);
@@ -371,15 +366,12 @@ void end_buffer_async_write(struct buffe
 		}
 		tmp = tmp->b_this_page;
 	}
-	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
-	local_irq_restore(flags);
+	bh_uptodate_unlock_irqrestore(first, flags);
 	end_page_writeback(page);
 	return;
 
 still_busy:
-	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
-	local_irq_restore(flags);
-	return;
+	bh_uptodate_unlock_irqrestore(first, flags);
 }
 EXPORT_SYMBOL(end_buffer_async_write);
 
@@ -3383,6 +3375,7 @@ struct buffer_head *alloc_buffer_head(gf
 	struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags);
 	if (ret) {
 		INIT_LIST_HEAD(&ret->b_assoc_buffers);
+		buffer_head_init_locks(ret);
 		preempt_disable();
 		__this_cpu_inc(bh_accounting.nr);
 		recalc_bh_state();
Index: linux-4.9.20-rt16/fs/cifs/readdir.c
===================================================================
--- linux-4.9.20-rt16.orig/fs/cifs/readdir.c
+++ linux-4.9.20-rt16/fs/cifs/readdir.c
@@ -80,7 +80,7 @@ cifs_prime_dcache(struct dentry *parent,
 	struct inode *inode;
 	struct super_block *sb = parent->d_sb;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
-	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+	DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
 
 	cifs_dbg(FYI, "%s: for %s\n", __func__, name->name);
 
Index: linux-4.9.20-rt16/fs/dcache.c
===================================================================
--- linux-4.9.20-rt16.orig/fs/dcache.c
+++ linux-4.9.20-rt16/fs/dcache.c
@@ -19,6 +19,7 @@
 #include <linux/mm.h>
 #include <linux/fs.h>
 #include <linux/fsnotify.h>
+#include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/hash.h>
@@ -777,6 +778,8 @@ static inline bool fast_dput(struct dent
  */
 void dput(struct dentry *dentry)
 {
+	struct dentry *parent;
+
 	if (unlikely(!dentry))
 		return;
 
@@ -815,9 +818,18 @@ repeat:
 	return;
 
 kill_it:
-	dentry = dentry_kill(dentry);
-	if (dentry) {
-		cond_resched();
+	parent = dentry_kill(dentry);
+	if (parent) {
+		int r;
+
+		if (parent == dentry) {
+			/* the task with the highest priority won't schedule */
+			r = cond_resched();
+			if (!r)
+				cpu_chill();
+		} else {
+			dentry = parent;
+		}
 		goto repeat;
 	}
 }
@@ -2352,7 +2364,7 @@ again:
 	if (dentry->d_lockref.count == 1) {
 		if (!spin_trylock(&inode->i_lock)) {
 			spin_unlock(&dentry->d_lock);
-			cpu_relax();
+			cpu_chill();
 			goto again;
 		}
 		dentry->d_flags &= ~DCACHE_CANT_MOUNT;
@@ -2412,21 +2424,24 @@ static inline void end_dir_add(struct in
 
 static void d_wait_lookup(struct dentry *dentry)
 {
-	if (d_in_lookup(dentry)) {
-		DECLARE_WAITQUEUE(wait, current);
-		add_wait_queue(dentry->d_wait, &wait);
-		do {
-			set_current_state(TASK_UNINTERRUPTIBLE);
-			spin_unlock(&dentry->d_lock);
-			schedule();
-			spin_lock(&dentry->d_lock);
-		} while (d_in_lookup(dentry));
-	}
+	struct swait_queue __wait;
+
+	if (!d_in_lookup(dentry))
+		return;
+
+	INIT_LIST_HEAD(&__wait.task_list);
+	do {
+		prepare_to_swait(dentry->d_wait, &__wait, TASK_UNINTERRUPTIBLE);
+		spin_unlock(&dentry->d_lock);
+		schedule();
+		spin_lock(&dentry->d_lock);
+	} while (d_in_lookup(dentry));
+	finish_swait(dentry->d_wait, &__wait);
 }
 
 struct dentry *d_alloc_parallel(struct dentry *parent,
 				const struct qstr *name,
-				wait_queue_head_t *wq)
+				struct swait_queue_head *wq)
 {
 	unsigned int hash = name->hash;
 	struct hlist_bl_head *b = in_lookup_hash(parent, hash);
@@ -2535,7 +2550,7 @@ void __d_lookup_done(struct dentry *dent
 	hlist_bl_lock(b);
 	dentry->d_flags &= ~DCACHE_PAR_LOOKUP;
 	__hlist_bl_del(&dentry->d_u.d_in_lookup_hash);
-	wake_up_all(dentry->d_wait);
+	swake_up_all(dentry->d_wait);
 	dentry->d_wait = NULL;
 	hlist_bl_unlock(b);
 	INIT_HLIST_NODE(&dentry->d_u.d_alias);
@@ -3632,6 +3647,11 @@ EXPORT_SYMBOL(d_genocide);
 
 void __init vfs_caches_init_early(void)
 {
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(in_lookup_hashtable); i++)
+		INIT_HLIST_BL_HEAD(&in_lookup_hashtable[i]);
+
 	dcache_init_early();
 	inode_init_early();
 }
Index: linux-4.9.20-rt16/fs/eventpoll.c
===================================================================
--- linux-4.9.20-rt16.orig/fs/eventpoll.c
+++ linux-4.9.20-rt16/fs/eventpoll.c
@@ -510,12 +510,12 @@ static int ep_poll_wakeup_proc(void *pri
  */
 static void ep_poll_safewake(wait_queue_head_t *wq)
 {
-	int this_cpu = get_cpu();
+	int this_cpu = get_cpu_light();
 
 	ep_call_nested(&poll_safewake_ncalls, EP_MAX_NESTS,
 		       ep_poll_wakeup_proc, NULL, wq, (void *) (long) this_cpu);
 
-	put_cpu();
+	put_cpu_light();
 }
 
 static void ep_remove_wait_queue(struct eppoll_entry *pwq)
Index: linux-4.9.20-rt16/fs/exec.c
===================================================================
--- linux-4.9.20-rt16.orig/fs/exec.c
+++ linux-4.9.20-rt16/fs/exec.c
@@ -1038,12 +1038,14 @@ static int exec_mmap(struct mm_struct *m
 		}
 	}
 	task_lock(tsk);
+	preempt_disable_rt();
 	active_mm = tsk->active_mm;
 	tsk->mm = mm;
 	tsk->active_mm = mm;
 	activate_mm(active_mm, mm);
 	tsk->mm->vmacache_seqnum = 0;
 	vmacache_flush(tsk);
+	preempt_enable_rt();
 	task_unlock(tsk);
 	if (old_mm) {
 		up_read(&old_mm->mmap_sem);
Index: linux-4.9.20-rt16/fs/fuse/dir.c
===================================================================
--- linux-4.9.20-rt16.orig/fs/fuse/dir.c
+++ linux-4.9.20-rt16/fs/fuse/dir.c
@@ -1191,7 +1191,7 @@ static int fuse_direntplus_link(struct f
 	struct inode *dir = d_inode(parent);
 	struct fuse_conn *fc;
 	struct inode *inode;
-	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+	DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
 
 	if (!o->nodeid) {
 		/*
Index: linux-4.9.20-rt16/fs/jbd2/checkpoint.c
===================================================================
--- linux-4.9.20-rt16.orig/fs/jbd2/checkpoint.c
+++ linux-4.9.20-rt16/fs/jbd2/checkpoint.c
@@ -116,6 +116,8 @@ void __jbd2_log_wait_for_space(journal_t
 	nblocks = jbd2_space_needed(journal);
 	while (jbd2_log_space_left(journal) < nblocks) {
 		write_unlock(&journal->j_state_lock);
+		if (current->plug)
+			io_schedule();
 		mutex_lock(&journal->j_checkpoint_mutex);
 
 		/*
Index: linux-4.9.20-rt16/fs/locks.c
===================================================================
--- linux-4.9.20-rt16.orig/fs/locks.c
+++ linux-4.9.20-rt16/fs/locks.c
@@ -935,7 +935,7 @@ static int flock_lock_inode(struct inode
 			return -ENOMEM;
 	}
 
-	percpu_down_read_preempt_disable(&file_rwsem);
+	percpu_down_read(&file_rwsem);
 	spin_lock(&ctx->flc_lock);
 	if (request->fl_flags & FL_ACCESS)
 		goto find_conflict;
@@ -976,7 +976,7 @@ find_conflict:
 
 out:
 	spin_unlock(&ctx->flc_lock);
-	percpu_up_read_preempt_enable(&file_rwsem);
+	percpu_up_read(&file_rwsem);
 	if (new_fl)
 		locks_free_lock(new_fl);
 	locks_dispose_list(&dispose);
@@ -1013,7 +1013,7 @@ static int posix_lock_inode(struct inode
 		new_fl2 = locks_alloc_lock();
 	}
 
-	percpu_down_read_preempt_disable(&file_rwsem);
+	percpu_down_read(&file_rwsem);
 	spin_lock(&ctx->flc_lock);
 	/*
 	 * New lock request. Walk all POSIX locks and look for conflicts. If
@@ -1185,7 +1185,7 @@ static int posix_lock_inode(struct inode
 	}
  out:
 	spin_unlock(&ctx->flc_lock);
-	percpu_up_read_preempt_enable(&file_rwsem);
+	percpu_up_read(&file_rwsem);
 	/*
 	 * Free any unused locks.
 	 */
@@ -1460,7 +1460,7 @@ int __break_lease(struct inode *inode, u
 		return error;
 	}
 
-	percpu_down_read_preempt_disable(&file_rwsem);
+	percpu_down_read(&file_rwsem);
 	spin_lock(&ctx->flc_lock);
 
 	time_out_leases(inode, &dispose);
@@ -1512,13 +1512,13 @@ restart:
 	locks_insert_block(fl, new_fl);
 	trace_break_lease_block(inode, new_fl);
 	spin_unlock(&ctx->flc_lock);
-	percpu_up_read_preempt_enable(&file_rwsem);
+	percpu_up_read(&file_rwsem);
 
 	locks_dispose_list(&dispose);
 	error = wait_event_interruptible_timeout(new_fl->fl_wait,
 						!new_fl->fl_next, break_time);
 
-	percpu_down_read_preempt_disable(&file_rwsem);
+	percpu_down_read(&file_rwsem);
 	spin_lock(&ctx->flc_lock);
 	trace_break_lease_unblock(inode, new_fl);
 	locks_delete_block(new_fl);
@@ -1535,7 +1535,7 @@ restart:
 	}
 out:
 	spin_unlock(&ctx->flc_lock);
-	percpu_up_read_preempt_enable(&file_rwsem);
+	percpu_up_read(&file_rwsem);
 	locks_dispose_list(&dispose);
 	locks_free_lock(new_fl);
 	return error;
@@ -1609,7 +1609,7 @@ int fcntl_getlease(struct file *filp)
 
 	ctx = smp_load_acquire(&inode->i_flctx);
 	if (ctx && !list_empty_careful(&ctx->flc_lease)) {
-		percpu_down_read_preempt_disable(&file_rwsem);
+		percpu_down_read(&file_rwsem);
 		spin_lock(&ctx->flc_lock);
 		time_out_leases(inode, &dispose);
 		list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
@@ -1619,7 +1619,7 @@ int fcntl_getlease(struct file *filp)
 			break;
 		}
 		spin_unlock(&ctx->flc_lock);
-		percpu_up_read_preempt_enable(&file_rwsem);
+		percpu_up_read(&file_rwsem);
 
 		locks_dispose_list(&dispose);
 	}
@@ -1694,7 +1694,7 @@ generic_add_lease(struct file *filp, lon
 		return -EINVAL;
 	}
 
-	percpu_down_read_preempt_disable(&file_rwsem);
+	percpu_down_read(&file_rwsem);
 	spin_lock(&ctx->flc_lock);
 	time_out_leases(inode, &dispose);
 	error = check_conflicting_open(dentry, arg, lease->fl_flags);
@@ -1765,7 +1765,7 @@ out_setup:
 		lease->fl_lmops->lm_setup(lease, priv);
 out:
 	spin_unlock(&ctx->flc_lock);
-	percpu_up_read_preempt_enable(&file_rwsem);
+	percpu_up_read(&file_rwsem);
 	locks_dispose_list(&dispose);
 	if (is_deleg)
 		inode_unlock(inode);
@@ -1788,7 +1788,7 @@ static int generic_delete_lease(struct f
 		return error;
 	}
 
-	percpu_down_read_preempt_disable(&file_rwsem);
+	percpu_down_read(&file_rwsem);
 	spin_lock(&ctx->flc_lock);
 	list_for_each_entry(fl, &ctx->flc_lease, fl_list) {
 		if (fl->fl_file == filp &&
@@ -1801,7 +1801,7 @@ static int generic_delete_lease(struct f
 	if (victim)
 		error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose);
 	spin_unlock(&ctx->flc_lock);
-	percpu_up_read_preempt_enable(&file_rwsem);
+	percpu_up_read(&file_rwsem);
 	locks_dispose_list(&dispose);
 	return error;
 }
@@ -2532,13 +2532,13 @@ locks_remove_lease(struct file *filp, st
 	if (list_empty(&ctx->flc_lease))
 		return;
 
-	percpu_down_read_preempt_disable(&file_rwsem);
+	percpu_down_read(&file_rwsem);
 	spin_lock(&ctx->flc_lock);
 	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list)
 		if (filp == fl->fl_file)
 			lease_modify(fl, F_UNLCK, &dispose);
 	spin_unlock(&ctx->flc_lock);
-	percpu_up_read_preempt_enable(&file_rwsem);
+	percpu_up_read(&file_rwsem);
 
 	locks_dispose_list(&dispose);
 }
Index: linux-4.9.20-rt16/fs/namei.c
===================================================================
--- linux-4.9.20-rt16.orig/fs/namei.c
+++ linux-4.9.20-rt16/fs/namei.c
@@ -1626,7 +1626,7 @@ static struct dentry *lookup_slow(const
 {
 	struct dentry *dentry = ERR_PTR(-ENOENT), *old;
 	struct inode *inode = dir->d_inode;
-	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+	DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
 
 	inode_lock_shared(inode);
 	/* Don't go there if it's already dead */
@@ -3083,7 +3083,7 @@ static int lookup_open(struct nameidata
 	struct dentry *dentry;
 	int error, create_error = 0;
 	umode_t mode = op->mode;
-	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+	DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
 
 	if (unlikely(IS_DEADDIR(dir_inode)))
 		return -ENOENT;
Index: linux-4.9.20-rt16/fs/namespace.c
===================================================================
--- linux-4.9.20-rt16.orig/fs/namespace.c
+++ linux-4.9.20-rt16/fs/namespace.c
@@ -14,6 +14,7 @@
 #include <linux/mnt_namespace.h>
 #include <linux/user_namespace.h>
 #include <linux/namei.h>
+#include <linux/delay.h>
 #include <linux/security.h>
 #include <linux/idr.h>
 #include <linux/init.h>		/* init_rootfs */
@@ -357,8 +358,11 @@ int __mnt_want_write(struct vfsmount *m)
 	 * incremented count after it has set MNT_WRITE_HOLD.
 	 */
 	smp_mb();
-	while (ACCESS_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD)
-		cpu_relax();
+	while (ACCESS_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) {
+		preempt_enable();
+		cpu_chill();
+		preempt_disable();
+	}
 	/*
 	 * After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will
 	 * be set to match its requirements. So we must not load that until
Index: linux-4.9.20-rt16/fs/nfs/delegation.c
===================================================================
--- linux-4.9.20-rt16.orig/fs/nfs/delegation.c
+++ linux-4.9.20-rt16/fs/nfs/delegation.c
@@ -150,11 +150,11 @@ again:
 		sp = state->owner;
 		/* Block nfs4_proc_unlck */
 		mutex_lock(&sp->so_delegreturn_mutex);
-		seq = raw_seqcount_begin(&sp->so_reclaim_seqcount);
+		seq = read_seqbegin(&sp->so_reclaim_seqlock);
 		err = nfs4_open_delegation_recall(ctx, state, stateid, type);
 		if (!err)
 			err = nfs_delegation_claim_locks(ctx, state, stateid);
-		if (!err && read_seqcount_retry(&sp->so_reclaim_seqcount, seq))
+		if (!err && read_seqretry(&sp->so_reclaim_seqlock, seq))
 			err = -EAGAIN;
 		mutex_unlock(&sp->so_delegreturn_mutex);
 		put_nfs_open_context(ctx);
Index: linux-4.9.20-rt16/fs/nfs/dir.c
===================================================================
--- linux-4.9.20-rt16.orig/fs/nfs/dir.c
+++ linux-4.9.20-rt16/fs/nfs/dir.c
@@ -485,7 +485,7 @@ static
 void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
 {
 	struct qstr filename = QSTR_INIT(entry->name, entry->len);
-	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+	DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
 	struct dentry *dentry;
 	struct dentry *alias;
 	struct inode *dir = d_inode(parent);
@@ -1491,7 +1491,7 @@ int nfs_atomic_open(struct inode *dir, s
 		    struct file *file, unsigned open_flags,
 		    umode_t mode, int *opened)
 {
-	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+	DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
 	struct nfs_open_context *ctx;
 	struct dentry *res;
 	struct iattr attr = { .ia_valid = ATTR_OPEN };
@@ -1806,7 +1806,11 @@ int nfs_rmdir(struct inode *dir, struct
 
 	trace_nfs_rmdir_enter(dir, dentry);
 	if (d_really_is_positive(dentry)) {
+#ifdef CONFIG_PREEMPT_RT_BASE
+		down(&NFS_I(d_inode(dentry))->rmdir_sem);
+#else
 		down_write(&NFS_I(d_inode(dentry))->rmdir_sem);
+#endif
 		error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name);
 		/* Ensure the VFS deletes this inode */
 		switch (error) {
@@ -1816,7 +1820,11 @@ int nfs_rmdir(struct inode *dir, struct
 		case -ENOENT:
 			nfs_dentry_handle_enoent(dentry);
 		}
+#ifdef CONFIG_PREEMPT_RT_BASE
+		up(&NFS_I(d_inode(dentry))->rmdir_sem);
+#else
 		up_write(&NFS_I(d_inode(dentry))->rmdir_sem);
+#endif
 	} else
 		error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name);
 	trace_nfs_rmdir_exit(dir, dentry, error);
Index: linux-4.9.20-rt16/fs/nfs/inode.c
===================================================================
--- linux-4.9.20-rt16.orig/fs/nfs/inode.c
+++ linux-4.9.20-rt16/fs/nfs/inode.c
@@ -1957,7 +1957,11 @@ static void init_once(void *foo)
 	nfsi->nrequests = 0;
 	nfsi->commit_info.ncommit = 0;
 	atomic_set(&nfsi->commit_info.rpcs_out, 0);
+#ifdef CONFIG_PREEMPT_RT_BASE
+	sema_init(&nfsi->rmdir_sem, 1);
+#else
 	init_rwsem(&nfsi->rmdir_sem);
+#endif
 	nfs4_init_once(nfsi);
 }
 
Index: linux-4.9.20-rt16/fs/nfs/nfs4_fs.h
===================================================================
--- linux-4.9.20-rt16.orig/fs/nfs/nfs4_fs.h
+++ linux-4.9.20-rt16/fs/nfs/nfs4_fs.h
@@ -111,7 +111,7 @@ struct nfs4_state_owner {
 	unsigned long	     so_flags;
 	struct list_head     so_states;
 	struct nfs_seqid_counter so_seqid;
-	seqcount_t	     so_reclaim_seqcount;
+	seqlock_t	     so_reclaim_seqlock;
 	struct mutex	     so_delegreturn_mutex;
 };
 
Index: linux-4.9.20-rt16/fs/nfs/nfs4proc.c
===================================================================
--- linux-4.9.20-rt16.orig/fs/nfs/nfs4proc.c
+++ linux-4.9.20-rt16/fs/nfs/nfs4proc.c
@@ -2695,7 +2695,7 @@ static int _nfs4_open_and_get_state(stru
 	unsigned int seq;
 	int ret;
 
-	seq = raw_seqcount_begin(&sp->so_reclaim_seqcount);
+	seq = raw_seqcount_begin(&sp->so_reclaim_seqlock.seqcount);
 
 	ret = _nfs4_proc_open(opendata);
 	if (ret != 0)
@@ -2733,7 +2733,7 @@ static int _nfs4_open_and_get_state(stru
 
 	if (d_inode(dentry) == state->inode) {
 		nfs_inode_attach_open_context(ctx);
-		if (read_seqcount_retry(&sp->so_reclaim_seqcount, seq))
+		if (read_seqretry(&sp->so_reclaim_seqlock, seq))
 			nfs4_schedule_stateid_recovery(server, state);
 	}
 out:
Index: linux-4.9.20-rt16/fs/nfs/nfs4state.c
===================================================================
--- linux-4.9.20-rt16.orig/fs/nfs/nfs4state.c
+++ linux-4.9.20-rt16/fs/nfs/nfs4state.c
@@ -488,7 +488,7 @@ nfs4_alloc_state_owner(struct nfs_server
 	nfs4_init_seqid_counter(&sp->so_seqid);
 	atomic_set(&sp->so_count, 1);
 	INIT_LIST_HEAD(&sp->so_lru);
-	seqcount_init(&sp->so_reclaim_seqcount);
+	seqlock_init(&sp->so_reclaim_seqlock);
 	mutex_init(&sp->so_delegreturn_mutex);
 	return sp;
 }
@@ -1498,8 +1498,12 @@ static int nfs4_reclaim_open_state(struc
 	 * recovering after a network partition or a reboot from a
 	 * server that doesn't support a grace period.
 	 */
+#ifdef CONFIG_PREEMPT_RT_FULL
+	write_seqlock(&sp->so_reclaim_seqlock);
+#else
+	write_seqcount_begin(&sp->so_reclaim_seqlock.seqcount);
+#endif
 	spin_lock(&sp->so_lock);
-	raw_write_seqcount_begin(&sp->so_reclaim_seqcount);
 restart:
 	list_for_each_entry(state, &sp->so_states, open_states) {
 		if (!test_and_clear_bit(ops->state_flag_bit, &state->flags))
@@ -1568,14 +1572,20 @@ restart:
 		spin_lock(&sp->so_lock);
 		goto restart;
 	}
-	raw_write_seqcount_end(&sp->so_reclaim_seqcount);
 	spin_unlock(&sp->so_lock);
+#ifdef CONFIG_PREEMPT_RT_FULL
+	write_sequnlock(&sp->so_reclaim_seqlock);
+#else
+	write_seqcount_end(&sp->so_reclaim_seqlock.seqcount);
+#endif
 	return 0;
 out_err:
 	nfs4_put_open_state(state);
-	spin_lock(&sp->so_lock);
-	raw_write_seqcount_end(&sp->so_reclaim_seqcount);
-	spin_unlock(&sp->so_lock);
+#ifdef CONFIG_PREEMPT_RT_FULL
+	write_sequnlock(&sp->so_reclaim_seqlock);
+#else
+	write_seqcount_end(&sp->so_reclaim_seqlock.seqcount);
+#endif
 	return status;
 }
 
Index: linux-4.9.20-rt16/fs/nfs/unlink.c
===================================================================
--- linux-4.9.20-rt16.orig/fs/nfs/unlink.c
+++ linux-4.9.20-rt16/fs/nfs/unlink.c
@@ -12,7 +12,7 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/nfs_fs.h>
 #include <linux/sched.h>
-#include <linux/wait.h>
+#include <linux/swait.h>
 #include <linux/namei.h>
 #include <linux/fsnotify.h>
 
@@ -51,6 +51,29 @@ static void nfs_async_unlink_done(struct
 		rpc_restart_call_prepare(task);
 }
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+static void nfs_down_anon(struct semaphore *sema)
+{
+	down(sema);
+}
+
+static void nfs_up_anon(struct semaphore *sema)
+{
+	up(sema);
+}
+
+#else
+static void nfs_down_anon(struct rw_semaphore *rwsem)
+{
+	down_read_non_owner(rwsem);
+}
+
+static void nfs_up_anon(struct rw_semaphore *rwsem)
+{
+	up_read_non_owner(rwsem);
+}
+#endif
+
 /**
  * nfs_async_unlink_release - Release the sillydelete data.
  * @task: rpc_task of the sillydelete
@@ -64,7 +87,7 @@ static void nfs_async_unlink_release(voi
 	struct dentry *dentry = data->dentry;
 	struct super_block *sb = dentry->d_sb;
 
-	up_read_non_owner(&NFS_I(d_inode(dentry->d_parent))->rmdir_sem);
+	nfs_up_anon(&NFS_I(d_inode(dentry->d_parent))->rmdir_sem);
 	d_lookup_done(dentry);
 	nfs_free_unlinkdata(data);
 	dput(dentry);
@@ -117,10 +140,10 @@ static int nfs_call_unlink(struct dentry
 	struct inode *dir = d_inode(dentry->d_parent);
 	struct dentry *alias;
 
-	down_read_non_owner(&NFS_I(dir)->rmdir_sem);
+	nfs_down_anon(&NFS_I(dir)->rmdir_sem);
 	alias = d_alloc_parallel(dentry->d_parent, &data->args.name, &data->wq);
 	if (IS_ERR(alias)) {
-		up_read_non_owner(&NFS_I(dir)->rmdir_sem);
+		nfs_up_anon(&NFS_I(dir)->rmdir_sem);
 		return 0;
 	}
 	if (!d_in_lookup(alias)) {
@@ -142,7 +165,7 @@ static int nfs_call_unlink(struct dentry
 			ret = 0;
 		spin_unlock(&alias->d_lock);
 		dput(alias);
-		up_read_non_owner(&NFS_I(dir)->rmdir_sem);
+		nfs_up_anon(&NFS_I(dir)->rmdir_sem);
 		/*
 		 * If we'd displaced old cached devname, free it.  At that
 		 * point dentry is definitely not a root, so we won't need
@@ -182,7 +205,7 @@ nfs_async_unlink(struct dentry *dentry,
 		goto out_free_name;
 	}
 	data->res.dir_attr = &data->dir_attr;
-	init_waitqueue_head(&data->wq);
+	init_swait_queue_head(&data->wq);
 
 	status = -EBUSY;
 	spin_lock(&dentry->d_lock);
Index: linux-4.9.20-rt16/fs/ntfs/aops.c
===================================================================
--- linux-4.9.20-rt16.orig/fs/ntfs/aops.c
+++ linux-4.9.20-rt16/fs/ntfs/aops.c
@@ -92,13 +92,13 @@ static void ntfs_end_buffer_async_read(s
 			ofs = 0;
 			if (file_ofs < init_size)
 				ofs = init_size - file_ofs;
-			local_irq_save(flags);
+			local_irq_save_nort(flags);
 			kaddr = kmap_atomic(page);
 			memset(kaddr + bh_offset(bh) + ofs, 0,
 					bh->b_size - ofs);
 			flush_dcache_page(page);
 			kunmap_atomic(kaddr);
-			local_irq_restore(flags);
+			local_irq_restore_nort(flags);
 		}
 	} else {
 		clear_buffer_uptodate(bh);
@@ -107,8 +107,7 @@ static void ntfs_end_buffer_async_read(s
 				"0x%llx.", (unsigned long long)bh->b_blocknr);
 	}
 	first = page_buffers(page);
-	local_irq_save(flags);
-	bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
+	flags = bh_uptodate_lock_irqsave(first);
 	clear_buffer_async_read(bh);
 	unlock_buffer(bh);
 	tmp = bh;
@@ -123,8 +122,7 @@ static void ntfs_end_buffer_async_read(s
 		}
 		tmp = tmp->b_this_page;
 	} while (tmp != bh);
-	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
-	local_irq_restore(flags);
+	bh_uptodate_unlock_irqrestore(first, flags);
 	/*
 	 * If none of the buffers had errors then we can set the page uptodate,
 	 * but we first have to perform the post read mst fixups, if the
@@ -145,13 +143,13 @@ static void ntfs_end_buffer_async_read(s
 		recs = PAGE_SIZE / rec_size;
 		/* Should have been verified before we got here... */
 		BUG_ON(!recs);
-		local_irq_save(flags);
+		local_irq_save_nort(flags);
 		kaddr = kmap_atomic(page);
 		for (i = 0; i < recs; i++)
 			post_read_mst_fixup((NTFS_RECORD*)(kaddr +
 					i * rec_size), rec_size);
 		kunmap_atomic(kaddr);
-		local_irq_restore(flags);
+		local_irq_restore_nort(flags);
 		flush_dcache_page(page);
 		if (likely(page_uptodate && !PageError(page)))
 			SetPageUptodate(page);
@@ -159,9 +157,7 @@ static void ntfs_end_buffer_async_read(s
 	unlock_page(page);
 	return;
 still_busy:
-	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
-	local_irq_restore(flags);
-	return;
+	bh_uptodate_unlock_irqrestore(first, flags);
 }
 
 /**
Index: linux-4.9.20-rt16/fs/proc/base.c
===================================================================
--- linux-4.9.20-rt16.orig/fs/proc/base.c
+++ linux-4.9.20-rt16/fs/proc/base.c
@@ -1834,7 +1834,7 @@ bool proc_fill_cache(struct file *file,
 
 	child = d_hash_and_lookup(dir, &qname);
 	if (!child) {
-		DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+		DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
 		child = d_alloc_parallel(dir, &qname, &wq);
 		if (IS_ERR(child))
 			goto end_instantiate;
Index: linux-4.9.20-rt16/fs/proc/proc_sysctl.c
===================================================================
--- linux-4.9.20-rt16.orig/fs/proc/proc_sysctl.c
+++ linux-4.9.20-rt16/fs/proc/proc_sysctl.c
@@ -632,7 +632,7 @@ static bool proc_sys_fill_cache(struct f
 
 	child = d_lookup(dir, &qname);
 	if (!child) {
-		DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+		DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
 		child = d_alloc_parallel(dir, &qname, &wq);
 		if (IS_ERR(child))
 			return false;
Index: linux-4.9.20-rt16/fs/timerfd.c
===================================================================
--- linux-4.9.20-rt16.orig/fs/timerfd.c
+++ linux-4.9.20-rt16/fs/timerfd.c
@@ -471,7 +471,10 @@ static int do_timerfd_settime(int ufd, i
 				break;
 		}
 		spin_unlock_irq(&ctx->wqh.lock);
-		cpu_relax();
+		if (isalarm(ctx))
+			hrtimer_wait_for_timer(&ctx->t.alarm.timer);
+		else
+			hrtimer_wait_for_timer(&ctx->t.tmr);
 	}
 
 	/*
Index: linux-4.9.20-rt16/include/acpi/platform/aclinux.h
===================================================================
--- linux-4.9.20-rt16.orig/include/acpi/platform/aclinux.h
+++ linux-4.9.20-rt16/include/acpi/platform/aclinux.h
@@ -133,6 +133,7 @@
 
 #define acpi_cache_t                        struct kmem_cache
 #define acpi_spinlock                       spinlock_t *
+#define acpi_raw_spinlock		raw_spinlock_t *
 #define acpi_cpu_flags                      unsigned long
 
 /* Use native linux version of acpi_os_allocate_zeroed */
@@ -151,6 +152,20 @@
 #define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_get_thread_id
 #define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_create_lock
 
+#define acpi_os_create_raw_lock(__handle)			\
+({								\
+	 raw_spinlock_t *lock = ACPI_ALLOCATE(sizeof(*lock));	\
+								\
+	 if (lock) {						\
+		*(__handle) = lock;				\
+		raw_spin_lock_init(*(__handle));		\
+	 }							\
+	 lock ? AE_OK : AE_NO_MEMORY;				\
+ })
+
+#define acpi_os_delete_raw_lock(__handle)	kfree(__handle)
+
+
 /*
  * OSL interfaces used by debugger/disassembler
  */
Index: linux-4.9.20-rt16/include/asm-generic/bug.h
===================================================================
--- linux-4.9.20-rt16.orig/include/asm-generic/bug.h
+++ linux-4.9.20-rt16/include/asm-generic/bug.h
@@ -215,6 +215,20 @@ void __warn(const char *file, int line,
 # define WARN_ON_SMP(x)			({0;})
 #endif
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+# define BUG_ON_RT(c)			BUG_ON(c)
+# define BUG_ON_NONRT(c)		do { } while (0)
+# define WARN_ON_RT(condition)		WARN_ON(condition)
+# define WARN_ON_NONRT(condition)	do { } while (0)
+# define WARN_ON_ONCE_NONRT(condition)	do { } while (0)
+#else
+# define BUG_ON_RT(c)			do { } while (0)
+# define BUG_ON_NONRT(c)		BUG_ON(c)
+# define WARN_ON_RT(condition)		do { } while (0)
+# define WARN_ON_NONRT(condition)	WARN_ON(condition)
+# define WARN_ON_ONCE_NONRT(condition)	WARN_ON_ONCE(condition)
+#endif
+
 #endif /* __ASSEMBLY__ */
 
 #endif
Index: linux-4.9.20-rt16/include/linux/blk-mq.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/blk-mq.h
+++ linux-4.9.20-rt16/include/linux/blk-mq.h
@@ -209,7 +209,7 @@ static inline u16 blk_mq_unique_tag_to_t
 	return unique_tag & BLK_MQ_UNIQUE_TAG_MASK;
 }
 
-
+void __blk_mq_complete_request_remote_work(struct work_struct *work);
 int blk_mq_request_started(struct request *rq);
 void blk_mq_start_request(struct request *rq);
 void blk_mq_end_request(struct request *rq, int error);
Index: linux-4.9.20-rt16/include/linux/blkdev.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/blkdev.h
+++ linux-4.9.20-rt16/include/linux/blkdev.h
@@ -89,6 +89,7 @@ struct request {
 	struct list_head queuelist;
 	union {
 		struct call_single_data csd;
+		struct work_struct work;
 		u64 fifo_time;
 	};
 
@@ -467,7 +468,7 @@ struct request_queue {
 	struct throtl_data *td;
 #endif
 	struct rcu_head		rcu_head;
-	wait_queue_head_t	mq_freeze_wq;
+	struct swait_queue_head	mq_freeze_wq;
 	struct percpu_ref	q_usage_counter;
 	struct list_head	all_q_node;
 
Index: linux-4.9.20-rt16/include/linux/bottom_half.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/bottom_half.h
+++ linux-4.9.20-rt16/include/linux/bottom_half.h
@@ -3,6 +3,39 @@
 
 #include <linux/preempt.h>
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+
+extern void __local_bh_disable(void);
+extern void _local_bh_enable(void);
+extern void __local_bh_enable(void);
+
+static inline void local_bh_disable(void)
+{
+	__local_bh_disable();
+}
+
+static inline void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
+{
+	__local_bh_disable();
+}
+
+static inline void local_bh_enable(void)
+{
+	__local_bh_enable();
+}
+
+static inline void __local_bh_enable_ip(unsigned long ip, unsigned int cnt)
+{
+	__local_bh_enable();
+}
+
+static inline void local_bh_enable_ip(unsigned long ip)
+{
+	__local_bh_enable();
+}
+
+#else
+
 #ifdef CONFIG_TRACE_IRQFLAGS
 extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt);
 #else
@@ -30,5 +63,6 @@ static inline void local_bh_enable(void)
 {
 	__local_bh_enable_ip(_THIS_IP_, SOFTIRQ_DISABLE_OFFSET);
 }
+#endif
 
 #endif /* _LINUX_BH_H */
Index: linux-4.9.20-rt16/include/linux/buffer_head.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/buffer_head.h
+++ linux-4.9.20-rt16/include/linux/buffer_head.h
@@ -75,8 +75,50 @@ struct buffer_head {
 	struct address_space *b_assoc_map;	/* mapping this buffer is
 						   associated with */
 	atomic_t b_count;		/* users using this buffer_head */
+#ifdef CONFIG_PREEMPT_RT_BASE
+	spinlock_t b_uptodate_lock;
+#if IS_ENABLED(CONFIG_JBD2)
+	spinlock_t b_state_lock;
+	spinlock_t b_journal_head_lock;
+#endif
+#endif
 };
 
+static inline unsigned long bh_uptodate_lock_irqsave(struct buffer_head *bh)
+{
+	unsigned long flags;
+
+#ifndef CONFIG_PREEMPT_RT_BASE
+	local_irq_save(flags);
+	bit_spin_lock(BH_Uptodate_Lock, &bh->b_state);
+#else
+	spin_lock_irqsave(&bh->b_uptodate_lock, flags);
+#endif
+	return flags;
+}
+
+static inline void
+bh_uptodate_unlock_irqrestore(struct buffer_head *bh, unsigned long flags)
+{
+#ifndef CONFIG_PREEMPT_RT_BASE
+	bit_spin_unlock(BH_Uptodate_Lock, &bh->b_state);
+	local_irq_restore(flags);
+#else
+	spin_unlock_irqrestore(&bh->b_uptodate_lock, flags);
+#endif
+}
+
+static inline void buffer_head_init_locks(struct buffer_head *bh)
+{
+#ifdef CONFIG_PREEMPT_RT_BASE
+	spin_lock_init(&bh->b_uptodate_lock);
+#if IS_ENABLED(CONFIG_JBD2)
+	spin_lock_init(&bh->b_state_lock);
+	spin_lock_init(&bh->b_journal_head_lock);
+#endif
+#endif
+}
+
 /*
  * macro tricks to expand the set_buffer_foo(), clear_buffer_foo()
  * and buffer_foo() functions.
Index: linux-4.9.20-rt16/include/linux/cgroup-defs.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/cgroup-defs.h
+++ linux-4.9.20-rt16/include/linux/cgroup-defs.h
@@ -16,6 +16,7 @@
 #include <linux/percpu-refcount.h>
 #include <linux/percpu-rwsem.h>
 #include <linux/workqueue.h>
+#include <linux/swork.h>
 
 #ifdef CONFIG_CGROUPS
 
@@ -138,6 +139,7 @@ struct cgroup_subsys_state {
 	/* percpu_ref killing and RCU release */
 	struct rcu_head rcu_head;
 	struct work_struct destroy_work;
+	struct swork_event destroy_swork;
 };
 
 /*
Index: linux-4.9.20-rt16/include/linux/completion.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/completion.h
+++ linux-4.9.20-rt16/include/linux/completion.h
@@ -7,8 +7,7 @@
  * Atomic wait-for-completion handler data structures.
  * See kernel/sched/completion.c for details.
  */
-
-#include <linux/wait.h>
+#include <linux/swait.h>
 
 /*
  * struct completion - structure used to maintain state for a "completion"
@@ -24,11 +23,11 @@
  */
 struct completion {
 	unsigned int done;
-	wait_queue_head_t wait;
+	struct swait_queue_head wait;
 };
 
 #define COMPLETION_INITIALIZER(work) \
-	{ 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) }
+	{ 0, __SWAIT_QUEUE_HEAD_INITIALIZER((work).wait) }
 
 #define COMPLETION_INITIALIZER_ONSTACK(work) \
 	({ init_completion(&work); work; })
@@ -73,7 +72,7 @@ struct completion {
 static inline void init_completion(struct completion *x)
 {
 	x->done = 0;
-	init_waitqueue_head(&x->wait);
+	init_swait_queue_head(&x->wait);
 }
 
 /**
Index: linux-4.9.20-rt16/include/linux/cpu.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/cpu.h
+++ linux-4.9.20-rt16/include/linux/cpu.h
@@ -182,6 +182,8 @@ extern void get_online_cpus(void);
 extern void put_online_cpus(void);
 extern void cpu_hotplug_disable(void);
 extern void cpu_hotplug_enable(void);
+extern void pin_current_cpu(void);
+extern void unpin_current_cpu(void);
 #define hotcpu_notifier(fn, pri)	cpu_notifier(fn, pri)
 #define __hotcpu_notifier(fn, pri)	__cpu_notifier(fn, pri)
 #define register_hotcpu_notifier(nb)	register_cpu_notifier(nb)
@@ -199,6 +201,8 @@ static inline void cpu_hotplug_done(void
 #define put_online_cpus()	do { } while (0)
 #define cpu_hotplug_disable()	do { } while (0)
 #define cpu_hotplug_enable()	do { } while (0)
+static inline void pin_current_cpu(void) { }
+static inline void unpin_current_cpu(void) { }
 #define hotcpu_notifier(fn, pri)	do { (void)(fn); } while (0)
 #define __hotcpu_notifier(fn, pri)	do { (void)(fn); } while (0)
 /* These aren't inline functions due to a GCC bug. */
Index: linux-4.9.20-rt16/include/linux/dcache.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/dcache.h
+++ linux-4.9.20-rt16/include/linux/dcache.h
@@ -11,6 +11,7 @@
 #include <linux/rcupdate.h>
 #include <linux/lockref.h>
 #include <linux/stringhash.h>
+#include <linux/wait.h>
 
 struct path;
 struct vfsmount;
@@ -100,7 +101,7 @@ struct dentry {
 
 	union {
 		struct list_head d_lru;		/* LRU list */
-		wait_queue_head_t *d_wait;	/* in-lookup ones only */
+		struct swait_queue_head *d_wait;	/* in-lookup ones only */
 	};
 	struct list_head d_child;	/* child of parent list */
 	struct list_head d_subdirs;	/* our children */
@@ -230,7 +231,7 @@ extern void d_set_d_op(struct dentry *de
 extern struct dentry * d_alloc(struct dentry *, const struct qstr *);
 extern struct dentry * d_alloc_pseudo(struct super_block *, const struct qstr *);
 extern struct dentry * d_alloc_parallel(struct dentry *, const struct qstr *,
-					wait_queue_head_t *);
+					struct swait_queue_head *);
 extern struct dentry * d_splice_alias(struct inode *, struct dentry *);
 extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *);
 extern struct dentry * d_exact_alias(struct dentry *, struct inode *);
Index: linux-4.9.20-rt16/include/linux/delay.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/delay.h
+++ linux-4.9.20-rt16/include/linux/delay.h
@@ -52,4 +52,10 @@ static inline void ssleep(unsigned int s
 	msleep(seconds * 1000);
 }
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+extern void cpu_chill(void);
+#else
+# define cpu_chill()	cpu_relax()
+#endif
+
 #endif /* defined(_LINUX_DELAY_H) */
Index: linux-4.9.20-rt16/include/linux/highmem.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/highmem.h
+++ linux-4.9.20-rt16/include/linux/highmem.h
@@ -7,6 +7,7 @@
 #include <linux/mm.h>
 #include <linux/uaccess.h>
 #include <linux/hardirq.h>
+#include <linux/sched.h>
 
 #include <asm/cacheflush.h>
 
@@ -65,7 +66,7 @@ static inline void kunmap(struct page *p
 
 static inline void *kmap_atomic(struct page *page)
 {
-	preempt_disable();
+	preempt_disable_nort();
 	pagefault_disable();
 	return page_address(page);
 }
@@ -74,7 +75,7 @@ static inline void *kmap_atomic(struct p
 static inline void __kunmap_atomic(void *addr)
 {
 	pagefault_enable();
-	preempt_enable();
+	preempt_enable_nort();
 }
 
 #define kmap_atomic_pfn(pfn)	kmap_atomic(pfn_to_page(pfn))
@@ -86,32 +87,51 @@ static inline void __kunmap_atomic(void
 
 #if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32)
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 DECLARE_PER_CPU(int, __kmap_atomic_idx);
+#endif
 
 static inline int kmap_atomic_idx_push(void)
 {
+#ifndef CONFIG_PREEMPT_RT_FULL
 	int idx = __this_cpu_inc_return(__kmap_atomic_idx) - 1;
 
-#ifdef CONFIG_DEBUG_HIGHMEM
+# ifdef CONFIG_DEBUG_HIGHMEM
 	WARN_ON_ONCE(in_irq() && !irqs_disabled());
 	BUG_ON(idx >= KM_TYPE_NR);
-#endif
+# endif
 	return idx;
+#else
+	current->kmap_idx++;
+	BUG_ON(current->kmap_idx > KM_TYPE_NR);
+	return current->kmap_idx - 1;
+#endif
 }
 
 static inline int kmap_atomic_idx(void)
 {
+#ifndef CONFIG_PREEMPT_RT_FULL
 	return __this_cpu_read(__kmap_atomic_idx) - 1;
+#else
+	return current->kmap_idx - 1;
+#endif
 }
 
 static inline void kmap_atomic_idx_pop(void)
 {
-#ifdef CONFIG_DEBUG_HIGHMEM
+#ifndef CONFIG_PREEMPT_RT_FULL
+# ifdef CONFIG_DEBUG_HIGHMEM
 	int idx = __this_cpu_dec_return(__kmap_atomic_idx);
 
 	BUG_ON(idx < 0);
-#else
+# else
 	__this_cpu_dec(__kmap_atomic_idx);
+# endif
+#else
+	current->kmap_idx--;
+# ifdef CONFIG_DEBUG_HIGHMEM
+	BUG_ON(current->kmap_idx < 0);
+# endif
 #endif
 }
 
Index: linux-4.9.20-rt16/include/linux/hrtimer.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/hrtimer.h
+++ linux-4.9.20-rt16/include/linux/hrtimer.h
@@ -87,6 +87,9 @@ enum hrtimer_restart {
  * @function:	timer expiry callback function
  * @base:	pointer to the timer base (per cpu and per clock)
  * @state:	state information (See bit values above)
+ * @cb_entry:	list entry to defer timers from hardirq context
+ * @irqsafe:	timer can run in hardirq context
+ * @praecox:	timer expiry time if expired at the time of programming
  * @is_rel:	Set if the timer was armed relative
  * @start_pid:  timer statistics field to store the pid of the task which
  *		started the timer
@@ -103,6 +106,11 @@ struct hrtimer {
 	enum hrtimer_restart		(*function)(struct hrtimer *);
 	struct hrtimer_clock_base	*base;
 	u8				state;
+	struct list_head		cb_entry;
+	int				irqsafe;
+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
+	ktime_t				praecox;
+#endif
 	u8				is_rel;
 #ifdef CONFIG_TIMER_STATS
 	int				start_pid;
@@ -123,11 +131,7 @@ struct hrtimer_sleeper {
 	struct task_struct *task;
 };
 
-#ifdef CONFIG_64BIT
 # define HRTIMER_CLOCK_BASE_ALIGN	64
-#else
-# define HRTIMER_CLOCK_BASE_ALIGN	32
-#endif
 
 /**
  * struct hrtimer_clock_base - the timer base for a specific clock
@@ -136,6 +140,7 @@ struct hrtimer_sleeper {
  *			timer to a base on another cpu.
  * @clockid:		clock id for per_cpu support
  * @active:		red black tree root node for the active timers
+ * @expired:		list head for deferred timers.
  * @get_time:		function to retrieve the current time of the clock
  * @offset:		offset of this clock to the monotonic base
  */
@@ -144,6 +149,7 @@ struct hrtimer_clock_base {
 	int			index;
 	clockid_t		clockid;
 	struct timerqueue_head	active;
+	struct list_head	expired;
 	ktime_t			(*get_time)(void);
 	ktime_t			offset;
 } __attribute__((__aligned__(HRTIMER_CLOCK_BASE_ALIGN)));
@@ -187,6 +193,7 @@ struct hrtimer_cpu_base {
 	raw_spinlock_t			lock;
 	seqcount_t			seq;
 	struct hrtimer			*running;
+	struct hrtimer			*running_soft;
 	unsigned int			cpu;
 	unsigned int			active_bases;
 	unsigned int			clock_was_set_seq;
@@ -203,6 +210,9 @@ struct hrtimer_cpu_base {
 	unsigned int			nr_hangs;
 	unsigned int			max_hang_time;
 #endif
+#ifdef CONFIG_PREEMPT_RT_BASE
+	wait_queue_head_t		wait;
+#endif
 	struct hrtimer_clock_base	clock_base[HRTIMER_MAX_CLOCK_BASES];
 } ____cacheline_aligned;
 
@@ -412,6 +422,13 @@ static inline void hrtimer_restart(struc
 	hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
 }
 
+/* Softirq preemption could deadlock timer removal */
+#ifdef CONFIG_PREEMPT_RT_BASE
+  extern void hrtimer_wait_for_timer(const struct hrtimer *timer);
+#else
+# define hrtimer_wait_for_timer(timer)	do { cpu_relax(); } while (0)
+#endif
+
 /* Query timers: */
 extern ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust);
 
@@ -436,9 +453,15 @@ static inline int hrtimer_is_queued(stru
  * Helper function to check, whether the timer is running the callback
  * function
  */
-static inline int hrtimer_callback_running(struct hrtimer *timer)
+static inline int hrtimer_callback_running(const struct hrtimer *timer)
 {
-	return timer->base->cpu_base->running == timer;
+	if (timer->base->cpu_base->running == timer)
+		return 1;
+#ifdef CONFIG_PREEMPT_RT_BASE
+	if (timer->base->cpu_base->running_soft == timer)
+		return 1;
+#endif
+	return 0;
 }
 
 /* Forward a hrtimer so it expires after now: */
Index: linux-4.9.20-rt16/include/linux/idr.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/idr.h
+++ linux-4.9.20-rt16/include/linux/idr.h
@@ -95,10 +95,14 @@ bool idr_is_empty(struct idr *idp);
  * Each idr_preload() should be matched with an invocation of this
  * function.  See idr_preload() for details.
  */
+#ifdef CONFIG_PREEMPT_RT_FULL
+void idr_preload_end(void);
+#else
 static inline void idr_preload_end(void)
 {
 	preempt_enable();
 }
+#endif
 
 /**
  * idr_find - return pointer for given id
Index: linux-4.9.20-rt16/include/linux/init_task.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/init_task.h
+++ linux-4.9.20-rt16/include/linux/init_task.h
@@ -150,6 +150,12 @@ extern struct task_group root_task_group
 # define INIT_PERF_EVENTS(tsk)
 #endif
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+# define INIT_TIMER_LIST		.posix_timer_list = NULL,
+#else
+# define INIT_TIMER_LIST
+#endif
+
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 # define INIT_VTIME(tsk)						\
 	.vtime_seqcount = SEQCNT_ZERO(tsk.vtime_seqcount),	\
@@ -164,6 +170,7 @@ extern struct task_group root_task_group
 #ifdef CONFIG_RT_MUTEXES
 # define INIT_RT_MUTEXES(tsk)						\
 	.pi_waiters = RB_ROOT,						\
+	.pi_top_task = NULL,						\
 	.pi_waiters_leftmost = NULL,
 #else
 # define INIT_RT_MUTEXES(tsk)
@@ -250,6 +257,7 @@ extern struct task_group root_task_group
 	.cpu_timers	= INIT_CPU_TIMERS(tsk.cpu_timers),		\
 	.pi_lock	= __RAW_SPIN_LOCK_UNLOCKED(tsk.pi_lock),	\
 	.timer_slack_ns = 50000, /* 50 usec default slack */		\
+	INIT_TIMER_LIST							\
 	.pids = {							\
 		[PIDTYPE_PID]  = INIT_PID_LINK(PIDTYPE_PID),		\
 		[PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID),		\
Index: linux-4.9.20-rt16/include/linux/interrupt.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/interrupt.h
+++ linux-4.9.20-rt16/include/linux/interrupt.h
@@ -14,6 +14,7 @@
 #include <linux/hrtimer.h>
 #include <linux/kref.h>
 #include <linux/workqueue.h>
+#include <linux/swork.h>
 
 #include <linux/atomic.h>
 #include <asm/ptrace.h>
@@ -61,6 +62,7 @@
  *                interrupt handler after suspending interrupts. For system
  *                wakeup devices users need to implement wakeup detection in
  *                their interrupt handlers.
+ * IRQF_NO_SOFTIRQ_CALL - Do not process softirqs in the irq thread context (RT)
  */
 #define IRQF_SHARED		0x00000080
 #define IRQF_PROBE_SHARED	0x00000100
@@ -74,6 +76,7 @@
 #define IRQF_NO_THREAD		0x00010000
 #define IRQF_EARLY_RESUME	0x00020000
 #define IRQF_COND_SUSPEND	0x00040000
+#define IRQF_NO_SOFTIRQ_CALL	0x00080000
 
 #define IRQF_TIMER		(__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD)
 
@@ -196,7 +199,7 @@ extern void devm_free_irq(struct device
 #ifdef CONFIG_LOCKDEP
 # define local_irq_enable_in_hardirq()	do { } while (0)
 #else
-# define local_irq_enable_in_hardirq()	local_irq_enable()
+# define local_irq_enable_in_hardirq()	local_irq_enable_nort()
 #endif
 
 extern void disable_irq_nosync(unsigned int irq);
@@ -216,6 +219,7 @@ extern void resume_device_irqs(void);
  * struct irq_affinity_notify - context for notification of IRQ affinity changes
  * @irq:		Interrupt to which notification applies
  * @kref:		Reference count, for internal use
+ * @swork:		Swork item, for internal use
  * @work:		Work item, for internal use
  * @notify:		Function to be called on change.  This will be
  *			called in process context.
@@ -227,7 +231,11 @@ extern void resume_device_irqs(void);
 struct irq_affinity_notify {
 	unsigned int irq;
 	struct kref kref;
+#ifdef CONFIG_PREEMPT_RT_BASE
+	struct swork_event swork;
+#else
 	struct work_struct work;
+#endif
 	void (*notify)(struct irq_affinity_notify *, const cpumask_t *mask);
 	void (*release)(struct kref *ref);
 };
@@ -406,9 +414,13 @@ extern int irq_set_irqchip_state(unsigne
 				 bool state);
 
 #ifdef CONFIG_IRQ_FORCED_THREADING
+# ifndef CONFIG_PREEMPT_RT_BASE
 extern bool force_irqthreads;
+# else
+#  define force_irqthreads	(true)
+# endif
 #else
-#define force_irqthreads	(0)
+#define force_irqthreads	(false)
 #endif
 
 #ifndef __ARCH_SET_SOFTIRQ_PENDING
@@ -465,9 +477,10 @@ struct softirq_action
 	void	(*action)(struct softirq_action *);
 };
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 asmlinkage void do_softirq(void);
 asmlinkage void __do_softirq(void);
-
+static inline void thread_do_softirq(void) { do_softirq(); }
 #ifdef __ARCH_HAS_DO_SOFTIRQ
 void do_softirq_own_stack(void);
 #else
@@ -476,13 +489,25 @@ static inline void do_softirq_own_stack(
 	__do_softirq();
 }
 #endif
+#else
+extern void thread_do_softirq(void);
+#endif
 
 extern void open_softirq(int nr, void (*action)(struct softirq_action *));
 extern void softirq_init(void);
 extern void __raise_softirq_irqoff(unsigned int nr);
+#ifdef CONFIG_PREEMPT_RT_FULL
+extern void __raise_softirq_irqoff_ksoft(unsigned int nr);
+#else
+static inline void __raise_softirq_irqoff_ksoft(unsigned int nr)
+{
+	__raise_softirq_irqoff(nr);
+}
+#endif
 
 extern void raise_softirq_irqoff(unsigned int nr);
 extern void raise_softirq(unsigned int nr);
+extern void softirq_check_pending_idle(void);
 
 DECLARE_PER_CPU(struct task_struct *, ksoftirqd);
 
@@ -504,8 +529,9 @@ static inline struct task_struct *this_c
      to be executed on some cpu at least once after this.
    * If the tasklet is already scheduled, but its execution is still not
      started, it will be executed only once.
-   * If this tasklet is already running on another CPU (or schedule is called
-     from tasklet itself), it is rescheduled for later.
+   * If this tasklet is already running on another CPU, it is rescheduled
+     for later.
+   * Schedule must not be called from the tasklet itself (a lockup occurs)
    * Tasklet is strictly serialized wrt itself, but not
      wrt another tasklets. If client needs some intertask synchronization,
      he makes it with spinlocks.
@@ -530,27 +556,36 @@ struct tasklet_struct name = { NULL, 0,
 enum
 {
 	TASKLET_STATE_SCHED,	/* Tasklet is scheduled for execution */
-	TASKLET_STATE_RUN	/* Tasklet is running (SMP only) */
+	TASKLET_STATE_RUN,	/* Tasklet is running (SMP only) */
+	TASKLET_STATE_PENDING	/* Tasklet is pending */
 };
 
-#ifdef CONFIG_SMP
+#define TASKLET_STATEF_SCHED	(1 << TASKLET_STATE_SCHED)
+#define TASKLET_STATEF_RUN	(1 << TASKLET_STATE_RUN)
+#define TASKLET_STATEF_PENDING	(1 << TASKLET_STATE_PENDING)
+
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL)
 static inline int tasklet_trylock(struct tasklet_struct *t)
 {
 	return !test_and_set_bit(TASKLET_STATE_RUN, &(t)->state);
 }
 
+static inline int tasklet_tryunlock(struct tasklet_struct *t)
+{
+	return cmpxchg(&t->state, TASKLET_STATEF_RUN, 0) == TASKLET_STATEF_RUN;
+}
+
 static inline void tasklet_unlock(struct tasklet_struct *t)
 {
 	smp_mb__before_atomic();
 	clear_bit(TASKLET_STATE_RUN, &(t)->state);
 }
 
-static inline void tasklet_unlock_wait(struct tasklet_struct *t)
-{
-	while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { barrier(); }
-}
+extern void tasklet_unlock_wait(struct tasklet_struct *t);
+
 #else
 #define tasklet_trylock(t) 1
+#define tasklet_tryunlock(t)	1
 #define tasklet_unlock_wait(t) do { } while (0)
 #define tasklet_unlock(t) do { } while (0)
 #endif
@@ -599,12 +634,7 @@ static inline void tasklet_disable(struc
 	smp_mb();
 }
 
-static inline void tasklet_enable(struct tasklet_struct *t)
-{
-	smp_mb__before_atomic();
-	atomic_dec(&t->count);
-}
-
+extern void tasklet_enable(struct tasklet_struct *t);
 extern void tasklet_kill(struct tasklet_struct *t);
 extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu);
 extern void tasklet_init(struct tasklet_struct *t,
@@ -635,6 +665,12 @@ void tasklet_hrtimer_cancel(struct taskl
 	tasklet_kill(&ttimer->tasklet);
 }
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+extern void softirq_early_init(void);
+#else
+static inline void softirq_early_init(void) { }
+#endif
+
 /*
  * Autoprobing for irqs:
  *
Index: linux-4.9.20-rt16/include/linux/irq.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/irq.h
+++ linux-4.9.20-rt16/include/linux/irq.h
@@ -72,6 +72,7 @@ enum irqchip_irq_state;
  * IRQ_IS_POLLED		- Always polled by another interrupt. Exclude
  *				  it from the spurious interrupt detection
  *				  mechanism and from core side polling.
+ * IRQ_NO_SOFTIRQ_CALL		- No softirq processing in the irq thread context (RT)
  * IRQ_DISABLE_UNLAZY		- Disable lazy irq disable
  */
 enum {
@@ -99,13 +100,14 @@ enum {
 	IRQ_PER_CPU_DEVID	= (1 << 17),
 	IRQ_IS_POLLED		= (1 << 18),
 	IRQ_DISABLE_UNLAZY	= (1 << 19),
+	IRQ_NO_SOFTIRQ_CALL	= (1 << 20),
 };
 
 #define IRQF_MODIFY_MASK	\
 	(IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \
 	 IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \
 	 IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID | \
-	 IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY)
+	 IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY | IRQ_NO_SOFTIRQ_CALL)
 
 #define IRQ_NO_BALANCING_MASK	(IRQ_PER_CPU | IRQ_NO_BALANCING)
 
Index: linux-4.9.20-rt16/include/linux/irq_work.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/irq_work.h
+++ linux-4.9.20-rt16/include/linux/irq_work.h
@@ -16,6 +16,7 @@
 #define IRQ_WORK_BUSY		2UL
 #define IRQ_WORK_FLAGS		3UL
 #define IRQ_WORK_LAZY		4UL /* Doesn't want IPI, wait for tick */
+#define IRQ_WORK_HARD_IRQ	8UL /* Run hard IRQ context, even on RT */
 
 struct irq_work {
 	unsigned long flags;
@@ -51,4 +52,10 @@ static inline bool irq_work_needs_cpu(vo
 static inline void irq_work_run(void) { }
 #endif
 
+#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL)
+void irq_work_tick_soft(void);
+#else
+static inline void irq_work_tick_soft(void) { }
+#endif
+
 #endif /* _LINUX_IRQ_WORK_H */
Index: linux-4.9.20-rt16/include/linux/irqdesc.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/irqdesc.h
+++ linux-4.9.20-rt16/include/linux/irqdesc.h
@@ -66,6 +66,7 @@ struct irq_desc {
 	unsigned int		irqs_unhandled;
 	atomic_t		threads_handled;
 	int			threads_handled_last;
+	u64			random_ip;
 	raw_spinlock_t		lock;
 	struct cpumask		*percpu_enabled;
 	const struct cpumask	*percpu_affinity;
Index: linux-4.9.20-rt16/include/linux/irqflags.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/irqflags.h
+++ linux-4.9.20-rt16/include/linux/irqflags.h
@@ -25,8 +25,6 @@
 # define trace_softirqs_enabled(p)	((p)->softirqs_enabled)
 # define trace_hardirq_enter()	do { current->hardirq_context++; } while (0)
 # define trace_hardirq_exit()	do { current->hardirq_context--; } while (0)
-# define lockdep_softirq_enter()	do { current->softirq_context++; } while (0)
-# define lockdep_softirq_exit()	do { current->softirq_context--; } while (0)
 # define INIT_TRACE_IRQFLAGS	.softirqs_enabled = 1,
 #else
 # define trace_hardirqs_on()		do { } while (0)
@@ -39,9 +37,15 @@
 # define trace_softirqs_enabled(p)	0
 # define trace_hardirq_enter()		do { } while (0)
 # define trace_hardirq_exit()		do { } while (0)
+# define INIT_TRACE_IRQFLAGS
+#endif
+
+#if defined(CONFIG_TRACE_IRQFLAGS) && !defined(CONFIG_PREEMPT_RT_FULL)
+# define lockdep_softirq_enter() do { current->softirq_context++; } while (0)
+# define lockdep_softirq_exit()	 do { current->softirq_context--; } while (0)
+#else
 # define lockdep_softirq_enter()	do { } while (0)
 # define lockdep_softirq_exit()		do { } while (0)
-# define INIT_TRACE_IRQFLAGS
 #endif
 
 #if defined(CONFIG_IRQSOFF_TRACER) || \
@@ -148,4 +152,23 @@
 
 #define irqs_disabled_flags(flags) raw_irqs_disabled_flags(flags)
 
+/*
+ * local_irq* variants depending on RT/!RT
+ */
+#ifdef CONFIG_PREEMPT_RT_FULL
+# define local_irq_disable_nort()	do { } while (0)
+# define local_irq_enable_nort()	do { } while (0)
+# define local_irq_save_nort(flags)	local_save_flags(flags)
+# define local_irq_restore_nort(flags)	(void)(flags)
+# define local_irq_disable_rt()		local_irq_disable()
+# define local_irq_enable_rt()		local_irq_enable()
+#else
+# define local_irq_disable_nort()	local_irq_disable()
+# define local_irq_enable_nort()	local_irq_enable()
+# define local_irq_save_nort(flags)	local_irq_save(flags)
+# define local_irq_restore_nort(flags)	local_irq_restore(flags)
+# define local_irq_disable_rt()		do { } while (0)
+# define local_irq_enable_rt()		do { } while (0)
+#endif
+
 #endif
Index: linux-4.9.20-rt16/include/linux/jbd2.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/jbd2.h
+++ linux-4.9.20-rt16/include/linux/jbd2.h
@@ -347,32 +347,56 @@ static inline struct journal_head *bh2jh
 
 static inline void jbd_lock_bh_state(struct buffer_head *bh)
 {
+#ifndef CONFIG_PREEMPT_RT_BASE
 	bit_spin_lock(BH_State, &bh->b_state);
+#else
+	spin_lock(&bh->b_state_lock);
+#endif
 }
 
 static inline int jbd_trylock_bh_state(struct buffer_head *bh)
 {
+#ifndef CONFIG_PREEMPT_RT_BASE
 	return bit_spin_trylock(BH_State, &bh->b_state);
+#else
+	return spin_trylock(&bh->b_state_lock);
+#endif
 }
 
 static inline int jbd_is_locked_bh_state(struct buffer_head *bh)
 {
+#ifndef CONFIG_PREEMPT_RT_BASE
 	return bit_spin_is_locked(BH_State, &bh->b_state);
+#else
+	return spin_is_locked(&bh->b_state_lock);
+#endif
 }
 
 static inline void jbd_unlock_bh_state(struct buffer_head *bh)
 {
+#ifndef CONFIG_PREEMPT_RT_BASE
 	bit_spin_unlock(BH_State, &bh->b_state);
+#else
+	spin_unlock(&bh->b_state_lock);
+#endif
 }
 
 static inline void jbd_lock_bh_journal_head(struct buffer_head *bh)
 {
+#ifndef CONFIG_PREEMPT_RT_BASE
 	bit_spin_lock(BH_JournalHead, &bh->b_state);
+#else
+	spin_lock(&bh->b_journal_head_lock);
+#endif
 }
 
 static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh)
 {
+#ifndef CONFIG_PREEMPT_RT_BASE
 	bit_spin_unlock(BH_JournalHead, &bh->b_state);
+#else
+	spin_unlock(&bh->b_journal_head_lock);
+#endif
 }
 
 #define J_ASSERT(assert)	BUG_ON(!(assert))
Index: linux-4.9.20-rt16/include/linux/kdb.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/kdb.h
+++ linux-4.9.20-rt16/include/linux/kdb.h
@@ -167,6 +167,7 @@ extern __printf(2, 0) int vkdb_printf(en
 extern __printf(1, 2) int kdb_printf(const char *, ...);
 typedef __printf(1, 2) int (*kdb_printf_t)(const char *, ...);
 
+#define in_kdb_printk()	(kdb_trap_printk)
 extern void kdb_init(int level);
 
 /* Access to kdb specific polling devices */
@@ -201,6 +202,7 @@ extern int kdb_register_flags(char *, kd
 extern int kdb_unregister(char *);
 #else /* ! CONFIG_KGDB_KDB */
 static inline __printf(1, 2) int kdb_printf(const char *fmt, ...) { return 0; }
+#define in_kdb_printk() (0)
 static inline void kdb_init(int level) {}
 static inline int kdb_register(char *cmd, kdb_func_t func, char *usage,
 			       char *help, short minlen) { return 0; }
Index: linux-4.9.20-rt16/include/linux/kernel.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/kernel.h
+++ linux-4.9.20-rt16/include/linux/kernel.h
@@ -194,6 +194,9 @@ extern int _cond_resched(void);
  */
 # define might_sleep() \
 	do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0)
+
+# define might_sleep_no_state_check() \
+	do { ___might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0)
 # define sched_annotate_sleep()	(current->task_state_change = 0)
 #else
   static inline void ___might_sleep(const char *file, int line,
@@ -201,6 +204,7 @@ extern int _cond_resched(void);
   static inline void __might_sleep(const char *file, int line,
 				   int preempt_offset) { }
 # define might_sleep() do { might_resched(); } while (0)
+# define might_sleep_no_state_check() do { might_resched(); } while (0)
 # define sched_annotate_sleep() do { } while (0)
 #endif
 
@@ -488,6 +492,7 @@ extern enum system_states {
 	SYSTEM_HALT,
 	SYSTEM_POWER_OFF,
 	SYSTEM_RESTART,
+	SYSTEM_SUSPEND,
 } system_state;
 
 #define TAINT_PROPRIETARY_MODULE	0
Index: linux-4.9.20-rt16/include/linux/list_bl.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/list_bl.h
+++ linux-4.9.20-rt16/include/linux/list_bl.h
@@ -2,6 +2,7 @@
 #define _LINUX_LIST_BL_H
 
 #include <linux/list.h>
+#include <linux/spinlock.h>
 #include <linux/bit_spinlock.h>
 
 /*
@@ -32,13 +33,24 @@
 
 struct hlist_bl_head {
 	struct hlist_bl_node *first;
+#ifdef CONFIG_PREEMPT_RT_BASE
+	raw_spinlock_t lock;
+#endif
 };
 
 struct hlist_bl_node {
 	struct hlist_bl_node *next, **pprev;
 };
-#define INIT_HLIST_BL_HEAD(ptr) \
-	((ptr)->first = NULL)
+
+#ifdef CONFIG_PREEMPT_RT_BASE
+#define INIT_HLIST_BL_HEAD(h)		\
+do {					\
+	(h)->first = NULL;		\
+	raw_spin_lock_init(&(h)->lock);	\
+} while (0)
+#else
+#define INIT_HLIST_BL_HEAD(h) (h)->first = NULL
+#endif
 
 static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h)
 {
@@ -118,12 +130,26 @@ static inline void hlist_bl_del_init(str
 
 static inline void hlist_bl_lock(struct hlist_bl_head *b)
 {
+#ifndef CONFIG_PREEMPT_RT_BASE
 	bit_spin_lock(0, (unsigned long *)b);
+#else
+	raw_spin_lock(&b->lock);
+#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
+	__set_bit(0, (unsigned long *)b);
+#endif
+#endif
 }
 
 static inline void hlist_bl_unlock(struct hlist_bl_head *b)
 {
+#ifndef CONFIG_PREEMPT_RT_BASE
 	__bit_spin_unlock(0, (unsigned long *)b);
+#else
+#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
+	__clear_bit(0, (unsigned long *)b);
+#endif
+	raw_spin_unlock(&b->lock);
+#endif
 }
 
 static inline bool hlist_bl_is_locked(struct hlist_bl_head *b)
Index: linux-4.9.20-rt16/include/linux/locallock.h
===================================================================
--- /dev/null
+++ linux-4.9.20-rt16/include/linux/locallock.h
@@ -0,0 +1,278 @@
+#ifndef _LINUX_LOCALLOCK_H
+#define _LINUX_LOCALLOCK_H
+
+#include <linux/percpu.h>
+#include <linux/spinlock.h>
+
+#ifdef CONFIG_PREEMPT_RT_BASE
+
+#ifdef CONFIG_DEBUG_SPINLOCK
+# define LL_WARN(cond)	WARN_ON(cond)
+#else
+# define LL_WARN(cond)	do { } while (0)
+#endif
+
+/*
+ * per cpu lock based substitute for local_irq_*()
+ */
+struct local_irq_lock {
+	spinlock_t		lock;
+	struct task_struct	*owner;
+	int			nestcnt;
+	unsigned long		flags;
+};
+
+#define DEFINE_LOCAL_IRQ_LOCK(lvar)					\
+	DEFINE_PER_CPU(struct local_irq_lock, lvar) = {			\
+		.lock = __SPIN_LOCK_UNLOCKED((lvar).lock) }
+
+#define DECLARE_LOCAL_IRQ_LOCK(lvar)					\
+	DECLARE_PER_CPU(struct local_irq_lock, lvar)
+
+#define local_irq_lock_init(lvar)					\
+	do {								\
+		int __cpu;						\
+		for_each_possible_cpu(__cpu)				\
+			spin_lock_init(&per_cpu(lvar, __cpu).lock);	\
+	} while (0)
+
+/*
+ * spin_lock|trylock|unlock_local flavour that does not migrate disable
+ * used for __local_lock|trylock|unlock where get_local_var/put_local_var
+ * already takes care of the migrate_disable/enable
+ * for CONFIG_PREEMPT_BASE map to the normal spin_* calls.
+ */
+#ifdef CONFIG_PREEMPT_RT_FULL
+# define spin_lock_local(lock)			rt_spin_lock__no_mg(lock)
+# define spin_trylock_local(lock)		rt_spin_trylock__no_mg(lock)
+# define spin_unlock_local(lock)		rt_spin_unlock__no_mg(lock)
+#else
+# define spin_lock_local(lock)			spin_lock(lock)
+# define spin_trylock_local(lock)		spin_trylock(lock)
+# define spin_unlock_local(lock)		spin_unlock(lock)
+#endif
+
+static inline void __local_lock(struct local_irq_lock *lv)
+{
+	if (lv->owner != current) {
+		spin_lock_local(&lv->lock);
+		LL_WARN(lv->owner);
+		LL_WARN(lv->nestcnt);
+		lv->owner = current;
+	}
+	lv->nestcnt++;
+}
+
+#define local_lock(lvar)					\
+	do { __local_lock(&get_local_var(lvar)); } while (0)
+
+#define local_lock_on(lvar, cpu)				\
+	do { __local_lock(&per_cpu(lvar, cpu)); } while (0)
+
+static inline int __local_trylock(struct local_irq_lock *lv)
+{
+	if (lv->owner != current && spin_trylock_local(&lv->lock)) {
+		LL_WARN(lv->owner);
+		LL_WARN(lv->nestcnt);
+		lv->owner = current;
+		lv->nestcnt = 1;
+		return 1;
+	}
+	return 0;
+}
+
+#define local_trylock(lvar)						\
+	({								\
+		int __locked;						\
+		__locked = __local_trylock(&get_local_var(lvar));	\
+		if (!__locked)						\
+			put_local_var(lvar);				\
+		__locked;						\
+	})
+
+static inline void __local_unlock(struct local_irq_lock *lv)
+{
+	LL_WARN(lv->nestcnt == 0);
+	LL_WARN(lv->owner != current);
+	if (--lv->nestcnt)
+		return;
+
+	lv->owner = NULL;
+	spin_unlock_local(&lv->lock);
+}
+
+#define local_unlock(lvar)					\
+	do {							\
+		__local_unlock(this_cpu_ptr(&lvar));		\
+		put_local_var(lvar);				\
+	} while (0)
+
+#define local_unlock_on(lvar, cpu)                       \
+	do { __local_unlock(&per_cpu(lvar, cpu)); } while (0)
+
+static inline void __local_lock_irq(struct local_irq_lock *lv)
+{
+	spin_lock_irqsave(&lv->lock, lv->flags);
+	LL_WARN(lv->owner);
+	LL_WARN(lv->nestcnt);
+	lv->owner = current;
+	lv->nestcnt = 1;
+}
+
+#define local_lock_irq(lvar)						\
+	do { __local_lock_irq(&get_local_var(lvar)); } while (0)
+
+#define local_lock_irq_on(lvar, cpu)					\
+	do { __local_lock_irq(&per_cpu(lvar, cpu)); } while (0)
+
+static inline void __local_unlock_irq(struct local_irq_lock *lv)
+{
+	LL_WARN(!lv->nestcnt);
+	LL_WARN(lv->owner != current);
+	lv->owner = NULL;
+	lv->nestcnt = 0;
+	spin_unlock_irq(&lv->lock);
+}
+
+#define local_unlock_irq(lvar)						\
+	do {								\
+		__local_unlock_irq(this_cpu_ptr(&lvar));		\
+		put_local_var(lvar);					\
+	} while (0)
+
+#define local_unlock_irq_on(lvar, cpu)					\
+	do {								\
+		__local_unlock_irq(&per_cpu(lvar, cpu));		\
+	} while (0)
+
+static inline int __local_lock_irqsave(struct local_irq_lock *lv)
+{
+	if (lv->owner != current) {
+		__local_lock_irq(lv);
+		return 0;
+	} else {
+		lv->nestcnt++;
+		return 1;
+	}
+}
+
+#define local_lock_irqsave(lvar, _flags)				\
+	do {								\
+		if (__local_lock_irqsave(&get_local_var(lvar)))		\
+			put_local_var(lvar);				\
+		_flags = __this_cpu_read(lvar.flags);			\
+	} while (0)
+
+#define local_lock_irqsave_on(lvar, _flags, cpu)			\
+	do {								\
+		__local_lock_irqsave(&per_cpu(lvar, cpu));		\
+		_flags = per_cpu(lvar, cpu).flags;			\
+	} while (0)
+
+static inline int __local_unlock_irqrestore(struct local_irq_lock *lv,
+					    unsigned long flags)
+{
+	LL_WARN(!lv->nestcnt);
+	LL_WARN(lv->owner != current);
+	if (--lv->nestcnt)
+		return 0;
+
+	lv->owner = NULL;
+	spin_unlock_irqrestore(&lv->lock, lv->flags);
+	return 1;
+}
+
+#define local_unlock_irqrestore(lvar, flags)				\
+	do {								\
+		if (__local_unlock_irqrestore(this_cpu_ptr(&lvar), flags)) \
+			put_local_var(lvar);				\
+	} while (0)
+
+#define local_unlock_irqrestore_on(lvar, flags, cpu)			\
+	do {								\
+		__local_unlock_irqrestore(&per_cpu(lvar, cpu), flags);	\
+	} while (0)
+
+#define local_spin_trylock_irq(lvar, lock)				\
+	({								\
+		int __locked;						\
+		local_lock_irq(lvar);					\
+		__locked = spin_trylock(lock);				\
+		if (!__locked)						\
+			local_unlock_irq(lvar);				\
+		__locked;						\
+	})
+
+#define local_spin_lock_irq(lvar, lock)					\
+	do {								\
+		local_lock_irq(lvar);					\
+		spin_lock(lock);					\
+	} while (0)
+
+#define local_spin_unlock_irq(lvar, lock)				\
+	do {								\
+		spin_unlock(lock);					\
+		local_unlock_irq(lvar);					\
+	} while (0)
+
+#define local_spin_lock_irqsave(lvar, lock, flags)			\
+	do {								\
+		local_lock_irqsave(lvar, flags);			\
+		spin_lock(lock);					\
+	} while (0)
+
+#define local_spin_unlock_irqrestore(lvar, lock, flags)			\
+	do {								\
+		spin_unlock(lock);					\
+		local_unlock_irqrestore(lvar, flags);			\
+	} while (0)
+
+#define get_locked_var(lvar, var)					\
+	(*({								\
+		local_lock(lvar);					\
+		this_cpu_ptr(&var);					\
+	}))
+
+#define put_locked_var(lvar, var)	local_unlock(lvar);
+
+#define local_lock_cpu(lvar)						\
+	({								\
+		local_lock(lvar);					\
+		smp_processor_id();					\
+	})
+
+#define local_unlock_cpu(lvar)			local_unlock(lvar)
+
+#else /* PREEMPT_RT_BASE */
+
+#define DEFINE_LOCAL_IRQ_LOCK(lvar)		__typeof__(const int) lvar
+#define DECLARE_LOCAL_IRQ_LOCK(lvar)		extern __typeof__(const int) lvar
+
+static inline void local_irq_lock_init(int lvar) { }
+
+#define local_lock(lvar)			preempt_disable()
+#define local_unlock(lvar)			preempt_enable()
+#define local_lock_irq(lvar)			local_irq_disable()
+#define local_lock_irq_on(lvar, cpu)		local_irq_disable()
+#define local_unlock_irq(lvar)			local_irq_enable()
+#define local_unlock_irq_on(lvar, cpu)		local_irq_enable()
+#define local_lock_irqsave(lvar, flags)		local_irq_save(flags)
+#define local_unlock_irqrestore(lvar, flags)	local_irq_restore(flags)
+
+#define local_spin_trylock_irq(lvar, lock)	spin_trylock_irq(lock)
+#define local_spin_lock_irq(lvar, lock)		spin_lock_irq(lock)
+#define local_spin_unlock_irq(lvar, lock)	spin_unlock_irq(lock)
+#define local_spin_lock_irqsave(lvar, lock, flags)	\
+	spin_lock_irqsave(lock, flags)
+#define local_spin_unlock_irqrestore(lvar, lock, flags)	\
+	spin_unlock_irqrestore(lock, flags)
+
+#define get_locked_var(lvar, var)		get_cpu_var(var)
+#define put_locked_var(lvar, var)		put_cpu_var(var)
+
+#define local_lock_cpu(lvar)			get_cpu()
+#define local_unlock_cpu(lvar)			put_cpu()
+
+#endif
+
+#endif
Index: linux-4.9.20-rt16/include/linux/mm_types.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/mm_types.h
+++ linux-4.9.20-rt16/include/linux/mm_types.h
@@ -11,6 +11,7 @@
 #include <linux/completion.h>
 #include <linux/cpumask.h>
 #include <linux/uprobes.h>
+#include <linux/rcupdate.h>
 #include <linux/page-flags-layout.h>
 #include <linux/workqueue.h>
 #include <asm/page.h>
@@ -513,6 +514,9 @@ struct mm_struct {
 	bool tlb_flush_batched;
 #endif
 	struct uprobes_state uprobes_state;
+#ifdef CONFIG_PREEMPT_RT_BASE
+	struct rcu_head delayed_drop;
+#endif
 #ifdef CONFIG_X86_INTEL_MPX
 	/* address of the bounds directory */
 	void __user *bd_addr;
Index: linux-4.9.20-rt16/include/linux/module.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/module.h
+++ linux-4.9.20-rt16/include/linux/module.h
@@ -496,6 +496,7 @@ static inline int module_is_live(struct
 struct module *__module_text_address(unsigned long addr);
 struct module *__module_address(unsigned long addr);
 bool is_module_address(unsigned long addr);
+bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr);
 bool is_module_percpu_address(unsigned long addr);
 bool is_module_text_address(unsigned long addr);
 
@@ -662,6 +663,11 @@ static inline bool is_module_percpu_addr
 {
 	return false;
 }
+
+static inline bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr)
+{
+	return false;
+}
 
 static inline bool is_module_text_address(unsigned long addr)
 {
Index: linux-4.9.20-rt16/include/linux/mutex.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/mutex.h
+++ linux-4.9.20-rt16/include/linux/mutex.h
@@ -19,6 +19,17 @@
 #include <asm/processor.h>
 #include <linux/osq_lock.h>
 
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \
+	, .dep_map = { .name = #lockname }
+#else
+# define __DEP_MAP_MUTEX_INITIALIZER(lockname)
+#endif
+
+#ifdef CONFIG_PREEMPT_RT_FULL
+# include <linux/mutex_rt.h>
+#else
+
 /*
  * Simple, straightforward mutexes with strict semantics:
  *
@@ -99,13 +110,6 @@ do {							\
 static inline void mutex_destroy(struct mutex *lock) {}
 #endif
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \
-		, .dep_map = { .name = #lockname }
-#else
-# define __DEP_MAP_MUTEX_INITIALIZER(lockname)
-#endif
-
 #define __MUTEX_INITIALIZER(lockname) \
 		{ .count = ATOMIC_INIT(1) \
 		, .wait_lock = __SPIN_LOCK_UNLOCKED(lockname.wait_lock) \
@@ -173,6 +177,8 @@ extern int __must_check mutex_lock_killa
 extern int mutex_trylock(struct mutex *lock);
 extern void mutex_unlock(struct mutex *lock);
 
+#endif /* !PREEMPT_RT_FULL */
+
 extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
 
 #endif /* __LINUX_MUTEX_H */
Index: linux-4.9.20-rt16/include/linux/mutex_rt.h
===================================================================
--- /dev/null
+++ linux-4.9.20-rt16/include/linux/mutex_rt.h
@@ -0,0 +1,89 @@
+#ifndef __LINUX_MUTEX_RT_H
+#define __LINUX_MUTEX_RT_H
+
+#ifndef __LINUX_MUTEX_H
+#error "Please include mutex.h"
+#endif
+
+#include <linux/rtmutex.h>
+
+/* FIXME: Just for __lockfunc */
+#include <linux/spinlock.h>
+
+struct mutex {
+	struct rt_mutex		lock;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	dep_map;
+#endif
+};
+
+#define __MUTEX_INITIALIZER(mutexname)					\
+	{								\
+		.lock = __RT_MUTEX_INITIALIZER(mutexname.lock)		\
+		__DEP_MAP_MUTEX_INITIALIZER(mutexname)			\
+	}
+
+#define DEFINE_MUTEX(mutexname)						\
+	struct mutex mutexname = __MUTEX_INITIALIZER(mutexname)
+
+extern void __mutex_do_init(struct mutex *lock, const char *name, struct lock_class_key *key);
+extern void __lockfunc _mutex_lock(struct mutex *lock);
+extern int __lockfunc _mutex_lock_interruptible(struct mutex *lock);
+extern int __lockfunc _mutex_lock_killable(struct mutex *lock);
+extern void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass);
+extern void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock);
+extern int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass);
+extern int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass);
+extern int __lockfunc _mutex_trylock(struct mutex *lock);
+extern void __lockfunc _mutex_unlock(struct mutex *lock);
+
+#define mutex_is_locked(l)		rt_mutex_is_locked(&(l)->lock)
+#define mutex_lock(l)			_mutex_lock(l)
+#define mutex_lock_interruptible(l)	_mutex_lock_interruptible(l)
+#define mutex_lock_killable(l)		_mutex_lock_killable(l)
+#define mutex_trylock(l)		_mutex_trylock(l)
+#define mutex_unlock(l)			_mutex_unlock(l)
+
+#ifdef CONFIG_DEBUG_MUTEXES
+#define mutex_destroy(l)		rt_mutex_destroy(&(l)->lock)
+#else
+static inline void mutex_destroy(struct mutex *lock) {}
+#endif
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define mutex_lock_nested(l, s)	_mutex_lock_nested(l, s)
+# define mutex_lock_interruptible_nested(l, s) \
+					_mutex_lock_interruptible_nested(l, s)
+# define mutex_lock_killable_nested(l, s) \
+					_mutex_lock_killable_nested(l, s)
+
+# define mutex_lock_nest_lock(lock, nest_lock)				\
+do {									\
+	typecheck(struct lockdep_map *, &(nest_lock)->dep_map);		\
+	_mutex_lock_nest_lock(lock, &(nest_lock)->dep_map);		\
+} while (0)
+
+#else
+# define mutex_lock_nested(l, s)	_mutex_lock(l)
+# define mutex_lock_interruptible_nested(l, s) \
+					_mutex_lock_interruptible(l)
+# define mutex_lock_killable_nested(l, s) \
+					_mutex_lock_killable(l)
+# define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock)
+#endif
+
+# define mutex_init(mutex)				\
+do {							\
+	static struct lock_class_key __key;		\
+							\
+	rt_mutex_init(&(mutex)->lock);			\
+	__mutex_do_init((mutex), #mutex, &__key);	\
+} while (0)
+
+# define __mutex_init(mutex, name, key)			\
+do {							\
+	rt_mutex_init(&(mutex)->lock);			\
+	__mutex_do_init((mutex), name, key);		\
+} while (0)
+
+#endif
Index: linux-4.9.20-rt16/include/linux/netdevice.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/netdevice.h
+++ linux-4.9.20-rt16/include/linux/netdevice.h
@@ -396,7 +396,19 @@ typedef enum rx_handler_result rx_handle
 typedef rx_handler_result_t rx_handler_func_t(struct sk_buff **pskb);
 
 void __napi_schedule(struct napi_struct *n);
+
+/*
+ * When PREEMPT_RT_FULL is defined, all device interrupt handlers
+ * run as threads, and they can also be preempted (without PREEMPT_RT
+ * interrupt threads can not be preempted). Which means that calling
+ * __napi_schedule_irqoff() from an interrupt handler can be preempted
+ * and can corrupt the napi->poll_list.
+ */
+#ifdef CONFIG_PREEMPT_RT_FULL
+#define __napi_schedule_irqoff(n) __napi_schedule(n)
+#else
 void __napi_schedule_irqoff(struct napi_struct *n);
+#endif
 
 static inline bool napi_disable_pending(struct napi_struct *n)
 {
@@ -2464,14 +2476,53 @@ void netdev_freemem(struct net_device *d
 void synchronize_net(void);
 int init_dummy_netdev(struct net_device *dev);
 
-DECLARE_PER_CPU(int, xmit_recursion);
 #define XMIT_RECURSION_LIMIT	10
+#ifdef CONFIG_PREEMPT_RT_FULL
+static inline int dev_recursion_level(void)
+{
+	return current->xmit_recursion;
+}
+
+static inline int xmit_rec_read(void)
+{
+	return current->xmit_recursion;
+}
+
+static inline void xmit_rec_inc(void)
+{
+	current->xmit_recursion++;
+}
+
+static inline void xmit_rec_dec(void)
+{
+	current->xmit_recursion--;
+}
+
+#else
+
+DECLARE_PER_CPU(int, xmit_recursion);
 
 static inline int dev_recursion_level(void)
 {
 	return this_cpu_read(xmit_recursion);
 }
 
+static inline int xmit_rec_read(void)
+{
+	return __this_cpu_read(xmit_recursion);
+}
+
+static inline void xmit_rec_inc(void)
+{
+	__this_cpu_inc(xmit_recursion);
+}
+
+static inline void xmit_rec_dec(void)
+{
+	__this_cpu_dec(xmit_recursion);
+}
+#endif
+
 struct net_device *dev_get_by_index(struct net *net, int ifindex);
 struct net_device *__dev_get_by_index(struct net *net, int ifindex);
 struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex);
@@ -2856,6 +2907,7 @@ struct softnet_data {
 	unsigned int		dropped;
 	struct sk_buff_head	input_pkt_queue;
 	struct napi_struct	backlog;
+	struct sk_buff_head	tofree_queue;
 
 };
 
Index: linux-4.9.20-rt16/include/linux/netfilter/x_tables.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/netfilter/x_tables.h
+++ linux-4.9.20-rt16/include/linux/netfilter/x_tables.h
@@ -4,6 +4,7 @@
 
 #include <linux/netdevice.h>
 #include <linux/static_key.h>
+#include <linux/locallock.h>
 #include <uapi/linux/netfilter/x_tables.h>
 
 /* Test a struct->invflags and a boolean for inequality */
@@ -300,6 +301,8 @@ void xt_free_table_info(struct xt_table_
  */
 DECLARE_PER_CPU(seqcount_t, xt_recseq);
 
+DECLARE_LOCAL_IRQ_LOCK(xt_write_lock);
+
 /* xt_tee_enabled - true if x_tables needs to handle reentrancy
  *
  * Enabled if current ip(6)tables ruleset has at least one -j TEE rule.
@@ -320,6 +323,9 @@ static inline unsigned int xt_write_recs
 {
 	unsigned int addend;
 
+	/* RT protection */
+	local_lock(xt_write_lock);
+
 	/*
 	 * Low order bit of sequence is set if we already
 	 * called xt_write_recseq_begin().
@@ -350,6 +356,7 @@ static inline void xt_write_recseq_end(u
 	/* this is kind of a write_seqcount_end(), but addend is 0 or 1 */
 	smp_wmb();
 	__this_cpu_add(xt_recseq.sequence, addend);
+	local_unlock(xt_write_lock);
 }
 
 /*
Index: linux-4.9.20-rt16/include/linux/nfs_fs.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/nfs_fs.h
+++ linux-4.9.20-rt16/include/linux/nfs_fs.h
@@ -165,7 +165,11 @@ struct nfs_inode {
 
 	/* Readers: in-flight sillydelete RPC calls */
 	/* Writers: rmdir */
+#ifdef CONFIG_PREEMPT_RT_BASE
+	struct semaphore	rmdir_sem;
+#else
 	struct rw_semaphore	rmdir_sem;
+#endif
 
 #if IS_ENABLED(CONFIG_NFS_V4)
 	struct nfs4_cached_acl	*nfs4_acl;
Index: linux-4.9.20-rt16/include/linux/nfs_xdr.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/nfs_xdr.h
+++ linux-4.9.20-rt16/include/linux/nfs_xdr.h
@@ -1490,7 +1490,7 @@ struct nfs_unlinkdata {
 	struct nfs_removeargs args;
 	struct nfs_removeres res;
 	struct dentry *dentry;
-	wait_queue_head_t wq;
+	struct swait_queue_head wq;
 	struct rpc_cred	*cred;
 	struct nfs_fattr dir_attr;
 	long timeout;
Index: linux-4.9.20-rt16/include/linux/notifier.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/notifier.h
+++ linux-4.9.20-rt16/include/linux/notifier.h
@@ -6,7 +6,7 @@
  *
  *				Alan Cox <Alan.Cox@linux.org>
  */
- 
+
 #ifndef _LINUX_NOTIFIER_H
 #define _LINUX_NOTIFIER_H
 #include <linux/errno.h>
@@ -42,9 +42,7 @@
  * in srcu_notifier_call_chain(): no cache bounces and no memory barriers.
  * As compensation, srcu_notifier_chain_unregister() is rather expensive.
  * SRCU notifier chains should be used when the chain will be called very
- * often but notifier_blocks will seldom be removed.  Also, SRCU notifier
- * chains are slightly more difficult to use because they require special
- * runtime initialization.
+ * often but notifier_blocks will seldom be removed.
  */
 
 struct notifier_block;
@@ -90,7 +88,7 @@ struct srcu_notifier_head {
 		(name)->head = NULL;		\
 	} while (0)
 
-/* srcu_notifier_heads must be initialized and cleaned up dynamically */
+/* srcu_notifier_heads must be cleaned up dynamically */
 extern void srcu_init_notifier_head(struct srcu_notifier_head *nh);
 #define srcu_cleanup_notifier_head(name)	\
 		cleanup_srcu_struct(&(name)->srcu);
@@ -103,7 +101,13 @@ extern void srcu_init_notifier_head(stru
 		.head = NULL }
 #define RAW_NOTIFIER_INIT(name)	{				\
 		.head = NULL }
-/* srcu_notifier_heads cannot be initialized statically */
+
+#define SRCU_NOTIFIER_INIT(name, pcpu)				\
+	{							\
+		.mutex = __MUTEX_INITIALIZER(name.mutex),	\
+		.head = NULL,					\
+		.srcu = __SRCU_STRUCT_INIT(name.srcu, pcpu),	\
+	}
 
 #define ATOMIC_NOTIFIER_HEAD(name)				\
 	struct atomic_notifier_head name =			\
@@ -115,6 +119,18 @@ extern void srcu_init_notifier_head(stru
 	struct raw_notifier_head name =				\
 		RAW_NOTIFIER_INIT(name)
 
+#define _SRCU_NOTIFIER_HEAD(name, mod)				\
+	static DEFINE_PER_CPU(struct srcu_struct_array,		\
+			name##_head_srcu_array);		\
+	mod struct srcu_notifier_head name =			\
+			SRCU_NOTIFIER_INIT(name, name##_head_srcu_array)
+
+#define SRCU_NOTIFIER_HEAD(name)				\
+	_SRCU_NOTIFIER_HEAD(name, )
+
+#define SRCU_NOTIFIER_HEAD_STATIC(name)				\
+	_SRCU_NOTIFIER_HEAD(name, static)
+
 #ifdef __KERNEL__
 
 extern int atomic_notifier_chain_register(struct atomic_notifier_head *nh,
@@ -184,12 +200,12 @@ static inline int notifier_to_errno(int
 
 /*
  *	Declared notifiers so far. I can imagine quite a few more chains
- *	over time (eg laptop power reset chains, reboot chain (to clean 
+ *	over time (eg laptop power reset chains, reboot chain (to clean
  *	device units up), device [un]mount chain, module load/unload chain,
- *	low memory chain, screenblank chain (for plug in modular screenblankers) 
+ *	low memory chain, screenblank chain (for plug in modular screenblankers)
  *	VC switch chains (for loadable kernel svgalib VC switch helpers) etc...
  */
- 
+
 /* CPU notfiers are defined in include/linux/cpu.h. */
 
 /* netdevice notifiers are defined in include/linux/netdevice.h */
Index: linux-4.9.20-rt16/include/linux/percpu-rwsem.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/percpu-rwsem.h
+++ linux-4.9.20-rt16/include/linux/percpu-rwsem.h
@@ -4,7 +4,7 @@
 #include <linux/atomic.h>
 #include <linux/rwsem.h>
 #include <linux/percpu.h>
-#include <linux/wait.h>
+#include <linux/swait.h>
 #include <linux/rcu_sync.h>
 #include <linux/lockdep.h>
 
@@ -12,7 +12,7 @@ struct percpu_rw_semaphore {
 	struct rcu_sync		rss;
 	unsigned int __percpu	*read_count;
 	struct rw_semaphore	rw_sem;
-	wait_queue_head_t	writer;
+	struct swait_queue_head	writer;
 	int			readers_block;
 };
 
@@ -22,13 +22,13 @@ static struct percpu_rw_semaphore name =
 	.rss = __RCU_SYNC_INITIALIZER(name.rss, RCU_SCHED_SYNC),	\
 	.read_count = &__percpu_rwsem_rc_##name,			\
 	.rw_sem = __RWSEM_INITIALIZER(name.rw_sem),			\
-	.writer = __WAIT_QUEUE_HEAD_INITIALIZER(name.writer),		\
+	.writer = __SWAIT_QUEUE_HEAD_INITIALIZER(name.writer),		\
 }
 
 extern int __percpu_down_read(struct percpu_rw_semaphore *, int);
 extern void __percpu_up_read(struct percpu_rw_semaphore *);
 
-static inline void percpu_down_read_preempt_disable(struct percpu_rw_semaphore *sem)
+static inline void percpu_down_read(struct percpu_rw_semaphore *sem)
 {
 	might_sleep();
 
@@ -46,16 +46,10 @@ static inline void percpu_down_read_pree
 	__this_cpu_inc(*sem->read_count);
 	if (unlikely(!rcu_sync_is_idle(&sem->rss)))
 		__percpu_down_read(sem, false); /* Unconditional memory barrier */
-	barrier();
 	/*
-	 * The barrier() prevents the compiler from
+	 * The preempt_enable() prevents the compiler from
 	 * bleeding the critical section out.
 	 */
-}
-
-static inline void percpu_down_read(struct percpu_rw_semaphore *sem)
-{
-	percpu_down_read_preempt_disable(sem);
 	preempt_enable();
 }
 
@@ -82,13 +76,9 @@ static inline int percpu_down_read_trylo
 	return ret;
 }
 
-static inline void percpu_up_read_preempt_enable(struct percpu_rw_semaphore *sem)
+static inline void percpu_up_read(struct percpu_rw_semaphore *sem)
 {
-	/*
-	 * The barrier() prevents the compiler from
-	 * bleeding the critical section out.
-	 */
-	barrier();
+	preempt_disable();
 	/*
 	 * Same as in percpu_down_read().
 	 */
@@ -101,12 +91,6 @@ static inline void percpu_up_read_preemp
 	rwsem_release(&sem->rw_sem.dep_map, 1, _RET_IP_);
 }
 
-static inline void percpu_up_read(struct percpu_rw_semaphore *sem)
-{
-	preempt_disable();
-	percpu_up_read_preempt_enable(sem);
-}
-
 extern void percpu_down_write(struct percpu_rw_semaphore *);
 extern void percpu_up_write(struct percpu_rw_semaphore *);
 
Index: linux-4.9.20-rt16/include/linux/percpu.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/percpu.h
+++ linux-4.9.20-rt16/include/linux/percpu.h
@@ -18,6 +18,35 @@
 #define PERCPU_MODULE_RESERVE		0
 #endif
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+
+#define get_local_var(var) (*({	\
+	migrate_disable();	\
+	this_cpu_ptr(&var);	}))
+
+#define put_local_var(var) do {	\
+	(void)&(var);		\
+	migrate_enable();	\
+} while (0)
+
+# define get_local_ptr(var) ({	\
+	migrate_disable();	\
+	this_cpu_ptr(var);	})
+
+# define put_local_ptr(var) do {	\
+	(void)(var);			\
+	migrate_enable();		\
+} while (0)
+
+#else
+
+#define get_local_var(var)	get_cpu_var(var)
+#define put_local_var(var)	put_cpu_var(var)
+#define get_local_ptr(var)	get_cpu_ptr(var)
+#define put_local_ptr(var)	put_cpu_ptr(var)
+
+#endif
+
 /* minimum unit size, also is the maximum supported allocation size */
 #define PCPU_MIN_UNIT_SIZE		PFN_ALIGN(32 << 10)
 
@@ -110,6 +139,7 @@ extern int __init pcpu_page_first_chunk(
 #endif
 
 extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align);
+extern bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr);
 extern bool is_kernel_percpu_address(unsigned long addr);
 
 #if !defined(CONFIG_SMP) || !defined(CONFIG_HAVE_SETUP_PER_CPU_AREA)
Index: linux-4.9.20-rt16/include/linux/pid.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/pid.h
+++ linux-4.9.20-rt16/include/linux/pid.h
@@ -2,6 +2,7 @@
 #define _LINUX_PID_H
 
 #include <linux/rcupdate.h>
+#include <linux/atomic.h>
 
 enum pid_type
 {
Index: linux-4.9.20-rt16/include/linux/preempt.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/preempt.h
+++ linux-4.9.20-rt16/include/linux/preempt.h
@@ -50,7 +50,11 @@
 #define HARDIRQ_OFFSET	(1UL << HARDIRQ_SHIFT)
 #define NMI_OFFSET	(1UL << NMI_SHIFT)
 
-#define SOFTIRQ_DISABLE_OFFSET	(2 * SOFTIRQ_OFFSET)
+#ifndef CONFIG_PREEMPT_RT_FULL
+# define SOFTIRQ_DISABLE_OFFSET		(2 * SOFTIRQ_OFFSET)
+#else
+# define SOFTIRQ_DISABLE_OFFSET		(0)
+#endif
 
 /* We use the MSB mostly because its available */
 #define PREEMPT_NEED_RESCHED	0x80000000
@@ -59,9 +63,15 @@
 #include <asm/preempt.h>
 
 #define hardirq_count()	(preempt_count() & HARDIRQ_MASK)
-#define softirq_count()	(preempt_count() & SOFTIRQ_MASK)
 #define irq_count()	(preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \
 				 | NMI_MASK))
+#ifndef CONFIG_PREEMPT_RT_FULL
+# define softirq_count()	(preempt_count() & SOFTIRQ_MASK)
+# define in_serving_softirq()	(softirq_count() & SOFTIRQ_OFFSET)
+#else
+# define softirq_count()	(0UL)
+extern int in_serving_softirq(void);
+#endif
 
 /*
  * Are we doing bottom half or hardware interrupt processing?
@@ -72,7 +82,6 @@
 #define in_irq()		(hardirq_count())
 #define in_softirq()		(softirq_count())
 #define in_interrupt()		(irq_count())
-#define in_serving_softirq()	(softirq_count() & SOFTIRQ_OFFSET)
 
 /*
  * Are we in NMI context?
@@ -91,7 +100,11 @@
 /*
  * The preempt_count offset after spin_lock()
  */
+#if !defined(CONFIG_PREEMPT_RT_FULL)
 #define PREEMPT_LOCK_OFFSET	PREEMPT_DISABLE_OFFSET
+#else
+#define PREEMPT_LOCK_OFFSET	0
+#endif
 
 /*
  * The preempt_count offset needed for things like:
@@ -140,6 +153,20 @@ extern void preempt_count_sub(int val);
 #define preempt_count_inc() preempt_count_add(1)
 #define preempt_count_dec() preempt_count_sub(1)
 
+#ifdef CONFIG_PREEMPT_LAZY
+#define add_preempt_lazy_count(val)	do { preempt_lazy_count() += (val); } while (0)
+#define sub_preempt_lazy_count(val)	do { preempt_lazy_count() -= (val); } while (0)
+#define inc_preempt_lazy_count()	add_preempt_lazy_count(1)
+#define dec_preempt_lazy_count()	sub_preempt_lazy_count(1)
+#define preempt_lazy_count()		(current_thread_info()->preempt_lazy_count)
+#else
+#define add_preempt_lazy_count(val)	do { } while (0)
+#define sub_preempt_lazy_count(val)	do { } while (0)
+#define inc_preempt_lazy_count()	do { } while (0)
+#define dec_preempt_lazy_count()	do { } while (0)
+#define preempt_lazy_count()		(0)
+#endif
+
 #ifdef CONFIG_PREEMPT_COUNT
 
 #define preempt_disable() \
@@ -148,13 +175,25 @@ do { \
 	barrier(); \
 } while (0)
 
+#define preempt_lazy_disable() \
+do { \
+	inc_preempt_lazy_count(); \
+	barrier(); \
+} while (0)
+
 #define sched_preempt_enable_no_resched() \
 do { \
 	barrier(); \
 	preempt_count_dec(); \
 } while (0)
 
-#define preempt_enable_no_resched() sched_preempt_enable_no_resched()
+#ifdef CONFIG_PREEMPT_RT_BASE
+# define preempt_enable_no_resched() sched_preempt_enable_no_resched()
+# define preempt_check_resched_rt() preempt_check_resched()
+#else
+# define preempt_enable_no_resched() preempt_enable()
+# define preempt_check_resched_rt() barrier();
+#endif
 
 #define preemptible()	(preempt_count() == 0 && !irqs_disabled())
 
@@ -179,6 +218,13 @@ do { \
 		__preempt_schedule(); \
 } while (0)
 
+#define preempt_lazy_enable() \
+do { \
+	dec_preempt_lazy_count(); \
+	barrier(); \
+	preempt_check_resched(); \
+} while (0)
+
 #else /* !CONFIG_PREEMPT */
 #define preempt_enable() \
 do { \
@@ -224,6 +270,7 @@ do { \
 #define preempt_disable_notrace()		barrier()
 #define preempt_enable_no_resched_notrace()	barrier()
 #define preempt_enable_notrace()		barrier()
+#define preempt_check_resched_rt()		barrier()
 #define preemptible()				0
 
 #endif /* CONFIG_PREEMPT_COUNT */
@@ -244,10 +291,31 @@ do { \
 } while (0)
 #define preempt_fold_need_resched() \
 do { \
-	if (tif_need_resched()) \
+	if (tif_need_resched_now()) \
 		set_preempt_need_resched(); \
 } while (0)
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+# define preempt_disable_rt()		preempt_disable()
+# define preempt_enable_rt()		preempt_enable()
+# define preempt_disable_nort()		barrier()
+# define preempt_enable_nort()		barrier()
+# ifdef CONFIG_SMP
+   extern void migrate_disable(void);
+   extern void migrate_enable(void);
+# else /* CONFIG_SMP */
+#  define migrate_disable()		barrier()
+#  define migrate_enable()		barrier()
+# endif /* CONFIG_SMP */
+#else
+# define preempt_disable_rt()		barrier()
+# define preempt_enable_rt()		barrier()
+# define preempt_disable_nort()		preempt_disable()
+# define preempt_enable_nort()		preempt_enable()
+# define migrate_disable()		preempt_disable()
+# define migrate_enable()		preempt_enable()
+#endif
+
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 
 struct preempt_notifier;
Index: linux-4.9.20-rt16/include/linux/printk.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/printk.h
+++ linux-4.9.20-rt16/include/linux/printk.h
@@ -126,9 +126,11 @@ struct va_format {
 #ifdef CONFIG_EARLY_PRINTK
 extern asmlinkage __printf(1, 2)
 void early_printk(const char *fmt, ...);
+extern void printk_kill(void);
 #else
 static inline __printf(1, 2) __cold
 void early_printk(const char *s, ...) { }
+static inline void printk_kill(void) { }
 #endif
 
 #ifdef CONFIG_PRINTK_NMI
Index: linux-4.9.20-rt16/include/linux/radix-tree.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/radix-tree.h
+++ linux-4.9.20-rt16/include/linux/radix-tree.h
@@ -292,6 +292,8 @@ unsigned int radix_tree_gang_lookup_slot
 int radix_tree_preload(gfp_t gfp_mask);
 int radix_tree_maybe_preload(gfp_t gfp_mask);
 int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order);
+void radix_tree_preload_end(void);
+
 void radix_tree_init(void);
 void *radix_tree_tag_set(struct radix_tree_root *root,
 			unsigned long index, unsigned int tag);
@@ -314,11 +316,6 @@ unsigned long radix_tree_range_tag_if_ta
 int radix_tree_tagged(struct radix_tree_root *root, unsigned int tag);
 unsigned long radix_tree_locate_item(struct radix_tree_root *root, void *item);
 
-static inline void radix_tree_preload_end(void)
-{
-	preempt_enable();
-}
-
 /**
  * struct radix_tree_iter - radix tree iterator state
  *
Index: linux-4.9.20-rt16/include/linux/random.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/random.h
+++ linux-4.9.20-rt16/include/linux/random.h
@@ -31,7 +31,7 @@ static inline void add_latent_entropy(vo
 
 extern void add_input_randomness(unsigned int type, unsigned int code,
 				 unsigned int value) __latent_entropy;
-extern void add_interrupt_randomness(int irq, int irq_flags) __latent_entropy;
+extern void add_interrupt_randomness(int irq, int irq_flags, __u64 ip) __latent_entropy;
 
 extern void get_random_bytes(void *buf, int nbytes);
 extern int add_random_ready_callback(struct random_ready_callback *rdy);
Index: linux-4.9.20-rt16/include/linux/rbtree.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/rbtree.h
+++ linux-4.9.20-rt16/include/linux/rbtree.h
@@ -31,7 +31,7 @@
 
 #include <linux/kernel.h>
 #include <linux/stddef.h>
-#include <linux/rcupdate.h>
+#include <linux/rcu_assign_pointer.h>
 
 struct rb_node {
 	unsigned long  __rb_parent_color;
Index: linux-4.9.20-rt16/include/linux/rbtree_augmented.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/rbtree_augmented.h
+++ linux-4.9.20-rt16/include/linux/rbtree_augmented.h
@@ -26,6 +26,7 @@
 
 #include <linux/compiler.h>
 #include <linux/rbtree.h>
+#include <linux/rcupdate.h>
 
 /*
  * Please note - only struct rb_augment_callbacks and the prototypes for
Index: linux-4.9.20-rt16/include/linux/rcu_assign_pointer.h
===================================================================
--- /dev/null
+++ linux-4.9.20-rt16/include/linux/rcu_assign_pointer.h
@@ -0,0 +1,54 @@
+#ifndef __LINUX_RCU_ASSIGN_POINTER_H__
+#define __LINUX_RCU_ASSIGN_POINTER_H__
+#include <linux/compiler.h>
+#include <asm/barrier.h>
+
+/**
+ * RCU_INITIALIZER() - statically initialize an RCU-protected global variable
+ * @v: The value to statically initialize with.
+ */
+#define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v)
+
+/**
+ * rcu_assign_pointer() - assign to RCU-protected pointer
+ * @p: pointer to assign to
+ * @v: value to assign (publish)
+ *
+ * Assigns the specified value to the specified RCU-protected
+ * pointer, ensuring that any concurrent RCU readers will see
+ * any prior initialization.
+ *
+ * Inserts memory barriers on architectures that require them
+ * (which is most of them), and also prevents the compiler from
+ * reordering the code that initializes the structure after the pointer
+ * assignment.  More importantly, this call documents which pointers
+ * will be dereferenced by RCU read-side code.
+ *
+ * In some special cases, you may use RCU_INIT_POINTER() instead
+ * of rcu_assign_pointer().  RCU_INIT_POINTER() is a bit faster due
+ * to the fact that it does not constrain either the CPU or the compiler.
+ * That said, using RCU_INIT_POINTER() when you should have used
+ * rcu_assign_pointer() is a very bad thing that results in
+ * impossible-to-diagnose memory corruption.  So please be careful.
+ * See the RCU_INIT_POINTER() comment header for details.
+ *
+ * Note that rcu_assign_pointer() evaluates each of its arguments only
+ * once, appearances notwithstanding.  One of the "extra" evaluations
+ * is in typeof() and the other visible only to sparse (__CHECKER__),
+ * neither of which actually execute the argument.  As with most cpp
+ * macros, this execute-arguments-only-once property is important, so
+ * please be careful when making changes to rcu_assign_pointer() and the
+ * other macros that it invokes.
+ */
+#define rcu_assign_pointer(p, v)					      \
+({									      \
+	uintptr_t _r_a_p__v = (uintptr_t)(v);				      \
+									      \
+	if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL)	      \
+		WRITE_ONCE((p), (typeof(p))(_r_a_p__v));		      \
+	else								      \
+		smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \
+	_r_a_p__v;							      \
+})
+
+#endif
Index: linux-4.9.20-rt16/include/linux/rcupdate.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/rcupdate.h
+++ linux-4.9.20-rt16/include/linux/rcupdate.h
@@ -46,6 +46,7 @@
 #include <linux/compiler.h>
 #include <linux/ktime.h>
 #include <linux/irqflags.h>
+#include <linux/rcu_assign_pointer.h>
 
 #include <asm/barrier.h>
 
@@ -178,6 +179,9 @@ void call_rcu(struct rcu_head *head,
 
 #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+#define call_rcu_bh	call_rcu
+#else
 /**
  * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period.
  * @head: structure to be used for queueing the RCU updates.
@@ -201,6 +205,7 @@ void call_rcu(struct rcu_head *head,
  */
 void call_rcu_bh(struct rcu_head *head,
 		 rcu_callback_t func);
+#endif
 
 /**
  * call_rcu_sched() - Queue an RCU for invocation after sched grace period.
@@ -301,6 +306,11 @@ void synchronize_rcu(void);
  * types of kernel builds, the rcu_read_lock() nesting depth is unknowable.
  */
 #define rcu_preempt_depth() (current->rcu_read_lock_nesting)
+#ifndef CONFIG_PREEMPT_RT_FULL
+#define sched_rcu_preempt_depth()	rcu_preempt_depth()
+#else
+static inline int sched_rcu_preempt_depth(void) { return 0; }
+#endif
 
 #else /* #ifdef CONFIG_PREEMPT_RCU */
 
@@ -326,6 +336,8 @@ static inline int rcu_preempt_depth(void
 	return 0;
 }
 
+#define sched_rcu_preempt_depth()	rcu_preempt_depth()
+
 #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
 
 /* Internal to kernel */
@@ -505,7 +517,14 @@ extern struct lockdep_map rcu_callback_m
 int debug_lockdep_rcu_enabled(void);
 
 int rcu_read_lock_held(void);
+#ifdef CONFIG_PREEMPT_RT_FULL
+static inline int rcu_read_lock_bh_held(void)
+{
+	return rcu_read_lock_held();
+}
+#else
 int rcu_read_lock_bh_held(void);
+#endif
 
 /**
  * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section?
@@ -626,54 +645,6 @@ static inline void rcu_preempt_sleep_che
 })
 
 /**
- * RCU_INITIALIZER() - statically initialize an RCU-protected global variable
- * @v: The value to statically initialize with.
- */
-#define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v)
-
-/**
- * rcu_assign_pointer() - assign to RCU-protected pointer
- * @p: pointer to assign to
- * @v: value to assign (publish)
- *
- * Assigns the specified value to the specified RCU-protected
- * pointer, ensuring that any concurrent RCU readers will see
- * any prior initialization.
- *
- * Inserts memory barriers on architectures that require them
- * (which is most of them), and also prevents the compiler from
- * reordering the code that initializes the structure after the pointer
- * assignment.  More importantly, this call documents which pointers
- * will be dereferenced by RCU read-side code.
- *
- * In some special cases, you may use RCU_INIT_POINTER() instead
- * of rcu_assign_pointer().  RCU_INIT_POINTER() is a bit faster due
- * to the fact that it does not constrain either the CPU or the compiler.
- * That said, using RCU_INIT_POINTER() when you should have used
- * rcu_assign_pointer() is a very bad thing that results in
- * impossible-to-diagnose memory corruption.  So please be careful.
- * See the RCU_INIT_POINTER() comment header for details.
- *
- * Note that rcu_assign_pointer() evaluates each of its arguments only
- * once, appearances notwithstanding.  One of the "extra" evaluations
- * is in typeof() and the other visible only to sparse (__CHECKER__),
- * neither of which actually execute the argument.  As with most cpp
- * macros, this execute-arguments-only-once property is important, so
- * please be careful when making changes to rcu_assign_pointer() and the
- * other macros that it invokes.
- */
-#define rcu_assign_pointer(p, v)					      \
-({									      \
-	uintptr_t _r_a_p__v = (uintptr_t)(v);				      \
-									      \
-	if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL)	      \
-		WRITE_ONCE((p), (typeof(p))(_r_a_p__v));		      \
-	else								      \
-		smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \
-	_r_a_p__v;							      \
-})
-
-/**
  * rcu_access_pointer() - fetch RCU pointer with no dereferencing
  * @p: The pointer to read
  *
@@ -951,10 +922,14 @@ static inline void rcu_read_unlock(void)
 static inline void rcu_read_lock_bh(void)
 {
 	local_bh_disable();
+#ifdef CONFIG_PREEMPT_RT_FULL
+	rcu_read_lock();
+#else
 	__acquire(RCU_BH);
 	rcu_lock_acquire(&rcu_bh_lock_map);
 	RCU_LOCKDEP_WARN(!rcu_is_watching(),
 			 "rcu_read_lock_bh() used illegally while idle");
+#endif
 }
 
 /*
@@ -964,10 +939,14 @@ static inline void rcu_read_lock_bh(void
  */
 static inline void rcu_read_unlock_bh(void)
 {
+#ifdef CONFIG_PREEMPT_RT_FULL
+	rcu_read_unlock();
+#else
 	RCU_LOCKDEP_WARN(!rcu_is_watching(),
 			 "rcu_read_unlock_bh() used illegally while idle");
 	rcu_lock_release(&rcu_bh_lock_map);
 	__release(RCU_BH);
+#endif
 	local_bh_enable();
 }
 
Index: linux-4.9.20-rt16/include/linux/rcutree.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/rcutree.h
+++ linux-4.9.20-rt16/include/linux/rcutree.h
@@ -44,7 +44,11 @@ static inline void rcu_virt_note_context
 	rcu_note_context_switch();
 }
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+# define synchronize_rcu_bh	synchronize_rcu
+#else
 void synchronize_rcu_bh(void);
+#endif
 void synchronize_sched_expedited(void);
 void synchronize_rcu_expedited(void);
 
@@ -72,7 +76,11 @@ static inline void synchronize_rcu_bh_ex
 }
 
 void rcu_barrier(void);
+#ifdef CONFIG_PREEMPT_RT_FULL
+# define rcu_barrier_bh                rcu_barrier
+#else
 void rcu_barrier_bh(void);
+#endif
 void rcu_barrier_sched(void);
 unsigned long get_state_synchronize_rcu(void);
 void cond_synchronize_rcu(unsigned long oldstate);
@@ -82,17 +90,14 @@ void cond_synchronize_sched(unsigned lon
 extern unsigned long rcutorture_testseq;
 extern unsigned long rcutorture_vernum;
 unsigned long rcu_batches_started(void);
-unsigned long rcu_batches_started_bh(void);
 unsigned long rcu_batches_started_sched(void);
 unsigned long rcu_batches_completed(void);
-unsigned long rcu_batches_completed_bh(void);
 unsigned long rcu_batches_completed_sched(void);
 unsigned long rcu_exp_batches_completed(void);
 unsigned long rcu_exp_batches_completed_sched(void);
 void show_rcu_gp_kthreads(void);
 
 void rcu_force_quiescent_state(void);
-void rcu_bh_force_quiescent_state(void);
 void rcu_sched_force_quiescent_state(void);
 
 void rcu_idle_enter(void);
@@ -109,6 +114,16 @@ extern int rcu_scheduler_active __read_m
 
 bool rcu_is_watching(void);
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+void rcu_bh_force_quiescent_state(void);
+unsigned long rcu_batches_started_bh(void);
+unsigned long rcu_batches_completed_bh(void);
+#else
+# define rcu_bh_force_quiescent_state	rcu_force_quiescent_state
+# define rcu_batches_completed_bh	rcu_batches_completed
+# define rcu_batches_started_bh		rcu_batches_completed
+#endif
+
 void rcu_all_qs(void);
 
 /* RCUtree hotplug events */
Index: linux-4.9.20-rt16/include/linux/rtmutex.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/rtmutex.h
+++ linux-4.9.20-rt16/include/linux/rtmutex.h
@@ -13,11 +13,15 @@
 #define __LINUX_RT_MUTEX_H
 
 #include <linux/linkage.h>
+#include <linux/spinlock_types_raw.h>
 #include <linux/rbtree.h>
-#include <linux/spinlock_types.h>
 
 extern int max_lock_depth; /* for sysctl */
 
+#ifdef CONFIG_DEBUG_MUTEXES
+#include <linux/debug_locks.h>
+#endif
+
 /**
  * The rt_mutex structure
  *
@@ -31,8 +35,8 @@ struct rt_mutex {
 	struct rb_root          waiters;
 	struct rb_node          *waiters_leftmost;
 	struct task_struct	*owner;
-#ifdef CONFIG_DEBUG_RT_MUTEXES
 	int			save_state;
+#ifdef CONFIG_DEBUG_RT_MUTEXES
 	const char 		*name, *file;
 	int			line;
 	void			*magic;
@@ -55,22 +59,33 @@ struct hrtimer_sleeper;
 # define rt_mutex_debug_check_no_locks_held(task)	do { } while (0)
 #endif
 
+# define rt_mutex_init(mutex)					\
+	do {							\
+		raw_spin_lock_init(&(mutex)->wait_lock);	\
+		__rt_mutex_init(mutex, #mutex);			\
+	} while (0)
+
 #ifdef CONFIG_DEBUG_RT_MUTEXES
 # define __DEBUG_RT_MUTEX_INITIALIZER(mutexname) \
 	, .name = #mutexname, .file = __FILE__, .line = __LINE__
-# define rt_mutex_init(mutex)			__rt_mutex_init(mutex, __func__)
  extern void rt_mutex_debug_task_free(struct task_struct *tsk);
 #else
 # define __DEBUG_RT_MUTEX_INITIALIZER(mutexname)
-# define rt_mutex_init(mutex)			__rt_mutex_init(mutex, NULL)
 # define rt_mutex_debug_task_free(t)			do { } while (0)
 #endif
 
-#define __RT_MUTEX_INITIALIZER(mutexname) \
-	{ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \
+#define __RT_MUTEX_INITIALIZER_PLAIN(mutexname) \
+	 .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \
 	, .waiters = RB_ROOT \
 	, .owner = NULL \
-	__DEBUG_RT_MUTEX_INITIALIZER(mutexname)}
+	__DEBUG_RT_MUTEX_INITIALIZER(mutexname)
+
+#define __RT_MUTEX_INITIALIZER(mutexname) \
+	{ __RT_MUTEX_INITIALIZER_PLAIN(mutexname) }
+
+#define __RT_MUTEX_INITIALIZER_SAVE_STATE(mutexname) \
+	{ __RT_MUTEX_INITIALIZER_PLAIN(mutexname)    \
+	, .save_state = 1 }
 
 #define DEFINE_RT_MUTEX(mutexname) \
 	struct rt_mutex mutexname = __RT_MUTEX_INITIALIZER(mutexname)
@@ -90,7 +105,9 @@ extern void __rt_mutex_init(struct rt_mu
 extern void rt_mutex_destroy(struct rt_mutex *lock);
 
 extern void rt_mutex_lock(struct rt_mutex *lock);
+extern int rt_mutex_lock_state(struct rt_mutex *lock, int state);
 extern int rt_mutex_lock_interruptible(struct rt_mutex *lock);
+extern int rt_mutex_lock_killable(struct rt_mutex *lock);
 extern int rt_mutex_timed_lock(struct rt_mutex *lock,
 			       struct hrtimer_sleeper *timeout);
 
Index: linux-4.9.20-rt16/include/linux/rwlock_rt.h
===================================================================
--- /dev/null
+++ linux-4.9.20-rt16/include/linux/rwlock_rt.h
@@ -0,0 +1,99 @@
+#ifndef __LINUX_RWLOCK_RT_H
+#define __LINUX_RWLOCK_RT_H
+
+#ifndef __LINUX_SPINLOCK_H
+#error Do not include directly. Use spinlock.h
+#endif
+
+#define rwlock_init(rwl)				\
+do {							\
+	static struct lock_class_key __key;		\
+							\
+	rt_mutex_init(&(rwl)->lock);			\
+	__rt_rwlock_init(rwl, #rwl, &__key);		\
+} while (0)
+
+extern void __lockfunc rt_write_lock(rwlock_t *rwlock);
+extern void __lockfunc rt_read_lock(rwlock_t *rwlock);
+extern int __lockfunc rt_write_trylock(rwlock_t *rwlock);
+extern int __lockfunc rt_write_trylock_irqsave(rwlock_t *trylock, unsigned long *flags);
+extern int __lockfunc rt_read_trylock(rwlock_t *rwlock);
+extern void __lockfunc rt_write_unlock(rwlock_t *rwlock);
+extern void __lockfunc rt_read_unlock(rwlock_t *rwlock);
+extern unsigned long __lockfunc rt_write_lock_irqsave(rwlock_t *rwlock);
+extern unsigned long __lockfunc rt_read_lock_irqsave(rwlock_t *rwlock);
+extern void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key);
+
+#define read_trylock(lock)	__cond_lock(lock, rt_read_trylock(lock))
+#define write_trylock(lock)	__cond_lock(lock, rt_write_trylock(lock))
+
+#define write_trylock_irqsave(lock, flags)	\
+	__cond_lock(lock, rt_write_trylock_irqsave(lock, &flags))
+
+#define read_lock_irqsave(lock, flags)			\
+	do {						\
+		typecheck(unsigned long, flags);	\
+		flags = rt_read_lock_irqsave(lock);	\
+	} while (0)
+
+#define write_lock_irqsave(lock, flags)			\
+	do {						\
+		typecheck(unsigned long, flags);	\
+		flags = rt_write_lock_irqsave(lock);	\
+	} while (0)
+
+#define read_lock(lock)		rt_read_lock(lock)
+
+#define read_lock_bh(lock)				\
+	do {						\
+		local_bh_disable();			\
+		rt_read_lock(lock);			\
+	} while (0)
+
+#define read_lock_irq(lock)	read_lock(lock)
+
+#define write_lock(lock)	rt_write_lock(lock)
+
+#define write_lock_bh(lock)				\
+	do {						\
+		local_bh_disable();			\
+		rt_write_lock(lock);			\
+	} while (0)
+
+#define write_lock_irq(lock)	write_lock(lock)
+
+#define read_unlock(lock)	rt_read_unlock(lock)
+
+#define read_unlock_bh(lock)				\
+	do {						\
+		rt_read_unlock(lock);			\
+		local_bh_enable();			\
+	} while (0)
+
+#define read_unlock_irq(lock)	read_unlock(lock)
+
+#define write_unlock(lock)	rt_write_unlock(lock)
+
+#define write_unlock_bh(lock)				\
+	do {						\
+		rt_write_unlock(lock);			\
+		local_bh_enable();			\
+	} while (0)
+
+#define write_unlock_irq(lock)	write_unlock(lock)
+
+#define read_unlock_irqrestore(lock, flags)		\
+	do {						\
+		typecheck(unsigned long, flags);	\
+		(void) flags;				\
+		rt_read_unlock(lock);			\
+	} while (0)
+
+#define write_unlock_irqrestore(lock, flags) \
+	do {						\
+		typecheck(unsigned long, flags);	\
+		(void) flags;				\
+		rt_write_unlock(lock);			\
+	} while (0)
+
+#endif
Index: linux-4.9.20-rt16/include/linux/rwlock_types.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/rwlock_types.h
+++ linux-4.9.20-rt16/include/linux/rwlock_types.h
@@ -1,6 +1,10 @@
 #ifndef __LINUX_RWLOCK_TYPES_H
 #define __LINUX_RWLOCK_TYPES_H
 
+#if !defined(__LINUX_SPINLOCK_TYPES_H)
+# error "Do not include directly, include spinlock_types.h"
+#endif
+
 /*
  * include/linux/rwlock_types.h - generic rwlock type definitions
  *				  and initializers
Index: linux-4.9.20-rt16/include/linux/rwlock_types_rt.h
===================================================================
--- /dev/null
+++ linux-4.9.20-rt16/include/linux/rwlock_types_rt.h
@@ -0,0 +1,33 @@
+#ifndef __LINUX_RWLOCK_TYPES_RT_H
+#define __LINUX_RWLOCK_TYPES_RT_H
+
+#ifndef __LINUX_SPINLOCK_TYPES_H
+#error "Do not include directly. Include spinlock_types.h instead"
+#endif
+
+/*
+ * rwlocks - rtmutex which allows single reader recursion
+ */
+typedef struct {
+	struct rt_mutex		lock;
+	int			read_depth;
+	unsigned int		break_lock;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	dep_map;
+#endif
+} rwlock_t;
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define RW_DEP_MAP_INIT(lockname)	.dep_map = { .name = #lockname }
+#else
+# define RW_DEP_MAP_INIT(lockname)
+#endif
+
+#define __RW_LOCK_UNLOCKED(name) \
+	{ .lock = __RT_MUTEX_INITIALIZER_SAVE_STATE(name.lock),	\
+	  RW_DEP_MAP_INIT(name) }
+
+#define DEFINE_RWLOCK(name) \
+	rwlock_t name = __RW_LOCK_UNLOCKED(name)
+
+#endif
Index: linux-4.9.20-rt16/include/linux/rwsem.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/rwsem.h
+++ linux-4.9.20-rt16/include/linux/rwsem.h
@@ -19,6 +19,10 @@
 #include <linux/osq_lock.h>
 #endif
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+#include <linux/rwsem_rt.h>
+#else /* PREEMPT_RT_FULL */
+
 struct rw_semaphore;
 
 #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK
@@ -106,6 +110,13 @@ static inline int rwsem_is_contended(str
 	return !list_empty(&sem->wait_list);
 }
 
+#endif /* !PREEMPT_RT_FULL */
+
+/*
+ * The functions below are the same for all rwsem implementations including
+ * the RT specific variant.
+ */
+
 /*
  * lock for reading
  */
Index: linux-4.9.20-rt16/include/linux/rwsem_rt.h
===================================================================
--- /dev/null
+++ linux-4.9.20-rt16/include/linux/rwsem_rt.h
@@ -0,0 +1,67 @@
+#ifndef _LINUX_RWSEM_RT_H
+#define _LINUX_RWSEM_RT_H
+
+#ifndef _LINUX_RWSEM_H
+#error "Include rwsem.h"
+#endif
+
+#include <linux/rtmutex.h>
+#include <linux/swait.h>
+
+#define READER_BIAS		(1U << 31)
+#define WRITER_BIAS		(1U << 30)
+
+struct rw_semaphore {
+	atomic_t		readers;
+	struct rt_mutex		rtmutex;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	dep_map;
+#endif
+};
+
+#define __RWSEM_INITIALIZER(name)				\
+{								\
+	.readers = ATOMIC_INIT(READER_BIAS),			\
+	.rtmutex = __RT_MUTEX_INITIALIZER(name.rtmutex),	\
+	RW_DEP_MAP_INIT(name)					\
+}
+
+#define DECLARE_RWSEM(lockname) \
+	struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname)
+
+extern void  __rwsem_init(struct rw_semaphore *rwsem, const char *name,
+			  struct lock_class_key *key);
+
+#define __init_rwsem(sem, name, key)			\
+do {							\
+		rt_mutex_init(&(sem)->rtmutex);		\
+		__rwsem_init((sem), (name), (key));	\
+} while (0)
+
+#define init_rwsem(sem)					\
+do {							\
+	static struct lock_class_key __key;		\
+							\
+	__init_rwsem((sem), #sem, &__key);		\
+} while (0)
+
+static inline int rwsem_is_locked(struct rw_semaphore *sem)
+{
+	return atomic_read(&sem->readers) != READER_BIAS;
+}
+
+static inline int rwsem_is_contended(struct rw_semaphore *sem)
+{
+	return atomic_read(&sem->readers) > 0;
+}
+
+extern void __down_read(struct rw_semaphore *sem);
+extern int __down_read_trylock(struct rw_semaphore *sem);
+extern void __down_write(struct rw_semaphore *sem);
+extern int __must_check __down_write_killable(struct rw_semaphore *sem);
+extern int __down_write_trylock(struct rw_semaphore *sem);
+extern void __up_read(struct rw_semaphore *sem);
+extern void __up_write(struct rw_semaphore *sem);
+extern void __downgrade_write(struct rw_semaphore *sem);
+
+#endif
Index: linux-4.9.20-rt16/include/linux/sched.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/sched.h
+++ linux-4.9.20-rt16/include/linux/sched.h
@@ -26,6 +26,7 @@ struct sched_param {
 #include <linux/nodemask.h>
 #include <linux/mm_types.h>
 #include <linux/preempt.h>
+#include <asm/kmap_types.h>
 
 #include <asm/page.h>
 #include <asm/ptrace.h>
@@ -236,17 +237,13 @@ extern char ___assert_task_state[1 - 2*!
 
 /* Convenience macros for the sake of wake_up */
 #define TASK_NORMAL		(TASK_INTERRUPTIBLE | TASK_UNINTERRUPTIBLE)
-#define TASK_ALL		(TASK_NORMAL | __TASK_STOPPED | __TASK_TRACED)
 
 /* get_task_state() */
 #define TASK_REPORT		(TASK_RUNNING | TASK_INTERRUPTIBLE | \
 				 TASK_UNINTERRUPTIBLE | __TASK_STOPPED | \
 				 __TASK_TRACED | EXIT_ZOMBIE | EXIT_DEAD)
 
-#define task_is_traced(task)	((task->state & __TASK_TRACED) != 0)
 #define task_is_stopped(task)	((task->state & __TASK_STOPPED) != 0)
-#define task_is_stopped_or_traced(task)	\
-			((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
 #define task_contributes_to_load(task)	\
 				((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
 				 (task->flags & PF_FROZEN) == 0 && \
@@ -312,6 +309,11 @@ extern char ___assert_task_state[1 - 2*!
 
 #endif
 
+#define __set_current_state_no_track(state_value)	\
+	do { current->state = (state_value); } while (0)
+#define set_current_state_no_track(state_value)		\
+	set_mb(current->state, (state_value))
+
 /* Task command name length */
 #define TASK_COMM_LEN 16
 
@@ -1022,9 +1024,31 @@ struct wake_q_head {
 #define WAKE_Q(name)					\
 	struct wake_q_head name = { WAKE_Q_TAIL, &name.first }
 
-extern void wake_q_add(struct wake_q_head *head,
-		       struct task_struct *task);
-extern void wake_up_q(struct wake_q_head *head);
+extern void __wake_q_add(struct wake_q_head *head,
+			 struct task_struct *task, bool sleeper);
+static inline void wake_q_add(struct wake_q_head *head,
+			      struct task_struct *task)
+{
+	__wake_q_add(head, task, false);
+}
+
+static inline void wake_q_add_sleeper(struct wake_q_head *head,
+				      struct task_struct *task)
+{
+	__wake_q_add(head, task, true);
+}
+
+extern void __wake_up_q(struct wake_q_head *head, bool sleeper);
+
+static inline void wake_up_q(struct wake_q_head *head)
+{
+	__wake_up_q(head, false);
+}
+
+static inline void wake_up_q_sleeper(struct wake_q_head *head)
+{
+	__wake_up_q(head, true);
+}
 
 /*
  * sched-domains (multiprocessor balancing) declarations:
@@ -1491,6 +1515,7 @@ struct task_struct {
 	struct thread_info thread_info;
 #endif
 	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
+	volatile long saved_state; /* saved state for "spinlock sleepers" */
 	void *stack;
 	atomic_t usage;
 	unsigned int flags;	/* per process flags, defined below */
@@ -1530,6 +1555,13 @@ struct task_struct {
 #endif
 
 	unsigned int policy;
+#ifdef CONFIG_PREEMPT_RT_FULL
+	int migrate_disable;
+	int migrate_disable_update;
+# ifdef CONFIG_SCHED_DEBUG
+	int migrate_disable_atomic;
+# endif
+#endif
 	int nr_cpus_allowed;
 	cpumask_t cpus_allowed;
 
@@ -1668,6 +1700,9 @@ struct task_struct {
 
 	struct task_cputime cputime_expires;
 	struct list_head cpu_timers[3];
+#ifdef CONFIG_PREEMPT_RT_BASE
+	struct task_struct *posix_timer_list;
+#endif
 
 /* process credentials */
 	const struct cred __rcu *ptracer_cred; /* Tracer's credentials at attach */
@@ -1699,10 +1734,15 @@ struct task_struct {
 /* signal handlers */
 	struct signal_struct *signal;
 	struct sighand_struct *sighand;
+	struct sigqueue *sigqueue_cache;
 
 	sigset_t blocked, real_blocked;
 	sigset_t saved_sigmask;	/* restored if set_restore_sigmask() was used */
 	struct sigpending pending;
+#ifdef CONFIG_PREEMPT_RT_FULL
+	/* TODO: move me into ->restart_block ? */
+	struct siginfo forced_info;
+#endif
 
 	unsigned long sas_ss_sp;
 	size_t sas_ss_size;
@@ -1728,11 +1768,14 @@ struct task_struct {
 	raw_spinlock_t pi_lock;
 
 	struct wake_q_node wake_q;
+	struct wake_q_node wake_q_sleeper;
 
 #ifdef CONFIG_RT_MUTEXES
 	/* PI waiters blocked on a rt_mutex held by this task */
 	struct rb_root pi_waiters;
 	struct rb_node *pi_waiters_leftmost;
+	/* Updated under owner's pi_lock and rq lock */
+	struct task_struct	*pi_top_task;
 	/* Deadlock detection and priority inheritance handling */
 	struct rt_mutex_waiter *pi_blocked_on;
 #endif
@@ -1931,6 +1974,12 @@ struct task_struct {
 	/* bitmask and counter of trace recursion */
 	unsigned long trace_recursion;
 #endif /* CONFIG_TRACING */
+#ifdef CONFIG_WAKEUP_LATENCY_HIST
+	u64 preempt_timestamp_hist;
+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
+	long timer_offset;
+#endif
+#endif
 #ifdef CONFIG_KCOV
 	/* Coverage collection mode enabled for this task (0 if disabled). */
 	enum kcov_mode kcov_mode;
@@ -1956,9 +2005,23 @@ struct task_struct {
 	unsigned int	sequential_io;
 	unsigned int	sequential_io_avg;
 #endif
+#ifdef CONFIG_PREEMPT_RT_BASE
+	struct rcu_head put_rcu;
+	int softirq_nestcnt;
+	unsigned int softirqs_raised;
+#endif
+#ifdef CONFIG_PREEMPT_RT_FULL
+# if defined CONFIG_HIGHMEM || defined CONFIG_X86_32
+	int kmap_idx;
+	pte_t kmap_pte[KM_TYPE_NR];
+# endif
+#endif
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 	unsigned long	task_state_change;
 #endif
+#ifdef CONFIG_PREEMPT_RT_FULL
+	int xmit_recursion;
+#endif
 	int pagefault_disabled;
 #ifdef CONFIG_MMU
 	struct task_struct *oom_reaper_list;
@@ -1998,14 +2061,6 @@ static inline struct vm_struct *task_sta
 }
 #endif
 
-/* Future-safe accessor for struct task_struct's cpus_allowed. */
-#define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
-
-static inline int tsk_nr_cpus_allowed(struct task_struct *p)
-{
-	return p->nr_cpus_allowed;
-}
-
 #define TNF_MIGRATED	0x01
 #define TNF_NO_GROUP	0x02
 #define TNF_SHARED	0x04
@@ -2225,6 +2280,15 @@ extern struct pid *cad_pid;
 extern void free_task(struct task_struct *tsk);
 #define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0)
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+extern void __put_task_struct_cb(struct rcu_head *rhp);
+
+static inline void put_task_struct(struct task_struct *t)
+{
+	if (atomic_dec_and_test(&t->usage))
+		call_rcu(&t->put_rcu, __put_task_struct_cb);
+}
+#else
 extern void __put_task_struct(struct task_struct *t);
 
 static inline void put_task_struct(struct task_struct *t)
@@ -2232,6 +2296,7 @@ static inline void put_task_struct(struc
 	if (atomic_dec_and_test(&t->usage))
 		__put_task_struct(t);
 }
+#endif
 
 struct task_struct *task_rcu_dereference(struct task_struct **ptask);
 struct task_struct *try_get_task_struct(struct task_struct **ptask);
@@ -2273,6 +2338,7 @@ extern void thread_group_cputime_adjuste
 /*
  * Per process flags
  */
+#define PF_IN_SOFTIRQ	0x00000001	/* Task is serving softirq */
 #define PF_EXITING	0x00000004	/* getting shut down */
 #define PF_EXITPIDONE	0x00000008	/* pi exit done on shut down */
 #define PF_VCPU		0x00000010	/* I'm a virtual CPU */
@@ -2441,6 +2507,10 @@ extern void do_set_cpus_allowed(struct t
 
 extern int set_cpus_allowed_ptr(struct task_struct *p,
 				const struct cpumask *new_mask);
+int migrate_me(void);
+void tell_sched_cpu_down_begin(int cpu);
+void tell_sched_cpu_down_done(int cpu);
+
 #else
 static inline void do_set_cpus_allowed(struct task_struct *p,
 				      const struct cpumask *new_mask)
@@ -2453,6 +2523,9 @@ static inline int set_cpus_allowed_ptr(s
 		return -EINVAL;
 	return 0;
 }
+static inline int migrate_me(void) { return 0; }
+static inline void tell_sched_cpu_down_begin(int cpu) { }
+static inline void tell_sched_cpu_down_done(int cpu) { }
 #endif
 
 #ifdef CONFIG_NO_HZ_COMMON
@@ -2691,6 +2764,7 @@ extern void xtime_update(unsigned long t
 
 extern int wake_up_state(struct task_struct *tsk, unsigned int state);
 extern int wake_up_process(struct task_struct *tsk);
+extern int wake_up_lock_sleeper(struct task_struct * tsk);
 extern void wake_up_new_task(struct task_struct *tsk);
 #ifdef CONFIG_SMP
  extern void kick_process(struct task_struct *tsk);
@@ -2899,6 +2973,17 @@ static inline void mmdrop(struct mm_stru
 		__mmdrop(mm);
 }
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+extern void __mmdrop_delayed(struct rcu_head *rhp);
+static inline void mmdrop_delayed(struct mm_struct *mm)
+{
+	if (atomic_dec_and_test(&mm->mm_count))
+		call_rcu(&mm->delayed_drop, __mmdrop_delayed);
+}
+#else
+# define mmdrop_delayed(mm)	mmdrop(mm)
+#endif
+
 static inline void mmdrop_async_fn(struct work_struct *work)
 {
 	struct mm_struct *mm = container_of(work, struct mm_struct, async_put_work);
@@ -3291,6 +3376,43 @@ static inline int test_tsk_need_resched(
 	return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED));
 }
 
+#ifdef CONFIG_PREEMPT_LAZY
+static inline void set_tsk_need_resched_lazy(struct task_struct *tsk)
+{
+	set_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY);
+}
+
+static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk)
+{
+	clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY);
+}
+
+static inline int test_tsk_need_resched_lazy(struct task_struct *tsk)
+{
+	return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY));
+}
+
+static inline int need_resched_lazy(void)
+{
+	return test_thread_flag(TIF_NEED_RESCHED_LAZY);
+}
+
+static inline int need_resched_now(void)
+{
+	return test_thread_flag(TIF_NEED_RESCHED);
+}
+
+#else
+static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk) { }
+static inline int need_resched_lazy(void) { return 0; }
+
+static inline int need_resched_now(void)
+{
+	return test_thread_flag(TIF_NEED_RESCHED);
+}
+
+#endif
+
 static inline int restart_syscall(void)
 {
 	set_tsk_thread_flag(current, TIF_SIGPENDING);
@@ -3322,6 +3444,51 @@ static inline int signal_pending_state(l
 	return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p);
 }
 
+static inline bool __task_is_stopped_or_traced(struct task_struct *task)
+{
+	if (task->state & (__TASK_STOPPED | __TASK_TRACED))
+		return true;
+#ifdef CONFIG_PREEMPT_RT_FULL
+	if (task->saved_state & (__TASK_STOPPED | __TASK_TRACED))
+		return true;
+#endif
+	return false;
+}
+
+static inline bool task_is_stopped_or_traced(struct task_struct *task)
+{
+	bool traced_stopped;
+
+#ifdef CONFIG_PREEMPT_RT_FULL
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&task->pi_lock, flags);
+	traced_stopped = __task_is_stopped_or_traced(task);
+	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+#else
+	traced_stopped = __task_is_stopped_or_traced(task);
+#endif
+	return traced_stopped;
+}
+
+static inline bool task_is_traced(struct task_struct *task)
+{
+	bool traced = false;
+
+	if (task->state & __TASK_TRACED)
+		return true;
+#ifdef CONFIG_PREEMPT_RT_FULL
+	/* in case the task is sleeping on tasklist_lock */
+	raw_spin_lock_irq(&task->pi_lock);
+	if (task->state & __TASK_TRACED)
+		traced = true;
+	else if (task->saved_state & __TASK_TRACED)
+		traced = true;
+	raw_spin_unlock_irq(&task->pi_lock);
+#endif
+	return traced;
+}
+
 /*
  * cond_resched() and cond_resched_lock(): latency reduction via
  * explicit rescheduling in places that are safe. The return
@@ -3347,12 +3514,16 @@ extern int __cond_resched_lock(spinlock_
 	__cond_resched_lock(lock);				\
 })
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 extern int __cond_resched_softirq(void);
 
 #define cond_resched_softirq() ({					\
 	___might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET);	\
 	__cond_resched_softirq();					\
 })
+#else
+# define cond_resched_softirq()		cond_resched()
+#endif
 
 static inline void cond_resched_rcu(void)
 {
@@ -3527,6 +3698,31 @@ static inline void set_task_cpu(struct t
 
 #endif /* CONFIG_SMP */
 
+static inline int __migrate_disabled(struct task_struct *p)
+{
+#ifdef CONFIG_PREEMPT_RT_FULL
+	return p->migrate_disable;
+#else
+	return 0;
+#endif
+}
+
+/* Future-safe accessor for struct task_struct's cpus_allowed. */
+static inline const struct cpumask *tsk_cpus_allowed(struct task_struct *p)
+{
+	if (__migrate_disabled(p))
+		return cpumask_of(task_cpu(p));
+
+	return &p->cpus_allowed;
+}
+
+static inline int tsk_nr_cpus_allowed(struct task_struct *p)
+{
+	if (__migrate_disabled(p))
+		return 1;
+	return p->nr_cpus_allowed;
+}
+
 extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask);
 extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
 
Index: linux-4.9.20-rt16/include/linux/sched/rt.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/sched/rt.h
+++ linux-4.9.20-rt16/include/linux/sched/rt.h
@@ -16,27 +16,20 @@ static inline int rt_task(struct task_st
 }
 
 #ifdef CONFIG_RT_MUTEXES
-extern int rt_mutex_getprio(struct task_struct *p);
-extern void rt_mutex_setprio(struct task_struct *p, int prio);
-extern int rt_mutex_get_effective_prio(struct task_struct *task, int newprio);
-extern struct task_struct *rt_mutex_get_top_task(struct task_struct *task);
+/*
+ * Must hold either p->pi_lock or task_rq(p)->lock.
+ */
+static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *p)
+{
+	return p->pi_top_task;
+}
+extern void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task);
 extern void rt_mutex_adjust_pi(struct task_struct *p);
 static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
 {
 	return tsk->pi_blocked_on != NULL;
 }
 #else
-static inline int rt_mutex_getprio(struct task_struct *p)
-{
-	return p->normal_prio;
-}
-
-static inline int rt_mutex_get_effective_prio(struct task_struct *task,
-					      int newprio)
-{
-	return newprio;
-}
-
 static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
 {
 	return NULL;
Index: linux-4.9.20-rt16/include/linux/seqlock.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/seqlock.h
+++ linux-4.9.20-rt16/include/linux/seqlock.h
@@ -220,20 +220,30 @@ static inline int read_seqcount_retry(co
 	return __read_seqcount_retry(s, start);
 }
 
-
-
-static inline void raw_write_seqcount_begin(seqcount_t *s)
+static inline void __raw_write_seqcount_begin(seqcount_t *s)
 {
 	s->sequence++;
 	smp_wmb();
 }
 
-static inline void raw_write_seqcount_end(seqcount_t *s)
+static inline void raw_write_seqcount_begin(seqcount_t *s)
+{
+	preempt_disable_rt();
+	__raw_write_seqcount_begin(s);
+}
+
+static inline void __raw_write_seqcount_end(seqcount_t *s)
 {
 	smp_wmb();
 	s->sequence++;
 }
 
+static inline void raw_write_seqcount_end(seqcount_t *s)
+{
+	__raw_write_seqcount_end(s);
+	preempt_enable_rt();
+}
+
 /**
  * raw_write_seqcount_barrier - do a seq write barrier
  * @s: pointer to seqcount_t
@@ -428,10 +438,32 @@ typedef struct {
 /*
  * Read side functions for starting and finalizing a read side section.
  */
+#ifndef CONFIG_PREEMPT_RT_FULL
 static inline unsigned read_seqbegin(const seqlock_t *sl)
 {
 	return read_seqcount_begin(&sl->seqcount);
 }
+#else
+/*
+ * Starvation safe read side for RT
+ */
+static inline unsigned read_seqbegin(seqlock_t *sl)
+{
+	unsigned ret;
+
+repeat:
+	ret = ACCESS_ONCE(sl->seqcount.sequence);
+	if (unlikely(ret & 1)) {
+		/*
+		 * Take the lock and let the writer proceed (i.e. evtl
+		 * boost it), otherwise we could loop here forever.
+		 */
+		spin_unlock_wait(&sl->lock);
+		goto repeat;
+	}
+	return ret;
+}
+#endif
 
 static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
 {
@@ -446,36 +478,45 @@ static inline unsigned read_seqretry(con
 static inline void write_seqlock(seqlock_t *sl)
 {
 	spin_lock(&sl->lock);
-	write_seqcount_begin(&sl->seqcount);
+	__raw_write_seqcount_begin(&sl->seqcount);
+}
+
+static inline int try_write_seqlock(seqlock_t *sl)
+{
+	if (spin_trylock(&sl->lock)) {
+		__raw_write_seqcount_begin(&sl->seqcount);
+		return 1;
+	}
+	return 0;
 }
 
 static inline void write_sequnlock(seqlock_t *sl)
 {
-	write_seqcount_end(&sl->seqcount);
+	__raw_write_seqcount_end(&sl->seqcount);
 	spin_unlock(&sl->lock);
 }
 
 static inline void write_seqlock_bh(seqlock_t *sl)
 {
 	spin_lock_bh(&sl->lock);
-	write_seqcount_begin(&sl->seqcount);
+	__raw_write_seqcount_begin(&sl->seqcount);
 }
 
 static inline void write_sequnlock_bh(seqlock_t *sl)
 {
-	write_seqcount_end(&sl->seqcount);
+	__raw_write_seqcount_end(&sl->seqcount);
 	spin_unlock_bh(&sl->lock);
 }
 
 static inline void write_seqlock_irq(seqlock_t *sl)
 {
 	spin_lock_irq(&sl->lock);
-	write_seqcount_begin(&sl->seqcount);
+	__raw_write_seqcount_begin(&sl->seqcount);
 }
 
 static inline void write_sequnlock_irq(seqlock_t *sl)
 {
-	write_seqcount_end(&sl->seqcount);
+	__raw_write_seqcount_end(&sl->seqcount);
 	spin_unlock_irq(&sl->lock);
 }
 
@@ -484,7 +525,7 @@ static inline unsigned long __write_seql
 	unsigned long flags;
 
 	spin_lock_irqsave(&sl->lock, flags);
-	write_seqcount_begin(&sl->seqcount);
+	__raw_write_seqcount_begin(&sl->seqcount);
 	return flags;
 }
 
@@ -494,7 +535,7 @@ static inline unsigned long __write_seql
 static inline void
 write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags)
 {
-	write_seqcount_end(&sl->seqcount);
+	__raw_write_seqcount_end(&sl->seqcount);
 	spin_unlock_irqrestore(&sl->lock, flags);
 }
 
Index: linux-4.9.20-rt16/include/linux/signal.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/signal.h
+++ linux-4.9.20-rt16/include/linux/signal.h
@@ -233,6 +233,7 @@ static inline void init_sigpending(struc
 }
 
 extern void flush_sigqueue(struct sigpending *queue);
+extern void flush_task_sigqueue(struct task_struct *tsk);
 
 /* Test if 'sig' is valid signal. Use this instead of testing _NSIG directly */
 static inline int valid_signal(unsigned long sig)
Index: linux-4.9.20-rt16/include/linux/skbuff.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/skbuff.h
+++ linux-4.9.20-rt16/include/linux/skbuff.h
@@ -284,6 +284,7 @@ struct sk_buff_head {
 
 	__u32		qlen;
 	spinlock_t	lock;
+	raw_spinlock_t	raw_lock;
 };
 
 struct sk_buff;
@@ -1573,6 +1574,12 @@ static inline void skb_queue_head_init(s
 	__skb_queue_head_init(list);
 }
 
+static inline void skb_queue_head_init_raw(struct sk_buff_head *list)
+{
+	raw_spin_lock_init(&list->raw_lock);
+	__skb_queue_head_init(list);
+}
+
 static inline void skb_queue_head_init_class(struct sk_buff_head *list,
 		struct lock_class_key *class)
 {
Index: linux-4.9.20-rt16/include/linux/smp.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/smp.h
+++ linux-4.9.20-rt16/include/linux/smp.h
@@ -120,6 +120,13 @@ extern unsigned int setup_max_cpus;
 extern void __init setup_nr_cpu_ids(void);
 extern void __init smp_init(void);
 
+extern int __boot_cpu_id;
+
+static inline int get_boot_cpu_id(void)
+{
+	return __boot_cpu_id;
+}
+
 #else /* !SMP */
 
 static inline void smp_send_stop(void) { }
@@ -158,6 +165,11 @@ static inline void smp_init(void) { up_l
 static inline void smp_init(void) { }
 #endif
 
+static inline int get_boot_cpu_id(void)
+{
+	return 0;
+}
+
 #endif /* !SMP */
 
 /*
@@ -185,6 +197,9 @@ static inline void smp_init(void) { }
 #define get_cpu()		({ preempt_disable(); smp_processor_id(); })
 #define put_cpu()		preempt_enable()
 
+#define get_cpu_light()		({ migrate_disable(); smp_processor_id(); })
+#define put_cpu_light()		migrate_enable()
+
 /*
  * Callback to arch code if there's nosmp or maxcpus=0 on the
  * boot command line:
Index: linux-4.9.20-rt16/include/linux/spinlock.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/spinlock.h
+++ linux-4.9.20-rt16/include/linux/spinlock.h
@@ -271,7 +271,11 @@ static inline void do_raw_spin_unlock(ra
 #define raw_spin_can_lock(lock)	(!raw_spin_is_locked(lock))
 
 /* Include rwlock functions */
-#include <linux/rwlock.h>
+#ifdef CONFIG_PREEMPT_RT_FULL
+# include <linux/rwlock_rt.h>
+#else
+# include <linux/rwlock.h>
+#endif
 
 /*
  * Pull the _spin_*()/_read_*()/_write_*() functions/declarations:
@@ -282,6 +286,10 @@ static inline void do_raw_spin_unlock(ra
 # include <linux/spinlock_api_up.h>
 #endif
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+# include <linux/spinlock_rt.h>
+#else /* PREEMPT_RT_FULL */
+
 /*
  * Map the spin_lock functions to the raw variants for PREEMPT_RT=n
  */
@@ -416,4 +424,6 @@ extern int _atomic_dec_and_lock(atomic_t
 #define atomic_dec_and_lock(atomic, lock) \
 		__cond_lock(lock, _atomic_dec_and_lock(atomic, lock))
 
+#endif /* !PREEMPT_RT_FULL */
+
 #endif /* __LINUX_SPINLOCK_H */
Index: linux-4.9.20-rt16/include/linux/spinlock_api_smp.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/spinlock_api_smp.h
+++ linux-4.9.20-rt16/include/linux/spinlock_api_smp.h
@@ -189,6 +189,8 @@ static inline int __raw_spin_trylock_bh(
 	return 0;
 }
 
-#include <linux/rwlock_api_smp.h>
+#ifndef CONFIG_PREEMPT_RT_FULL
+# include <linux/rwlock_api_smp.h>
+#endif
 
 #endif /* __LINUX_SPINLOCK_API_SMP_H */
Index: linux-4.9.20-rt16/include/linux/spinlock_rt.h
===================================================================
--- /dev/null
+++ linux-4.9.20-rt16/include/linux/spinlock_rt.h
@@ -0,0 +1,162 @@
+#ifndef __LINUX_SPINLOCK_RT_H
+#define __LINUX_SPINLOCK_RT_H
+
+#ifndef __LINUX_SPINLOCK_H
+#error Do not include directly. Use spinlock.h
+#endif
+
+#include <linux/bug.h>
+
+extern void
+__rt_spin_lock_init(spinlock_t *lock, char *name, struct lock_class_key *key);
+
+#define spin_lock_init(slock)				\
+do {							\
+	static struct lock_class_key __key;		\
+							\
+	rt_mutex_init(&(slock)->lock);			\
+	__rt_spin_lock_init(slock, #slock, &__key);	\
+} while (0)
+
+void __lockfunc rt_spin_lock__no_mg(spinlock_t *lock);
+void __lockfunc rt_spin_unlock__no_mg(spinlock_t *lock);
+int __lockfunc rt_spin_trylock__no_mg(spinlock_t *lock);
+
+extern void __lockfunc rt_spin_lock(spinlock_t *lock);
+extern unsigned long __lockfunc rt_spin_lock_trace_flags(spinlock_t *lock);
+extern void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass);
+extern void __lockfunc rt_spin_unlock(spinlock_t *lock);
+extern void __lockfunc rt_spin_unlock_wait(spinlock_t *lock);
+extern int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags);
+extern int __lockfunc rt_spin_trylock_bh(spinlock_t *lock);
+extern int __lockfunc rt_spin_trylock(spinlock_t *lock);
+extern int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock);
+
+/*
+ * lockdep-less calls, for derived types like rwlock:
+ * (for trylock they can use rt_mutex_trylock() directly.
+ */
+extern void __lockfunc __rt_spin_lock__no_mg(struct rt_mutex *lock);
+extern void __lockfunc __rt_spin_lock(struct rt_mutex *lock);
+extern void __lockfunc __rt_spin_unlock(struct rt_mutex *lock);
+
+#define spin_lock(lock)			rt_spin_lock(lock)
+
+#define spin_lock_bh(lock)			\
+	do {					\
+		local_bh_disable();		\
+		rt_spin_lock(lock);		\
+	} while (0)
+
+#define spin_lock_irq(lock)		spin_lock(lock)
+
+#define spin_do_trylock(lock)		__cond_lock(lock, rt_spin_trylock(lock))
+
+#define spin_trylock(lock)			\
+({						\
+	int __locked;				\
+	__locked = spin_do_trylock(lock);	\
+	__locked;				\
+})
+
+#ifdef CONFIG_LOCKDEP
+# define spin_lock_nested(lock, subclass)		\
+	do {						\
+		rt_spin_lock_nested(lock, subclass);	\
+	} while (0)
+
+#define spin_lock_bh_nested(lock, subclass)		\
+	do {						\
+		local_bh_disable();			\
+		rt_spin_lock_nested(lock, subclass);	\
+	} while (0)
+
+# define spin_lock_irqsave_nested(lock, flags, subclass) \
+	do {						 \
+		typecheck(unsigned long, flags);	 \
+		flags = 0;				 \
+		rt_spin_lock_nested(lock, subclass);	 \
+	} while (0)
+#else
+# define spin_lock_nested(lock, subclass)	spin_lock(lock)
+# define spin_lock_bh_nested(lock, subclass)	spin_lock_bh(lock)
+
+# define spin_lock_irqsave_nested(lock, flags, subclass) \
+	do {						 \
+		typecheck(unsigned long, flags);	 \
+		flags = 0;				 \
+		spin_lock(lock);			 \
+	} while (0)
+#endif
+
+#define spin_lock_irqsave(lock, flags)			 \
+	do {						 \
+		typecheck(unsigned long, flags);	 \
+		flags = 0;				 \
+		spin_lock(lock);			 \
+	} while (0)
+
+static inline unsigned long spin_lock_trace_flags(spinlock_t *lock)
+{
+	unsigned long flags = 0;
+#ifdef CONFIG_TRACE_IRQFLAGS
+	flags = rt_spin_lock_trace_flags(lock);
+#else
+	spin_lock(lock); /* lock_local */
+#endif
+	return flags;
+}
+
+/* FIXME: we need rt_spin_lock_nest_lock */
+#define spin_lock_nest_lock(lock, nest_lock) spin_lock_nested(lock, 0)
+
+#define spin_unlock(lock)			rt_spin_unlock(lock)
+
+#define spin_unlock_bh(lock)				\
+	do {						\
+		rt_spin_unlock(lock);			\
+		local_bh_enable();			\
+	} while (0)
+
+#define spin_unlock_irq(lock)		spin_unlock(lock)
+
+#define spin_unlock_irqrestore(lock, flags)		\
+	do {						\
+		typecheck(unsigned long, flags);	\
+		(void) flags;				\
+		spin_unlock(lock);			\
+	} while (0)
+
+#define spin_trylock_bh(lock)	__cond_lock(lock, rt_spin_trylock_bh(lock))
+#define spin_trylock_irq(lock)	spin_trylock(lock)
+
+#define spin_trylock_irqsave(lock, flags)	\
+	rt_spin_trylock_irqsave(lock, &(flags))
+
+#define spin_unlock_wait(lock)		rt_spin_unlock_wait(lock)
+
+#ifdef CONFIG_GENERIC_LOCKBREAK
+# define spin_is_contended(lock)	((lock)->break_lock)
+#else
+# define spin_is_contended(lock)	(((void)(lock), 0))
+#endif
+
+static inline int spin_can_lock(spinlock_t *lock)
+{
+	return !rt_mutex_is_locked(&lock->lock);
+}
+
+static inline int spin_is_locked(spinlock_t *lock)
+{
+	return rt_mutex_is_locked(&lock->lock);
+}
+
+static inline void assert_spin_locked(spinlock_t *lock)
+{
+	BUG_ON(!spin_is_locked(lock));
+}
+
+#define atomic_dec_and_lock(atomic, lock) \
+	atomic_dec_and_spin_lock(atomic, lock)
+
+#endif
Index: linux-4.9.20-rt16/include/linux/spinlock_types.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/spinlock_types.h
+++ linux-4.9.20-rt16/include/linux/spinlock_types.h
@@ -9,80 +9,15 @@
  * Released under the General Public License (GPL).
  */
 
-#if defined(CONFIG_SMP)
-# include <asm/spinlock_types.h>
-#else
-# include <linux/spinlock_types_up.h>
-#endif
-
-#include <linux/lockdep.h>
-
-typedef struct raw_spinlock {
-	arch_spinlock_t raw_lock;
-#ifdef CONFIG_GENERIC_LOCKBREAK
-	unsigned int break_lock;
-#endif
-#ifdef CONFIG_DEBUG_SPINLOCK
-	unsigned int magic, owner_cpu;
-	void *owner;
-#endif
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map dep_map;
-#endif
-} raw_spinlock_t;
-
-#define SPINLOCK_MAGIC		0xdead4ead
-
-#define SPINLOCK_OWNER_INIT	((void *)-1L)
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define SPIN_DEP_MAP_INIT(lockname)	.dep_map = { .name = #lockname }
-#else
-# define SPIN_DEP_MAP_INIT(lockname)
-#endif
+#include <linux/spinlock_types_raw.h>
 
-#ifdef CONFIG_DEBUG_SPINLOCK
-# define SPIN_DEBUG_INIT(lockname)		\
-	.magic = SPINLOCK_MAGIC,		\
-	.owner_cpu = -1,			\
-	.owner = SPINLOCK_OWNER_INIT,
+#ifndef CONFIG_PREEMPT_RT_FULL
+# include <linux/spinlock_types_nort.h>
+# include <linux/rwlock_types.h>
 #else
-# define SPIN_DEBUG_INIT(lockname)
+# include <linux/rtmutex.h>
+# include <linux/spinlock_types_rt.h>
+# include <linux/rwlock_types_rt.h>
 #endif
 
-#define __RAW_SPIN_LOCK_INITIALIZER(lockname)	\
-	{					\
-	.raw_lock = __ARCH_SPIN_LOCK_UNLOCKED,	\
-	SPIN_DEBUG_INIT(lockname)		\
-	SPIN_DEP_MAP_INIT(lockname) }
-
-#define __RAW_SPIN_LOCK_UNLOCKED(lockname)	\
-	(raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname)
-
-#define DEFINE_RAW_SPINLOCK(x)	raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x)
-
-typedef struct spinlock {
-	union {
-		struct raw_spinlock rlock;
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define LOCK_PADSIZE (offsetof(struct raw_spinlock, dep_map))
-		struct {
-			u8 __padding[LOCK_PADSIZE];
-			struct lockdep_map dep_map;
-		};
-#endif
-	};
-} spinlock_t;
-
-#define __SPIN_LOCK_INITIALIZER(lockname) \
-	{ { .rlock = __RAW_SPIN_LOCK_INITIALIZER(lockname) } }
-
-#define __SPIN_LOCK_UNLOCKED(lockname) \
-	(spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname)
-
-#define DEFINE_SPINLOCK(x)	spinlock_t x = __SPIN_LOCK_UNLOCKED(x)
-
-#include <linux/rwlock_types.h>
-
 #endif /* __LINUX_SPINLOCK_TYPES_H */
Index: linux-4.9.20-rt16/include/linux/spinlock_types_nort.h
===================================================================
--- /dev/null
+++ linux-4.9.20-rt16/include/linux/spinlock_types_nort.h
@@ -0,0 +1,33 @@
+#ifndef __LINUX_SPINLOCK_TYPES_NORT_H
+#define __LINUX_SPINLOCK_TYPES_NORT_H
+
+#ifndef __LINUX_SPINLOCK_TYPES_H
+#error "Do not include directly. Include spinlock_types.h instead"
+#endif
+
+/*
+ * The non RT version maps spinlocks to raw_spinlocks
+ */
+typedef struct spinlock {
+	union {
+		struct raw_spinlock rlock;
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define LOCK_PADSIZE (offsetof(struct raw_spinlock, dep_map))
+		struct {
+			u8 __padding[LOCK_PADSIZE];
+			struct lockdep_map dep_map;
+		};
+#endif
+	};
+} spinlock_t;
+
+#define __SPIN_LOCK_INITIALIZER(lockname) \
+	{ { .rlock = __RAW_SPIN_LOCK_INITIALIZER(lockname) } }
+
+#define __SPIN_LOCK_UNLOCKED(lockname) \
+	(spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname)
+
+#define DEFINE_SPINLOCK(x)	spinlock_t x = __SPIN_LOCK_UNLOCKED(x)
+
+#endif
Index: linux-4.9.20-rt16/include/linux/spinlock_types_raw.h
===================================================================
--- /dev/null
+++ linux-4.9.20-rt16/include/linux/spinlock_types_raw.h
@@ -0,0 +1,56 @@
+#ifndef __LINUX_SPINLOCK_TYPES_RAW_H
+#define __LINUX_SPINLOCK_TYPES_RAW_H
+
+#if defined(CONFIG_SMP)
+# include <asm/spinlock_types.h>
+#else
+# include <linux/spinlock_types_up.h>
+#endif
+
+#include <linux/lockdep.h>
+
+typedef struct raw_spinlock {
+	arch_spinlock_t raw_lock;
+#ifdef CONFIG_GENERIC_LOCKBREAK
+	unsigned int break_lock;
+#endif
+#ifdef CONFIG_DEBUG_SPINLOCK
+	unsigned int magic, owner_cpu;
+	void *owner;
+#endif
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map dep_map;
+#endif
+} raw_spinlock_t;
+
+#define SPINLOCK_MAGIC		0xdead4ead
+
+#define SPINLOCK_OWNER_INIT	((void *)-1L)
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define SPIN_DEP_MAP_INIT(lockname)	.dep_map = { .name = #lockname }
+#else
+# define SPIN_DEP_MAP_INIT(lockname)
+#endif
+
+#ifdef CONFIG_DEBUG_SPINLOCK
+# define SPIN_DEBUG_INIT(lockname)		\
+	.magic = SPINLOCK_MAGIC,		\
+	.owner_cpu = -1,			\
+	.owner = SPINLOCK_OWNER_INIT,
+#else
+# define SPIN_DEBUG_INIT(lockname)
+#endif
+
+#define __RAW_SPIN_LOCK_INITIALIZER(lockname)	\
+	{					\
+	.raw_lock = __ARCH_SPIN_LOCK_UNLOCKED,	\
+	SPIN_DEBUG_INIT(lockname)		\
+	SPIN_DEP_MAP_INIT(lockname) }
+
+#define __RAW_SPIN_LOCK_UNLOCKED(lockname)	\
+	(raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname)
+
+#define DEFINE_RAW_SPINLOCK(x)	raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x)
+
+#endif
Index: linux-4.9.20-rt16/include/linux/spinlock_types_rt.h
===================================================================
--- /dev/null
+++ linux-4.9.20-rt16/include/linux/spinlock_types_rt.h
@@ -0,0 +1,48 @@
+#ifndef __LINUX_SPINLOCK_TYPES_RT_H
+#define __LINUX_SPINLOCK_TYPES_RT_H
+
+#ifndef __LINUX_SPINLOCK_TYPES_H
+#error "Do not include directly. Include spinlock_types.h instead"
+#endif
+
+#include <linux/cache.h>
+
+/*
+ * PREEMPT_RT: spinlocks - an RT mutex plus lock-break field:
+ */
+typedef struct spinlock {
+	struct rt_mutex		lock;
+	unsigned int		break_lock;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	dep_map;
+#endif
+} spinlock_t;
+
+#ifdef CONFIG_DEBUG_RT_MUTEXES
+# define __RT_SPIN_INITIALIZER(name) \
+	{ \
+	.wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \
+	.save_state = 1, \
+	.file = __FILE__, \
+	.line = __LINE__ , \
+	}
+#else
+# define __RT_SPIN_INITIALIZER(name) \
+	{								\
+	.wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock),		\
+	.save_state = 1, \
+	}
+#endif
+
+/*
+.wait_list = PLIST_HEAD_INIT_RAW((name).lock.wait_list, (name).lock.wait_lock)
+*/
+
+#define __SPIN_LOCK_UNLOCKED(name)			\
+	{ .lock = __RT_SPIN_INITIALIZER(name.lock),		\
+	  SPIN_DEP_MAP_INIT(name) }
+
+#define DEFINE_SPINLOCK(name) \
+	spinlock_t name = __SPIN_LOCK_UNLOCKED(name)
+
+#endif
Index: linux-4.9.20-rt16/include/linux/srcu.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/srcu.h
+++ linux-4.9.20-rt16/include/linux/srcu.h
@@ -84,10 +84,10 @@ int init_srcu_struct(struct srcu_struct
 
 void process_srcu(struct work_struct *work);
 
-#define __SRCU_STRUCT_INIT(name)					\
+#define __SRCU_STRUCT_INIT(name, pcpu_name)				\
 	{								\
 		.completed = -300,					\
-		.per_cpu_ref = &name##_srcu_array,			\
+		.per_cpu_ref = &pcpu_name,				\
 		.queue_lock = __SPIN_LOCK_UNLOCKED(name.queue_lock),	\
 		.running = false,					\
 		.batch_queue = RCU_BATCH_INIT(name.batch_queue),	\
@@ -119,7 +119,7 @@ void process_srcu(struct work_struct *wo
  */
 #define __DEFINE_SRCU(name, is_static)					\
 	static DEFINE_PER_CPU(struct srcu_struct_array, name##_srcu_array);\
-	is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name)
+	is_static struct srcu_struct name = __SRCU_STRUCT_INIT(name, name##_srcu_array)
 #define DEFINE_SRCU(name)		__DEFINE_SRCU(name, /* not static */)
 #define DEFINE_STATIC_SRCU(name)	__DEFINE_SRCU(name, static)
 
Index: linux-4.9.20-rt16/include/linux/suspend.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/suspend.h
+++ linux-4.9.20-rt16/include/linux/suspend.h
@@ -193,6 +193,12 @@ struct platform_freeze_ops {
 	void (*end)(void);
 };
 
+#if defined(CONFIG_SUSPEND) || defined(CONFIG_HIBERNATION)
+extern bool pm_in_action;
+#else
+# define pm_in_action false
+#endif
+
 #ifdef CONFIG_SUSPEND
 /**
  * suspend_set_ops - set platform dependent suspend operations
Index: linux-4.9.20-rt16/include/linux/swait.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/swait.h
+++ linux-4.9.20-rt16/include/linux/swait.h
@@ -87,6 +87,7 @@ static inline int swait_active(struct sw
 extern void swake_up(struct swait_queue_head *q);
 extern void swake_up_all(struct swait_queue_head *q);
 extern void swake_up_locked(struct swait_queue_head *q);
+extern void swake_up_all_locked(struct swait_queue_head *q);
 
 extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait);
 extern void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state);
Index: linux-4.9.20-rt16/include/linux/swap.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/swap.h
+++ linux-4.9.20-rt16/include/linux/swap.h
@@ -11,6 +11,7 @@
 #include <linux/fs.h>
 #include <linux/atomic.h>
 #include <linux/page-flags.h>
+#include <linux/locallock.h>
 #include <asm/page.h>
 
 struct notifier_block;
@@ -247,7 +248,8 @@ struct swap_info_struct {
 void *workingset_eviction(struct address_space *mapping, struct page *page);
 bool workingset_refault(void *shadow);
 void workingset_activation(struct page *page);
-extern struct list_lru workingset_shadow_nodes;
+extern struct list_lru __workingset_shadow_nodes;
+DECLARE_LOCAL_IRQ_LOCK(workingset_shadow_lock);
 
 static inline unsigned int workingset_node_pages(struct radix_tree_node *node)
 {
@@ -292,6 +294,7 @@ extern unsigned long nr_free_pagecache_p
 
 
 /* linux/mm/swap.c */
+DECLARE_LOCAL_IRQ_LOCK(swapvec_lock);
 extern void lru_cache_add(struct page *);
 extern void lru_cache_add_anon(struct page *page);
 extern void lru_cache_add_file(struct page *page);
Index: linux-4.9.20-rt16/include/linux/swork.h
===================================================================
--- /dev/null
+++ linux-4.9.20-rt16/include/linux/swork.h
@@ -0,0 +1,24 @@
+#ifndef _LINUX_SWORK_H
+#define _LINUX_SWORK_H
+
+#include <linux/list.h>
+
+struct swork_event {
+	struct list_head item;
+	unsigned long flags;
+	void (*func)(struct swork_event *);
+};
+
+static inline void INIT_SWORK(struct swork_event *event,
+			      void (*func)(struct swork_event *))
+{
+	event->flags = 0;
+	event->func = func;
+}
+
+bool swork_queue(struct swork_event *sev);
+
+int swork_get(void);
+void swork_put(void);
+
+#endif /* _LINUX_SWORK_H */
Index: linux-4.9.20-rt16/include/linux/thread_info.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/thread_info.h
+++ linux-4.9.20-rt16/include/linux/thread_info.h
@@ -107,7 +107,17 @@ static inline int test_ti_thread_flag(st
 #define test_thread_flag(flag) \
 	test_ti_thread_flag(current_thread_info(), flag)
 
-#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED)
+#ifdef CONFIG_PREEMPT_LAZY
+#define tif_need_resched()	(test_thread_flag(TIF_NEED_RESCHED) || \
+				 test_thread_flag(TIF_NEED_RESCHED_LAZY))
+#define tif_need_resched_now()	(test_thread_flag(TIF_NEED_RESCHED))
+#define tif_need_resched_lazy()	test_thread_flag(TIF_NEED_RESCHED_LAZY))
+
+#else
+#define tif_need_resched()	test_thread_flag(TIF_NEED_RESCHED)
+#define tif_need_resched_now()	test_thread_flag(TIF_NEED_RESCHED)
+#define tif_need_resched_lazy()	0
+#endif
 
 #ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES
 static inline int arch_within_stack_frames(const void * const stack,
Index: linux-4.9.20-rt16/include/linux/timer.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/timer.h
+++ linux-4.9.20-rt16/include/linux/timer.h
@@ -241,7 +241,7 @@ extern void add_timer(struct timer_list
 
 extern int try_to_del_timer_sync(struct timer_list *timer);
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL)
   extern int del_timer_sync(struct timer_list *timer);
 #else
 # define del_timer_sync(t)		del_timer(t)
Index: linux-4.9.20-rt16/include/linux/trace_events.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/trace_events.h
+++ linux-4.9.20-rt16/include/linux/trace_events.h
@@ -56,6 +56,9 @@ struct trace_entry {
 	unsigned char		flags;
 	unsigned char		preempt_count;
 	int			pid;
+	unsigned short		migrate_disable;
+	unsigned short		padding;
+	unsigned char		preempt_lazy_count;
 };
 
 #define TRACE_EVENT_TYPE_MAX						\
Index: linux-4.9.20-rt16/include/linux/uaccess.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/uaccess.h
+++ linux-4.9.20-rt16/include/linux/uaccess.h
@@ -24,6 +24,7 @@ static __always_inline void pagefault_di
  */
 static inline void pagefault_disable(void)
 {
+	migrate_disable();
 	pagefault_disabled_inc();
 	/*
 	 * make sure to have issued the store before a pagefault
@@ -40,6 +41,7 @@ static inline void pagefault_enable(void
 	 */
 	barrier();
 	pagefault_disabled_dec();
+	migrate_enable();
 }
 
 /*
Index: linux-4.9.20-rt16/include/linux/uprobes.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/uprobes.h
+++ linux-4.9.20-rt16/include/linux/uprobes.h
@@ -27,6 +27,7 @@
 #include <linux/errno.h>
 #include <linux/rbtree.h>
 #include <linux/types.h>
+#include <linux/wait.h>
 
 struct vm_area_struct;
 struct mm_struct;
Index: linux-4.9.20-rt16/include/linux/vmstat.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/vmstat.h
+++ linux-4.9.20-rt16/include/linux/vmstat.h
@@ -33,7 +33,9 @@ DECLARE_PER_CPU(struct vm_event_state, v
  */
 static inline void __count_vm_event(enum vm_event_item item)
 {
+	preempt_disable_rt();
 	raw_cpu_inc(vm_event_states.event[item]);
+	preempt_enable_rt();
 }
 
 static inline void count_vm_event(enum vm_event_item item)
@@ -43,7 +45,9 @@ static inline void count_vm_event(enum v
 
 static inline void __count_vm_events(enum vm_event_item item, long delta)
 {
+	preempt_disable_rt();
 	raw_cpu_add(vm_event_states.event[item], delta);
+	preempt_enable_rt();
 }
 
 static inline void count_vm_events(enum vm_event_item item, long delta)
Index: linux-4.9.20-rt16/include/linux/wait.h
===================================================================
--- linux-4.9.20-rt16.orig/include/linux/wait.h
+++ linux-4.9.20-rt16/include/linux/wait.h
@@ -8,6 +8,7 @@
 #include <linux/spinlock.h>
 #include <asm/current.h>
 #include <uapi/linux/wait.h>
+#include <linux/atomic.h>
 
 typedef struct __wait_queue wait_queue_t;
 typedef int (*wait_queue_func_t)(wait_queue_t *wait, unsigned mode, int flags, void *key);
Index: linux-4.9.20-rt16/include/net/dst.h
===================================================================
--- linux-4.9.20-rt16.orig/include/net/dst.h
+++ linux-4.9.20-rt16/include/net/dst.h
@@ -452,7 +452,7 @@ static inline void dst_confirm(struct ds
 static inline int dst_neigh_output(struct dst_entry *dst, struct neighbour *n,
 				   struct sk_buff *skb)
 {
-	const struct hh_cache *hh;
+	struct hh_cache *hh;
 
 	if (dst->pending_confirm) {
 		unsigned long now = jiffies;
Index: linux-4.9.20-rt16/include/net/gen_stats.h
===================================================================
--- linux-4.9.20-rt16.orig/include/net/gen_stats.h
+++ linux-4.9.20-rt16/include/net/gen_stats.h
@@ -5,6 +5,7 @@
 #include <linux/socket.h>
 #include <linux/rtnetlink.h>
 #include <linux/pkt_sched.h>
+#include <net/net_seq_lock.h>
 
 struct gnet_stats_basic_cpu {
 	struct gnet_stats_basic_packed bstats;
@@ -33,11 +34,11 @@ int gnet_stats_start_copy_compat(struct
 				 spinlock_t *lock, struct gnet_dump *d,
 				 int padattr);
 
-int gnet_stats_copy_basic(const seqcount_t *running,
+int gnet_stats_copy_basic(net_seqlock_t *running,
 			  struct gnet_dump *d,
 			  struct gnet_stats_basic_cpu __percpu *cpu,
 			  struct gnet_stats_basic_packed *b);
-void __gnet_stats_copy_basic(const seqcount_t *running,
+void __gnet_stats_copy_basic(net_seqlock_t *running,
 			     struct gnet_stats_basic_packed *bstats,
 			     struct gnet_stats_basic_cpu __percpu *cpu,
 			     struct gnet_stats_basic_packed *b);
@@ -55,14 +56,14 @@ int gen_new_estimator(struct gnet_stats_
 		      struct gnet_stats_basic_cpu __percpu *cpu_bstats,
 		      struct gnet_stats_rate_est64 *rate_est,
 		      spinlock_t *stats_lock,
-		      seqcount_t *running, struct nlattr *opt);
+		      net_seqlock_t *running, struct nlattr *opt);
 void gen_kill_estimator(struct gnet_stats_basic_packed *bstats,
 			struct gnet_stats_rate_est64 *rate_est);
 int gen_replace_estimator(struct gnet_stats_basic_packed *bstats,
 			  struct gnet_stats_basic_cpu __percpu *cpu_bstats,
 			  struct gnet_stats_rate_est64 *rate_est,
 			  spinlock_t *stats_lock,
-			  seqcount_t *running, struct nlattr *opt);
+			  net_seqlock_t *running, struct nlattr *opt);
 bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats,
 			  const struct gnet_stats_rate_est64 *rate_est);
 #endif
Index: linux-4.9.20-rt16/include/net/neighbour.h
===================================================================
--- linux-4.9.20-rt16.orig/include/net/neighbour.h
+++ linux-4.9.20-rt16/include/net/neighbour.h
@@ -446,7 +446,7 @@ static inline int neigh_hh_bridge(struct
 }
 #endif
 
-static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb)
+static inline int neigh_hh_output(struct hh_cache *hh, struct sk_buff *skb)
 {
 	unsigned int seq;
 	int hh_len;
@@ -501,7 +501,7 @@ struct neighbour_cb {
 
 #define NEIGH_CB(skb)	((struct neighbour_cb *)(skb)->cb)
 
-static inline void neigh_ha_snapshot(char *dst, const struct neighbour *n,
+static inline void neigh_ha_snapshot(char *dst, struct neighbour *n,
 				     const struct net_device *dev)
 {
 	unsigned int seq;
Index: linux-4.9.20-rt16/include/net/net_seq_lock.h
===================================================================
--- /dev/null
+++ linux-4.9.20-rt16/include/net/net_seq_lock.h
@@ -0,0 +1,15 @@
+#ifndef __NET_NET_SEQ_LOCK_H__
+#define __NET_NET_SEQ_LOCK_H__
+
+#ifdef CONFIG_PREEMPT_RT_BASE
+# define net_seqlock_t			seqlock_t
+# define net_seq_begin(__r)		read_seqbegin(__r)
+# define net_seq_retry(__r, __s)	read_seqretry(__r, __s)
+
+#else
+# define net_seqlock_t			seqcount_t
+# define net_seq_begin(__r)		read_seqcount_begin(__r)
+# define net_seq_retry(__r, __s)	read_seqcount_retry(__r, __s)
+#endif
+
+#endif
Index: linux-4.9.20-rt16/include/net/netns/ipv4.h
===================================================================
--- linux-4.9.20-rt16.orig/include/net/netns/ipv4.h
+++ linux-4.9.20-rt16/include/net/netns/ipv4.h
@@ -69,6 +69,7 @@ struct netns_ipv4 {
 
 	int sysctl_icmp_echo_ignore_all;
 	int sysctl_icmp_echo_ignore_broadcasts;
+	int sysctl_icmp_echo_sysrq;
 	int sysctl_icmp_ignore_bogus_error_responses;
 	int sysctl_icmp_ratelimit;
 	int sysctl_icmp_ratemask;
Index: linux-4.9.20-rt16/include/net/sch_generic.h
===================================================================
--- linux-4.9.20-rt16.orig/include/net/sch_generic.h
+++ linux-4.9.20-rt16/include/net/sch_generic.h
@@ -10,6 +10,7 @@
 #include <linux/dynamic_queue_limits.h>
 #include <net/gen_stats.h>
 #include <net/rtnetlink.h>
+#include <net/net_seq_lock.h>
 
 struct Qdisc_ops;
 struct qdisc_walker;
@@ -86,7 +87,7 @@ struct Qdisc {
 	struct sk_buff		*gso_skb ____cacheline_aligned_in_smp;
 	struct qdisc_skb_head	q;
 	struct gnet_stats_basic_packed bstats;
-	seqcount_t		running;
+	net_seqlock_t		running;
 	struct gnet_stats_queue	qstats;
 	unsigned long		state;
 	struct Qdisc            *next_sched;
@@ -98,13 +99,22 @@ struct Qdisc {
 	spinlock_t		busylock ____cacheline_aligned_in_smp;
 };
 
-static inline bool qdisc_is_running(const struct Qdisc *qdisc)
+static inline bool qdisc_is_running(struct Qdisc *qdisc)
 {
+#ifdef CONFIG_PREEMPT_RT_BASE
+	return spin_is_locked(&qdisc->running.lock) ? true : false;
+#else
 	return (raw_read_seqcount(&qdisc->running) & 1) ? true : false;
+#endif
 }
 
 static inline bool qdisc_run_begin(struct Qdisc *qdisc)
 {
+#ifdef CONFIG_PREEMPT_RT_BASE
+	if (try_write_seqlock(&qdisc->running))
+		return true;
+	return false;
+#else
 	if (qdisc_is_running(qdisc))
 		return false;
 	/* Variant of write_seqcount_begin() telling lockdep a trylock
@@ -113,11 +123,16 @@ static inline bool qdisc_run_begin(struc
 	raw_write_seqcount_begin(&qdisc->running);
 	seqcount_acquire(&qdisc->running.dep_map, 0, 1, _RET_IP_);
 	return true;
+#endif
 }
 
 static inline void qdisc_run_end(struct Qdisc *qdisc)
 {
+#ifdef CONFIG_PREEMPT_RT_BASE
+	write_sequnlock(&qdisc->running);
+#else
 	write_seqcount_end(&qdisc->running);
+#endif
 }
 
 static inline bool qdisc_may_bulk(const struct Qdisc *qdisc)
@@ -308,7 +323,7 @@ static inline spinlock_t *qdisc_root_sle
 	return qdisc_lock(root);
 }
 
-static inline seqcount_t *qdisc_root_sleeping_running(const struct Qdisc *qdisc)
+static inline net_seqlock_t *qdisc_root_sleeping_running(const struct Qdisc *qdisc)
 {
 	struct Qdisc *root = qdisc_root_sleeping(qdisc);
 
Index: linux-4.9.20-rt16/include/trace/events/hist.h
===================================================================
--- /dev/null
+++ linux-4.9.20-rt16/include/trace/events/hist.h
@@ -0,0 +1,73 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM hist
+
+#if !defined(_TRACE_HIST_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_HIST_H
+
+#include "latency_hist.h"
+#include <linux/tracepoint.h>
+
+#if !defined(CONFIG_PREEMPT_OFF_HIST) && !defined(CONFIG_INTERRUPT_OFF_HIST)
+#define trace_preemptirqsoff_hist(a, b)
+#define trace_preemptirqsoff_hist_rcuidle(a, b)
+#else
+TRACE_EVENT(preemptirqsoff_hist,
+
+	TP_PROTO(int reason, int starthist),
+
+	TP_ARGS(reason, starthist),
+
+	TP_STRUCT__entry(
+		__field(int,	reason)
+		__field(int,	starthist)
+	),
+
+	TP_fast_assign(
+		__entry->reason		= reason;
+		__entry->starthist	= starthist;
+	),
+
+	TP_printk("reason=%s starthist=%s", getaction(__entry->reason),
+		  __entry->starthist ? "start" : "stop")
+);
+#endif
+
+#ifndef CONFIG_MISSED_TIMER_OFFSETS_HIST
+#define trace_hrtimer_interrupt(a, b, c, d)
+#else
+TRACE_EVENT(hrtimer_interrupt,
+
+	TP_PROTO(int cpu, long long offset, struct task_struct *curr,
+		struct task_struct *task),
+
+	TP_ARGS(cpu, offset, curr, task),
+
+	TP_STRUCT__entry(
+		__field(int,		cpu)
+		__field(long long,	offset)
+		__array(char,		ccomm,	TASK_COMM_LEN)
+		__field(int,		cprio)
+		__array(char,		tcomm,	TASK_COMM_LEN)
+		__field(int,		tprio)
+	),
+
+	TP_fast_assign(
+		__entry->cpu	= cpu;
+		__entry->offset	= offset;
+		memcpy(__entry->ccomm, curr->comm, TASK_COMM_LEN);
+		__entry->cprio  = curr->prio;
+		memcpy(__entry->tcomm, task != NULL ? task->comm : "<none>",
+			task != NULL ? TASK_COMM_LEN : 7);
+		__entry->tprio  = task != NULL ? task->prio : -1;
+	),
+
+	TP_printk("cpu=%d offset=%lld curr=%s[%d] thread=%s[%d]",
+		__entry->cpu, __entry->offset, __entry->ccomm,
+		__entry->cprio, __entry->tcomm, __entry->tprio)
+);
+#endif
+
+#endif /* _TRACE_HIST_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
Index: linux-4.9.20-rt16/include/trace/events/latency_hist.h
===================================================================
--- /dev/null
+++ linux-4.9.20-rt16/include/trace/events/latency_hist.h
@@ -0,0 +1,29 @@
+#ifndef _LATENCY_HIST_H
+#define _LATENCY_HIST_H
+
+enum hist_action {
+	IRQS_ON,
+	PREEMPT_ON,
+	TRACE_STOP,
+	IRQS_OFF,
+	PREEMPT_OFF,
+	TRACE_START,
+};
+
+static char *actions[] = {
+	"IRQS_ON",
+	"PREEMPT_ON",
+	"TRACE_STOP",
+	"IRQS_OFF",
+	"PREEMPT_OFF",
+	"TRACE_START",
+};
+
+static inline char *getaction(int action)
+{
+	if (action >= 0 && action <= sizeof(actions)/sizeof(actions[0]))
+		return actions[action];
+	return "unknown";
+}
+
+#endif /* _LATENCY_HIST_H */
Index: linux-4.9.20-rt16/include/trace/events/sched.h
===================================================================
--- linux-4.9.20-rt16.orig/include/trace/events/sched.h
+++ linux-4.9.20-rt16/include/trace/events/sched.h
@@ -70,7 +70,7 @@ DECLARE_EVENT_CLASS(sched_wakeup_templat
 	TP_fast_assign(
 		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
 		__entry->pid		= p->pid;
-		__entry->prio		= p->prio;
+		__entry->prio		= p->prio; /* XXX SCHED_DEADLINE */
 		__entry->success	= 1; /* rudiment, kill when possible */
 		__entry->target_cpu	= task_cpu(p);
 	),
@@ -147,6 +147,7 @@ TRACE_EVENT(sched_switch,
 		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
 		__entry->next_pid	= next->pid;
 		__entry->next_prio	= next->prio;
+		/* XXX SCHED_DEADLINE */
 	),
 
 	TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s%s ==> next_comm=%s next_pid=%d next_prio=%d",
@@ -181,7 +182,7 @@ TRACE_EVENT(sched_migrate_task,
 	TP_fast_assign(
 		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
 		__entry->pid		= p->pid;
-		__entry->prio		= p->prio;
+		__entry->prio		= p->prio; /* XXX SCHED_DEADLINE */
 		__entry->orig_cpu	= task_cpu(p);
 		__entry->dest_cpu	= dest_cpu;
 	),
@@ -206,7 +207,7 @@ DECLARE_EVENT_CLASS(sched_process_templa
 	TP_fast_assign(
 		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
 		__entry->pid		= p->pid;
-		__entry->prio		= p->prio;
+		__entry->prio		= p->prio; /* XXX SCHED_DEADLINE */
 	),
 
 	TP_printk("comm=%s pid=%d prio=%d",
@@ -253,7 +254,7 @@ TRACE_EVENT(sched_process_wait,
 	TP_fast_assign(
 		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
 		__entry->pid		= pid_nr(pid);
-		__entry->prio		= current->prio;
+		__entry->prio		= current->prio; /* XXX SCHED_DEADLINE */
 	),
 
 	TP_printk("comm=%s pid=%d prio=%d",
@@ -413,9 +414,9 @@ DEFINE_EVENT(sched_stat_runtime, sched_s
  */
 TRACE_EVENT(sched_pi_setprio,
 
-	TP_PROTO(struct task_struct *tsk, int newprio),
+	TP_PROTO(struct task_struct *tsk, struct task_struct *pi_task),
 
-	TP_ARGS(tsk, newprio),
+	TP_ARGS(tsk, pi_task),
 
 	TP_STRUCT__entry(
 		__array( char,	comm,	TASK_COMM_LEN	)
@@ -428,7 +429,8 @@ TRACE_EVENT(sched_pi_setprio,
 		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
 		__entry->pid		= tsk->pid;
 		__entry->oldprio	= tsk->prio;
-		__entry->newprio	= newprio;
+		__entry->newprio	= pi_task ? pi_task->prio : tsk->prio;
+		/* XXX SCHED_DEADLINE bits missing */
 	),
 
 	TP_printk("comm=%s pid=%d oldprio=%d newprio=%d",
Index: linux-4.9.20-rt16/init/Kconfig
===================================================================
--- linux-4.9.20-rt16.orig/init/Kconfig
+++ linux-4.9.20-rt16/init/Kconfig
@@ -506,7 +506,7 @@ config TINY_RCU
 
 config RCU_EXPERT
 	bool "Make expert-level adjustments to RCU configuration"
-	default n
+	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,
@@ -623,7 +623,7 @@ config RCU_FANOUT_LEAF
 
 config RCU_FAST_NO_HZ
 	bool "Accelerate last non-dyntick-idle CPU's grace periods"
-	depends on NO_HZ_COMMON && SMP && RCU_EXPERT
+	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
@@ -650,7 +650,7 @@ config TREE_RCU_TRACE
 config RCU_BOOST
 	bool "Enable RCU priority boosting"
 	depends on RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT
-	default n
+	default y if PREEMPT_RT_FULL
 	help
 	  This option boosts the priority of preempted RCU readers that
 	  block the current preemptible RCU grace period for too long.
@@ -781,19 +781,6 @@ config RCU_NOCB_CPU_ALL
 
 endchoice
 
-config RCU_EXPEDITE_BOOT
-	bool
-	default n
-	help
-	  This option enables expedited grace periods at boot time,
-	  as if rcu_expedite_gp() had been invoked early in boot.
-	  The corresponding rcu_unexpedite_gp() is invoked from
-	  rcu_end_inkernel_boot(), which is intended to be invoked
-	  at the end of the kernel-only boot sequence, just before
-	  init is exec'ed.
-
-	  Accept the default if unsure.
-
 endmenu # "RCU Subsystem"
 
 config BUILD_BIN2C
@@ -1064,6 +1051,7 @@ config CFS_BANDWIDTH
 config RT_GROUP_SCHED
 	bool "Group scheduling for SCHED_RR/FIFO"
 	depends on CGROUP_SCHED
+	depends on !PREEMPT_RT_FULL
 	default n
 	help
 	  This feature lets you explicitly allocate real CPU bandwidth
@@ -1772,6 +1760,7 @@ choice
 
 config SLAB
 	bool "SLAB"
+	depends on !PREEMPT_RT_FULL
 	select HAVE_HARDENED_USERCOPY_ALLOCATOR
 	help
 	  The regular slab allocator that is established and known to work
@@ -1792,6 +1781,7 @@ config SLUB
 config SLOB
 	depends on EXPERT
 	bool "SLOB (Simple Allocator)"
+	depends on !PREEMPT_RT_FULL
 	help
 	   SLOB replaces the stock allocator with a drastically simpler
 	   allocator. SLOB is generally more space efficient but
@@ -1810,7 +1800,7 @@ config SLAB_FREELIST_RANDOM
 
 config SLUB_CPU_PARTIAL
 	default y
-	depends on SLUB && SMP
+	depends on SLUB && SMP && !PREEMPT_RT_FULL
 	bool "SLUB per cpu partial cache"
 	help
 	  Per cpu partial caches accellerate objects allocation and freeing
Index: linux-4.9.20-rt16/init/Makefile
===================================================================
--- linux-4.9.20-rt16.orig/init/Makefile
+++ linux-4.9.20-rt16/init/Makefile
@@ -35,4 +35,4 @@ silent_chk_compile.h = :
 include/generated/compile.h: FORCE
 	@$($(quiet)chk_compile.h)
 	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/mkcompile_h $@ \
-	"$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CC) $(KBUILD_CFLAGS)"
+	"$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CONFIG_PREEMPT_RT_FULL)" "$(CC) $(KBUILD_CFLAGS)"
Index: linux-4.9.20-rt16/init/main.c
===================================================================
--- linux-4.9.20-rt16.orig/init/main.c
+++ linux-4.9.20-rt16/init/main.c
@@ -507,6 +507,7 @@ asmlinkage __visible void __init start_k
 	setup_command_line(command_line);
 	setup_nr_cpu_ids();
 	setup_per_cpu_areas();
+	softirq_early_init();
 	boot_cpu_state_init();
 	smp_prepare_boot_cpu();	/* arch-specific boot-cpu hooks */
 
Index: linux-4.9.20-rt16/ipc/sem.c
===================================================================
--- linux-4.9.20-rt16.orig/ipc/sem.c
+++ linux-4.9.20-rt16/ipc/sem.c
@@ -712,6 +712,13 @@ undo:
 static void wake_up_sem_queue_prepare(struct list_head *pt,
 				struct sem_queue *q, int error)
 {
+#ifdef CONFIG_PREEMPT_RT_BASE
+	struct task_struct *p = q->sleeper;
+	get_task_struct(p);
+	q->status = error;
+	wake_up_process(p);
+	put_task_struct(p);
+#else
 	if (list_empty(pt)) {
 		/*
 		 * Hold preempt off so that we don't get preempted and have the
@@ -723,6 +730,7 @@ static void wake_up_sem_queue_prepare(st
 	q->pid = error;
 
 	list_add_tail(&q->list, pt);
+#endif
 }
 
 /**
@@ -736,6 +744,7 @@ static void wake_up_sem_queue_prepare(st
  */
 static void wake_up_sem_queue_do(struct list_head *pt)
 {
+#ifndef CONFIG_PREEMPT_RT_BASE
 	struct sem_queue *q, *t;
 	int did_something;
 
@@ -748,6 +757,7 @@ static void wake_up_sem_queue_do(struct
 	}
 	if (did_something)
 		preempt_enable();
+#endif
 }
 
 static void unlink_queue(struct sem_array *sma, struct sem_queue *q)
Index: linux-4.9.20-rt16/kernel/Kconfig.locks
===================================================================
--- linux-4.9.20-rt16.orig/kernel/Kconfig.locks
+++ linux-4.9.20-rt16/kernel/Kconfig.locks
@@ -225,11 +225,11 @@ config ARCH_SUPPORTS_ATOMIC_RMW
 
 config MUTEX_SPIN_ON_OWNER
 	def_bool y
-	depends on SMP && !DEBUG_MUTEXES && ARCH_SUPPORTS_ATOMIC_RMW
+	depends on SMP && !DEBUG_MUTEXES && ARCH_SUPPORTS_ATOMIC_RMW && !PREEMPT_RT_FULL
 
 config RWSEM_SPIN_ON_OWNER
        def_bool y
-       depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW
+       depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW && !PREEMPT_RT_FULL
 
 config LOCK_SPIN_ON_OWNER
        def_bool y
Index: linux-4.9.20-rt16/kernel/Kconfig.preempt
===================================================================
--- linux-4.9.20-rt16.orig/kernel/Kconfig.preempt
+++ linux-4.9.20-rt16/kernel/Kconfig.preempt
@@ -1,3 +1,16 @@
+config PREEMPT
+	bool
+	select PREEMPT_COUNT
+
+config PREEMPT_RT_BASE
+	bool
+	select PREEMPT
+
+config HAVE_PREEMPT_LAZY
+	bool
+
+config PREEMPT_LAZY
+	def_bool y if HAVE_PREEMPT_LAZY && PREEMPT_RT_FULL
 
 choice
 	prompt "Preemption Model"
@@ -33,9 +46,9 @@ config PREEMPT_VOLUNTARY
 
 	  Select this if you are building a kernel for a desktop system.
 
-config PREEMPT
+config PREEMPT__LL
 	bool "Preemptible Kernel (Low-Latency Desktop)"
-	select PREEMPT_COUNT
+	select PREEMPT
 	select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK
 	help
 	  This option reduces the latency of the kernel by making
@@ -52,6 +65,22 @@ config PREEMPT
 	  embedded system with latency requirements in the milliseconds
 	  range.
 
+config PREEMPT_RTB
+	bool "Preemptible Kernel (Basic RT)"
+	select PREEMPT_RT_BASE
+	help
+	  This option is basically the same as (Low-Latency Desktop) but
+	  enables changes which are preliminary for the full preemptible
+	  RT kernel.
+
+config PREEMPT_RT_FULL
+	bool "Fully Preemptible Kernel (RT)"
+	depends on IRQ_FORCED_THREADING
+	select PREEMPT_RT_BASE
+	select PREEMPT_RCU
+	help
+	  All and everything
+
 endchoice
 
 config PREEMPT_COUNT
Index: linux-4.9.20-rt16/kernel/cgroup.c
===================================================================
--- linux-4.9.20-rt16.orig/kernel/cgroup.c
+++ linux-4.9.20-rt16/kernel/cgroup.c
@@ -5041,10 +5041,10 @@ static void css_free_rcu_fn(struct rcu_h
 	queue_work(cgroup_destroy_wq, &css->destroy_work);
 }
 
-static void css_release_work_fn(struct work_struct *work)
+static void css_release_work_fn(struct swork_event *sev)
 {
 	struct cgroup_subsys_state *css =
-		container_of(work, struct cgroup_subsys_state, destroy_work);
+		container_of(sev, struct cgroup_subsys_state, destroy_swork);
 	struct cgroup_subsys *ss = css->ss;
 	struct cgroup *cgrp = css->cgroup;
 
@@ -5087,8 +5087,8 @@ static void css_release(struct percpu_re
 	struct cgroup_subsys_state *css =
 		container_of(ref, struct cgroup_subsys_state, refcnt);
 
-	INIT_WORK(&css->destroy_work, css_release_work_fn);
-	queue_work(cgroup_destroy_wq, &css->destroy_work);
+	INIT_SWORK(&css->destroy_swork, css_release_work_fn);
+	swork_queue(&css->destroy_swork);
 }
 
 static void init_and_link_css(struct cgroup_subsys_state *css,
@@ -5749,6 +5749,7 @@ static int __init cgroup_wq_init(void)
 	 */
 	cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1);
 	BUG_ON(!cgroup_destroy_wq);
+	BUG_ON(swork_get());
 
 	/*
 	 * Used to destroy pidlists and separate to serve as flush domain.
Index: linux-4.9.20-rt16/kernel/cpu.c
===================================================================
--- linux-4.9.20-rt16.orig/kernel/cpu.c
+++ linux-4.9.20-rt16/kernel/cpu.c
@@ -239,6 +239,289 @@ static struct {
 #define cpuhp_lock_acquire()      lock_map_acquire(&cpu_hotplug.dep_map)
 #define cpuhp_lock_release()      lock_map_release(&cpu_hotplug.dep_map)
 
+/**
+ * hotplug_pcp	- per cpu hotplug descriptor
+ * @unplug:	set when pin_current_cpu() needs to sync tasks
+ * @sync_tsk:	the task that waits for tasks to finish pinned sections
+ * @refcount:	counter of tasks in pinned sections
+ * @grab_lock:	set when the tasks entering pinned sections should wait
+ * @synced:	notifier for @sync_tsk to tell cpu_down it's finished
+ * @mutex:	the mutex to make tasks wait (used when @grab_lock is true)
+ * @mutex_init:	zero if the mutex hasn't been initialized yet.
+ *
+ * Although @unplug and @sync_tsk may point to the same task, the @unplug
+ * is used as a flag and still exists after @sync_tsk has exited and
+ * @sync_tsk set to NULL.
+ */
+struct hotplug_pcp {
+	struct task_struct *unplug;
+	struct task_struct *sync_tsk;
+	int refcount;
+	int grab_lock;
+	struct completion synced;
+	struct completion unplug_wait;
+#ifdef CONFIG_PREEMPT_RT_FULL
+	/*
+	 * Note, on PREEMPT_RT, the hotplug lock must save the state of
+	 * the task, otherwise the mutex will cause the task to fail
+	 * to sleep when required. (Because it's called from migrate_disable())
+	 *
+	 * The spinlock_t on PREEMPT_RT is a mutex that saves the task's
+	 * state.
+	 */
+	spinlock_t lock;
+#else
+	struct mutex mutex;
+#endif
+	int mutex_init;
+};
+
+#ifdef CONFIG_PREEMPT_RT_FULL
+# define hotplug_lock(hp) rt_spin_lock__no_mg(&(hp)->lock)
+# define hotplug_unlock(hp) rt_spin_unlock__no_mg(&(hp)->lock)
+#else
+# define hotplug_lock(hp) mutex_lock(&(hp)->mutex)
+# define hotplug_unlock(hp) mutex_unlock(&(hp)->mutex)
+#endif
+
+static DEFINE_PER_CPU(struct hotplug_pcp, hotplug_pcp);
+
+/**
+ * pin_current_cpu - Prevent the current cpu from being unplugged
+ *
+ * Lightweight version of get_online_cpus() to prevent cpu from being
+ * unplugged when code runs in a migration disabled region.
+ *
+ * Must be called with preemption disabled (preempt_count = 1)!
+ */
+void pin_current_cpu(void)
+{
+	struct hotplug_pcp *hp;
+	int force = 0;
+
+retry:
+	hp = this_cpu_ptr(&hotplug_pcp);
+
+	if (!hp->unplug || hp->refcount || force || preempt_count() > 1 ||
+	    hp->unplug == current) {
+		hp->refcount++;
+		return;
+	}
+	if (hp->grab_lock) {
+		preempt_enable();
+		hotplug_lock(hp);
+		hotplug_unlock(hp);
+	} else {
+		preempt_enable();
+		/*
+		 * Try to push this task off of this CPU.
+		 */
+		if (!migrate_me()) {
+			preempt_disable();
+			hp = this_cpu_ptr(&hotplug_pcp);
+			if (!hp->grab_lock) {
+				/*
+				 * Just let it continue it's already pinned
+				 * or about to sleep.
+				 */
+				force = 1;
+				goto retry;
+			}
+			preempt_enable();
+		}
+	}
+	preempt_disable();
+	goto retry;
+}
+
+/**
+ * unpin_current_cpu - Allow unplug of current cpu
+ *
+ * Must be called with preemption or interrupts disabled!
+ */
+void unpin_current_cpu(void)
+{
+	struct hotplug_pcp *hp = this_cpu_ptr(&hotplug_pcp);
+
+	WARN_ON(hp->refcount <= 0);
+
+	/* This is safe. sync_unplug_thread is pinned to this cpu */
+	if (!--hp->refcount && hp->unplug && hp->unplug != current)
+		wake_up_process(hp->unplug);
+}
+
+static void wait_for_pinned_cpus(struct hotplug_pcp *hp)
+{
+	set_current_state(TASK_UNINTERRUPTIBLE);
+	while (hp->refcount) {
+		schedule_preempt_disabled();
+		set_current_state(TASK_UNINTERRUPTIBLE);
+	}
+}
+
+static int sync_unplug_thread(void *data)
+{
+	struct hotplug_pcp *hp = data;
+
+	wait_for_completion(&hp->unplug_wait);
+	preempt_disable();
+	hp->unplug = current;
+	wait_for_pinned_cpus(hp);
+
+	/*
+	 * This thread will synchronize the cpu_down() with threads
+	 * that have pinned the CPU. When the pinned CPU count reaches
+	 * zero, we inform the cpu_down code to continue to the next step.
+	 */
+	set_current_state(TASK_UNINTERRUPTIBLE);
+	preempt_enable();
+	complete(&hp->synced);
+
+	/*
+	 * If all succeeds, the next step will need tasks to wait till
+	 * the CPU is offline before continuing. To do this, the grab_lock
+	 * is set and tasks going into pin_current_cpu() will block on the
+	 * mutex. But we still need to wait for those that are already in
+	 * pinned CPU sections. If the cpu_down() failed, the kthread_should_stop()
+	 * will kick this thread out.
+	 */
+	while (!hp->grab_lock && !kthread_should_stop()) {
+		schedule();
+		set_current_state(TASK_UNINTERRUPTIBLE);
+	}
+
+	/* Make sure grab_lock is seen before we see a stale completion */
+	smp_mb();
+
+	/*
+	 * Now just before cpu_down() enters stop machine, we need to make
+	 * sure all tasks that are in pinned CPU sections are out, and new
+	 * tasks will now grab the lock, keeping them from entering pinned
+	 * CPU sections.
+	 */
+	if (!kthread_should_stop()) {
+		preempt_disable();
+		wait_for_pinned_cpus(hp);
+		preempt_enable();
+		complete(&hp->synced);
+	}
+
+	set_current_state(TASK_UNINTERRUPTIBLE);
+	while (!kthread_should_stop()) {
+		schedule();
+		set_current_state(TASK_UNINTERRUPTIBLE);
+	}
+	set_current_state(TASK_RUNNING);
+
+	/*
+	 * Force this thread off this CPU as it's going down and
+	 * we don't want any more work on this CPU.
+	 */
+	current->flags &= ~PF_NO_SETAFFINITY;
+	set_cpus_allowed_ptr(current, cpu_present_mask);
+	migrate_me();
+	return 0;
+}
+
+static void __cpu_unplug_sync(struct hotplug_pcp *hp)
+{
+	wake_up_process(hp->sync_tsk);
+	wait_for_completion(&hp->synced);
+}
+
+static void __cpu_unplug_wait(unsigned int cpu)
+{
+	struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu);
+
+	complete(&hp->unplug_wait);
+	wait_for_completion(&hp->synced);
+}
+
+/*
+ * Start the sync_unplug_thread on the target cpu and wait for it to
+ * complete.
+ */
+static int cpu_unplug_begin(unsigned int cpu)
+{
+	struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu);
+	int err;
+
+	/* Protected by cpu_hotplug.lock */
+	if (!hp->mutex_init) {
+#ifdef CONFIG_PREEMPT_RT_FULL
+		spin_lock_init(&hp->lock);
+#else
+		mutex_init(&hp->mutex);
+#endif
+		hp->mutex_init = 1;
+	}
+
+	/* Inform the scheduler to migrate tasks off this CPU */
+	tell_sched_cpu_down_begin(cpu);
+
+	init_completion(&hp->synced);
+	init_completion(&hp->unplug_wait);
+
+	hp->sync_tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d", cpu);
+	if (IS_ERR(hp->sync_tsk)) {
+		err = PTR_ERR(hp->sync_tsk);
+		hp->sync_tsk = NULL;
+		return err;
+	}
+	kthread_bind(hp->sync_tsk, cpu);
+
+	/*
+	 * Wait for tasks to get out of the pinned sections,
+	 * it's still OK if new tasks enter. Some CPU notifiers will
+	 * wait for tasks that are going to enter these sections and
+	 * we must not have them block.
+	 */
+	wake_up_process(hp->sync_tsk);
+	return 0;
+}
+
+static void cpu_unplug_sync(unsigned int cpu)
+{
+	struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu);
+
+	init_completion(&hp->synced);
+	/* The completion needs to be initialzied before setting grab_lock */
+	smp_wmb();
+
+	/* Grab the mutex before setting grab_lock */
+	hotplug_lock(hp);
+	hp->grab_lock = 1;
+
+	/*
+	 * The CPU notifiers have been completed.
+	 * Wait for tasks to get out of pinned CPU sections and have new
+	 * tasks block until the CPU is completely down.
+	 */
+	__cpu_unplug_sync(hp);
+
+	/* All done with the sync thread */
+	kthread_stop(hp->sync_tsk);
+	hp->sync_tsk = NULL;
+}
+
+static void cpu_unplug_done(unsigned int cpu)
+{
+	struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu);
+
+	hp->unplug = NULL;
+	/* Let all tasks know cpu unplug is finished before cleaning up */
+	smp_wmb();
+
+	if (hp->sync_tsk)
+		kthread_stop(hp->sync_tsk);
+
+	if (hp->grab_lock) {
+		hotplug_unlock(hp);
+		/* protected by cpu_hotplug.lock */
+		hp->grab_lock = 0;
+	}
+	tell_sched_cpu_down_done(cpu);
+}
 
 void get_online_cpus(void)
 {
@@ -802,10 +1085,14 @@ static int takedown_cpu(unsigned int cpu
 	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
 	int err;
 
+	__cpu_unplug_wait(cpu);
 	/* Park the smpboot threads */
 	kthread_park(per_cpu_ptr(&cpuhp_state, cpu)->thread);
 	smpboot_park_threads(cpu);
 
+	/* Notifiers are done. Don't let any more tasks pin this CPU. */
+	cpu_unplug_sync(cpu);
+
 	/*
 	 * Prevent irq alloc/free while the dying cpu reorganizes the
 	 * interrupt affinities.
@@ -890,6 +1177,9 @@ static int __ref _cpu_down(unsigned int
 	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
 	int prev_state, ret = 0;
 	bool hasdied = false;
+	int mycpu;
+	cpumask_var_t cpumask;
+	cpumask_var_t cpumask_org;
 
 	if (num_online_cpus() == 1)
 		return -EBUSY;
@@ -897,7 +1187,34 @@ static int __ref _cpu_down(unsigned int
 	if (!cpu_present(cpu))
 		return -EINVAL;
 
+	/* Move the downtaker off the unplug cpu */
+	if (!alloc_cpumask_var(&cpumask, GFP_KERNEL))
+		return -ENOMEM;
+	if (!alloc_cpumask_var(&cpumask_org, GFP_KERNEL))  {
+		free_cpumask_var(cpumask);
+		return -ENOMEM;
+	}
+
+	cpumask_copy(cpumask_org, tsk_cpus_allowed(current));
+	cpumask_andnot(cpumask, cpu_online_mask, cpumask_of(cpu));
+	set_cpus_allowed_ptr(current, cpumask);
+	free_cpumask_var(cpumask);
+	migrate_disable();
+	mycpu = smp_processor_id();
+	if (mycpu == cpu) {
+		printk(KERN_ERR "Yuck! Still on unplug CPU\n!");
+		migrate_enable();
+		ret = -EBUSY;
+		goto restore_cpus;
+	}
+
+	migrate_enable();
 	cpu_hotplug_begin();
+	ret = cpu_unplug_begin(cpu);
+	if (ret) {
+		printk("cpu_unplug_begin(%d) failed\n", cpu);
+		goto out_cancel;
+	}
 
 	cpuhp_tasks_frozen = tasks_frozen;
 
@@ -936,10 +1253,15 @@ static int __ref _cpu_down(unsigned int
 
 	hasdied = prev_state != st->state && st->state == CPUHP_OFFLINE;
 out:
+	cpu_unplug_done(cpu);
+out_cancel:
 	cpu_hotplug_done();
 	/* This post dead nonsense must die */
 	if (!ret && hasdied)
 		cpu_notify_nofail(CPU_POST_DEAD, cpu);
+restore_cpus:
+	set_cpus_allowed_ptr(current, cpumask_org);
+	free_cpumask_var(cpumask_org);
 	return ret;
 }
 
@@ -1242,6 +1564,8 @@ core_initcall(cpu_hotplug_pm_sync_init);
 
 #endif /* CONFIG_PM_SLEEP_SMP */
 
+int __boot_cpu_id;
+
 #endif /* CONFIG_SMP */
 
 /* Boot processor state steps */
@@ -1926,6 +2250,10 @@ void __init boot_cpu_init(void)
 	set_cpu_active(cpu, true);
 	set_cpu_present(cpu, true);
 	set_cpu_possible(cpu, true);
+
+#ifdef CONFIG_SMP
+	__boot_cpu_id = cpu;
+#endif
 }
 
 /*
Index: linux-4.9.20-rt16/kernel/cpuset.c
===================================================================
--- linux-4.9.20-rt16.orig/kernel/cpuset.c
+++ linux-4.9.20-rt16/kernel/cpuset.c
@@ -285,7 +285,7 @@ static struct cpuset top_cpuset = {
  */
 
 static DEFINE_MUTEX(cpuset_mutex);
-static DEFINE_SPINLOCK(callback_lock);
+static DEFINE_RAW_SPINLOCK(callback_lock);
 
 static struct workqueue_struct *cpuset_migrate_mm_wq;
 
@@ -908,9 +908,9 @@ static void update_cpumasks_hier(struct
 			continue;
 		rcu_read_unlock();
 
-		spin_lock_irq(&callback_lock);
+		raw_spin_lock_irq(&callback_lock);
 		cpumask_copy(cp->effective_cpus, new_cpus);
-		spin_unlock_irq(&callback_lock);
+		raw_spin_unlock_irq(&callback_lock);
 
 		WARN_ON(!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
 			!cpumask_equal(cp->cpus_allowed, cp->effective_cpus));
@@ -975,9 +975,9 @@ static int update_cpumask(struct cpuset
 	if (retval < 0)
 		return retval;
 
-	spin_lock_irq(&callback_lock);
+	raw_spin_lock_irq(&callback_lock);
 	cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed);
-	spin_unlock_irq(&callback_lock);
+	raw_spin_unlock_irq(&callback_lock);
 
 	/* use trialcs->cpus_allowed as a temp variable */
 	update_cpumasks_hier(cs, trialcs->cpus_allowed);
@@ -1177,9 +1177,9 @@ static void update_nodemasks_hier(struct
 			continue;
 		rcu_read_unlock();
 
-		spin_lock_irq(&callback_lock);
+		raw_spin_lock_irq(&callback_lock);
 		cp->effective_mems = *new_mems;
-		spin_unlock_irq(&callback_lock);
+		raw_spin_unlock_irq(&callback_lock);
 
 		WARN_ON(!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
 			!nodes_equal(cp->mems_allowed, cp->effective_mems));
@@ -1247,9 +1247,9 @@ static int update_nodemask(struct cpuset
 	if (retval < 0)
 		goto done;
 
-	spin_lock_irq(&callback_lock);
+	raw_spin_lock_irq(&callback_lock);
 	cs->mems_allowed = trialcs->mems_allowed;
-	spin_unlock_irq(&callback_lock);
+	raw_spin_unlock_irq(&callback_lock);
 
 	/* use trialcs->mems_allowed as a temp variable */
 	update_nodemasks_hier(cs, &trialcs->mems_allowed);
@@ -1340,9 +1340,9 @@ static int update_flag(cpuset_flagbits_t
 	spread_flag_changed = ((is_spread_slab(cs) != is_spread_slab(trialcs))
 			|| (is_spread_page(cs) != is_spread_page(trialcs)));
 
-	spin_lock_irq(&callback_lock);
+	raw_spin_lock_irq(&callback_lock);
 	cs->flags = trialcs->flags;
-	spin_unlock_irq(&callback_lock);
+	raw_spin_unlock_irq(&callback_lock);
 
 	if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed)
 		rebuild_sched_domains_locked();
@@ -1757,7 +1757,7 @@ static int cpuset_common_seq_show(struct
 	cpuset_filetype_t type = seq_cft(sf)->private;
 	int ret = 0;
 
-	spin_lock_irq(&callback_lock);
+	raw_spin_lock_irq(&callback_lock);
 
 	switch (type) {
 	case FILE_CPULIST:
@@ -1776,7 +1776,7 @@ static int cpuset_common_seq_show(struct
 		ret = -EINVAL;
 	}
 
-	spin_unlock_irq(&callback_lock);
+	raw_spin_unlock_irq(&callback_lock);
 	return ret;
 }
 
@@ -1990,12 +1990,12 @@ static int cpuset_css_online(struct cgro
 
 	cpuset_inc();
 
-	spin_lock_irq(&callback_lock);
+	raw_spin_lock_irq(&callback_lock);
 	if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) {
 		cpumask_copy(cs->effective_cpus, parent->effective_cpus);
 		cs->effective_mems = parent->effective_mems;
 	}
-	spin_unlock_irq(&callback_lock);
+	raw_spin_unlock_irq(&callback_lock);
 
 	if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags))
 		goto out_unlock;
@@ -2022,12 +2022,12 @@ static int cpuset_css_online(struct cgro
 	}
 	rcu_read_unlock();
 
-	spin_lock_irq(&callback_lock);
+	raw_spin_lock_irq(&callback_lock);
 	cs->mems_allowed = parent->mems_allowed;
 	cs->effective_mems = parent->mems_allowed;
 	cpumask_copy(cs->cpus_allowed, parent->cpus_allowed);
 	cpumask_copy(cs->effective_cpus, parent->cpus_allowed);
-	spin_unlock_irq(&callback_lock);
+	raw_spin_unlock_irq(&callback_lock);
 out_unlock:
 	mutex_unlock(&cpuset_mutex);
 	return 0;
@@ -2066,7 +2066,7 @@ static void cpuset_css_free(struct cgrou
 static void cpuset_bind(struct cgroup_subsys_state *root_css)
 {
 	mutex_lock(&cpuset_mutex);
-	spin_lock_irq(&callback_lock);
+	raw_spin_lock_irq(&callback_lock);
 
 	if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) {
 		cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask);
@@ -2077,7 +2077,7 @@ static void cpuset_bind(struct cgroup_su
 		top_cpuset.mems_allowed = top_cpuset.effective_mems;
 	}
 
-	spin_unlock_irq(&callback_lock);
+	raw_spin_unlock_irq(&callback_lock);
 	mutex_unlock(&cpuset_mutex);
 }
 
@@ -2178,12 +2178,12 @@ hotplug_update_tasks_legacy(struct cpuse
 {
 	bool is_empty;
 
-	spin_lock_irq(&callback_lock);
+	raw_spin_lock_irq(&callback_lock);
 	cpumask_copy(cs->cpus_allowed, new_cpus);
 	cpumask_copy(cs->effective_cpus, new_cpus);
 	cs->mems_allowed = *new_mems;
 	cs->effective_mems = *new_mems;
-	spin_unlock_irq(&callback_lock);
+	raw_spin_unlock_irq(&callback_lock);
 
 	/*
 	 * Don't call update_tasks_cpumask() if the cpuset becomes empty,
@@ -2220,10 +2220,10 @@ hotplug_update_tasks(struct cpuset *cs,
 	if (nodes_empty(*new_mems))
 		*new_mems = parent_cs(cs)->effective_mems;
 
-	spin_lock_irq(&callback_lock);
+	raw_spin_lock_irq(&callback_lock);
 	cpumask_copy(cs->effective_cpus, new_cpus);
 	cs->effective_mems = *new_mems;
-	spin_unlock_irq(&callback_lock);
+	raw_spin_unlock_irq(&callback_lock);
 
 	if (cpus_updated)
 		update_tasks_cpumask(cs);
@@ -2309,21 +2309,21 @@ static void cpuset_hotplug_workfn(struct
 
 	/* synchronize cpus_allowed to cpu_active_mask */
 	if (cpus_updated) {
-		spin_lock_irq(&callback_lock);
+		raw_spin_lock_irq(&callback_lock);
 		if (!on_dfl)
 			cpumask_copy(top_cpuset.cpus_allowed, &new_cpus);
 		cpumask_copy(top_cpuset.effective_cpus, &new_cpus);
-		spin_unlock_irq(&callback_lock);
+		raw_spin_unlock_irq(&callback_lock);
 		/* we don't mess with cpumasks of tasks in top_cpuset */
 	}
 
 	/* synchronize mems_allowed to N_MEMORY */
 	if (mems_updated) {
-		spin_lock_irq(&callback_lock);
+		raw_spin_lock_irq(&callback_lock);
 		if (!on_dfl)
 			top_cpuset.mems_allowed = new_mems;
 		top_cpuset.effective_mems = new_mems;
-		spin_unlock_irq(&callback_lock);
+		raw_spin_unlock_irq(&callback_lock);
 		update_tasks_nodemask(&top_cpuset);
 	}
 
@@ -2421,11 +2421,11 @@ void cpuset_cpus_allowed(struct task_str
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&callback_lock, flags);
+	raw_spin_lock_irqsave(&callback_lock, flags);
 	rcu_read_lock();
 	guarantee_online_cpus(task_cs(tsk), pmask);
 	rcu_read_unlock();
-	spin_unlock_irqrestore(&callback_lock, flags);
+	raw_spin_unlock_irqrestore(&callback_lock, flags);
 }
 
 void cpuset_cpus_allowed_fallback(struct task_struct *tsk)
@@ -2473,11 +2473,11 @@ nodemask_t cpuset_mems_allowed(struct ta
 	nodemask_t mask;
 	unsigned long flags;
 
-	spin_lock_irqsave(&callback_lock, flags);
+	raw_spin_lock_irqsave(&callback_lock, flags);
 	rcu_read_lock();
 	guarantee_online_mems(task_cs(tsk), &mask);
 	rcu_read_unlock();
-	spin_unlock_irqrestore(&callback_lock, flags);
+	raw_spin_unlock_irqrestore(&callback_lock, flags);
 
 	return mask;
 }
@@ -2569,14 +2569,14 @@ bool __cpuset_node_allowed(int node, gfp
 		return true;
 
 	/* Not hardwall and node outside mems_allowed: scan up cpusets */
-	spin_lock_irqsave(&callback_lock, flags);
+	raw_spin_lock_irqsave(&callback_lock, flags);
 
 	rcu_read_lock();
 	cs = nearest_hardwall_ancestor(task_cs(current));
 	allowed = node_isset(node, cs->mems_allowed);
 	rcu_read_unlock();
 
-	spin_unlock_irqrestore(&callback_lock, flags);
+	raw_spin_unlock_irqrestore(&callback_lock, flags);
 	return allowed;
 }
 
Index: linux-4.9.20-rt16/kernel/debug/kdb/kdb_io.c
===================================================================
--- linux-4.9.20-rt16.orig/kernel/debug/kdb/kdb_io.c
+++ linux-4.9.20-rt16/kernel/debug/kdb/kdb_io.c
@@ -554,7 +554,6 @@ int vkdb_printf(enum kdb_msgsrc src, con
 	int linecount;
 	int colcount;
 	int logging, saved_loglevel = 0;
-	int saved_trap_printk;
 	int got_printf_lock = 0;
 	int retlen = 0;
 	int fnd, len;
@@ -565,8 +564,6 @@ int vkdb_printf(enum kdb_msgsrc src, con
 	unsigned long uninitialized_var(flags);
 
 	preempt_disable();
-	saved_trap_printk = kdb_trap_printk;
-	kdb_trap_printk = 0;
 
 	/* Serialize kdb_printf if multiple cpus try to write at once.
 	 * But if any cpu goes recursive in kdb, just print the output,
@@ -855,7 +852,6 @@ kdb_print_out:
 	} else {
 		__release(kdb_printf_lock);
 	}
-	kdb_trap_printk = saved_trap_printk;
 	preempt_enable();
 	return retlen;
 }
@@ -865,9 +861,11 @@ int kdb_printf(const char *fmt, ...)
 	va_list ap;
 	int r;
 
+	kdb_trap_printk++;
 	va_start(ap, fmt);
 	r = vkdb_printf(KDB_MSGSRC_INTERNAL, fmt, ap);
 	va_end(ap);
+	kdb_trap_printk--;
 
 	return r;
 }
Index: linux-4.9.20-rt16/kernel/events/core.c
===================================================================
--- linux-4.9.20-rt16.orig/kernel/events/core.c
+++ linux-4.9.20-rt16/kernel/events/core.c
@@ -1050,6 +1050,7 @@ static void __perf_mux_hrtimer_init(stru
 	raw_spin_lock_init(&cpuctx->hrtimer_lock);
 	hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
 	timer->function = perf_mux_hrtimer_handler;
+	timer->irqsafe = 1;
 }
 
 static int perf_mux_hrtimer_restart(struct perf_cpu_context *cpuctx)
@@ -8389,6 +8390,7 @@ static void perf_swevent_init_hrtimer(st
 
 	hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	hwc->hrtimer.function = perf_swevent_hrtimer;
+	hwc->hrtimer.irqsafe = 1;
 
 	/*
 	 * Since hrtimers have a fixed rate, we can do a static freq->period
Index: linux-4.9.20-rt16/kernel/exit.c
===================================================================
--- linux-4.9.20-rt16.orig/kernel/exit.c
+++ linux-4.9.20-rt16/kernel/exit.c
@@ -143,7 +143,7 @@ static void __exit_signal(struct task_st
 	 * Do this under ->siglock, we can race with another thread
 	 * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals.
 	 */
-	flush_sigqueue(&tsk->pending);
+	flush_task_sigqueue(tsk);
 	tsk->sighand = NULL;
 	spin_unlock(&sighand->siglock);
 
Index: linux-4.9.20-rt16/kernel/fork.c
===================================================================
--- linux-4.9.20-rt16.orig/kernel/fork.c
+++ linux-4.9.20-rt16/kernel/fork.c
@@ -76,6 +76,7 @@
 #include <linux/compiler.h>
 #include <linux/sysctl.h>
 #include <linux/kcov.h>
+#include <linux/kprobes.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -376,13 +377,24 @@ static inline void put_signal_struct(str
 	if (atomic_dec_and_test(&sig->sigcnt))
 		free_signal_struct(sig);
 }
-
+#ifdef CONFIG_PREEMPT_RT_BASE
+static
+#endif
 void __put_task_struct(struct task_struct *tsk)
 {
 	WARN_ON(!tsk->exit_state);
 	WARN_ON(atomic_read(&tsk->usage));
 	WARN_ON(tsk == current);
 
+	/*
+	 * Remove function-return probe instances associated with this
+	 * task and put them back on the free list.
+	 */
+	kprobe_flush_task(tsk);
+
+	/* Task is done with its stack. */
+	put_task_stack(tsk);
+
 	cgroup_free(tsk);
 	task_numa_free(tsk);
 	security_task_free(tsk);
@@ -393,7 +405,18 @@ void __put_task_struct(struct task_struc
 	if (!profile_handoff_task(tsk))
 		free_task(tsk);
 }
+#ifndef CONFIG_PREEMPT_RT_BASE
 EXPORT_SYMBOL_GPL(__put_task_struct);
+#else
+void __put_task_struct_cb(struct rcu_head *rhp)
+{
+	struct task_struct *tsk = container_of(rhp, struct task_struct, put_rcu);
+
+	__put_task_struct(tsk);
+
+}
+EXPORT_SYMBOL_GPL(__put_task_struct_cb);
+#endif
 
 void __init __weak arch_task_cache_init(void) { }
 
@@ -535,6 +558,7 @@ static struct task_struct *dup_task_stru
 	tsk->splice_pipe = NULL;
 	tsk->task_frag.page = NULL;
 	tsk->wake_q.next = NULL;
+	tsk->wake_q_sleeper.next = NULL;
 
 	account_kernel_stack(tsk, 1);
 
@@ -853,6 +877,19 @@ void __mmdrop(struct mm_struct *mm)
 }
 EXPORT_SYMBOL_GPL(__mmdrop);
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+/*
+ * RCU callback for delayed mm drop. Not strictly rcu, but we don't
+ * want another facility to make this work.
+ */
+void __mmdrop_delayed(struct rcu_head *rhp)
+{
+	struct mm_struct *mm = container_of(rhp, struct mm_struct, delayed_drop);
+
+	__mmdrop(mm);
+}
+#endif
+
 static inline void __mmput(struct mm_struct *mm)
 {
 	VM_BUG_ON(atomic_read(&mm->mm_users));
@@ -1418,6 +1455,7 @@ static void rt_mutex_init_task(struct ta
 #ifdef CONFIG_RT_MUTEXES
 	p->pi_waiters = RB_ROOT;
 	p->pi_waiters_leftmost = NULL;
+	p->pi_top_task = NULL;
 	p->pi_blocked_on = NULL;
 #endif
 }
@@ -1427,6 +1465,9 @@ static void rt_mutex_init_task(struct ta
  */
 static void posix_cpu_timers_init(struct task_struct *tsk)
 {
+#ifdef CONFIG_PREEMPT_RT_BASE
+	tsk->posix_timer_list = NULL;
+#endif
 	tsk->cputime_expires.prof_exp = 0;
 	tsk->cputime_expires.virt_exp = 0;
 	tsk->cputime_expires.sched_exp = 0;
@@ -1553,6 +1594,7 @@ static __latent_entropy struct task_stru
 	spin_lock_init(&p->alloc_lock);
 
 	init_sigpending(&p->pending);
+	p->sigqueue_cache = NULL;
 
 	p->utime = p->stime = p->gtime = 0;
 	p->utimescaled = p->stimescaled = 0;
Index: linux-4.9.20-rt16/kernel/futex.c
===================================================================
--- linux-4.9.20-rt16.orig/kernel/futex.c
+++ linux-4.9.20-rt16/kernel/futex.c
@@ -801,7 +801,7 @@ static int refill_pi_state_cache(void)
 	return 0;
 }
 
-static struct futex_pi_state * alloc_pi_state(void)
+static struct futex_pi_state *alloc_pi_state(void)
 {
 	struct futex_pi_state *pi_state = current->pi_state_cache;
 
@@ -811,6 +811,11 @@ static struct futex_pi_state * alloc_pi_
 	return pi_state;
 }
 
+static void get_pi_state(struct futex_pi_state *pi_state)
+{
+	WARN_ON_ONCE(!atomic_inc_not_zero(&pi_state->refcount));
+}
+
 /*
  * Drops a reference to the pi_state object and frees or caches it
  * when the last reference is gone.
@@ -855,7 +860,7 @@ static void put_pi_state(struct futex_pi
  * Look up the task based on what TID userspace gave us.
  * We dont trust it.
  */
-static struct task_struct * futex_find_get_task(pid_t pid)
+static struct task_struct *futex_find_get_task(pid_t pid)
 {
 	struct task_struct *p;
 
@@ -905,7 +910,9 @@ void exit_pi_state_list(struct task_stru
 		 * task still owns the PI-state:
 		 */
 		if (head->next != next) {
+			raw_spin_unlock_irq(&curr->pi_lock);
 			spin_unlock(&hb->lock);
+			raw_spin_lock_irq(&curr->pi_lock);
 			continue;
 		}
 
@@ -915,10 +922,12 @@ void exit_pi_state_list(struct task_stru
 		pi_state->owner = NULL;
 		raw_spin_unlock_irq(&curr->pi_lock);
 
-		rt_mutex_unlock(&pi_state->pi_mutex);
-
+		get_pi_state(pi_state);
 		spin_unlock(&hb->lock);
 
+		rt_mutex_futex_unlock(&pi_state->pi_mutex);
+		put_pi_state(pi_state);
+
 		raw_spin_lock_irq(&curr->pi_lock);
 	}
 	raw_spin_unlock_irq(&curr->pi_lock);
@@ -972,6 +981,39 @@ void exit_pi_state_list(struct task_stru
  *
  * [10] There is no transient state which leaves owner and user space
  *	TID out of sync.
+ *
+ *
+ * Serialization and lifetime rules:
+ *
+ * hb->lock:
+ *
+ *	hb -> futex_q, relation
+ *	futex_q -> pi_state, relation
+ *
+ *	(cannot be raw because hb can contain arbitrary amount
+ *	 of futex_q's)
+ *
+ * pi_mutex->wait_lock:
+ *
+ *	{uval, pi_state}
+ *
+ *	(and pi_mutex 'obviously')
+ *
+ * p->pi_lock:
+ *
+ *	p->pi_state_list -> pi_state->list, relation
+ *
+ * pi_state->refcount:
+ *
+ *	pi_state lifetime
+ *
+ *
+ * Lock order:
+ *
+ *   hb->lock
+ *     pi_mutex->wait_lock
+ *       p->pi_lock
+ *
  */
 
 /*
@@ -979,10 +1021,13 @@ void exit_pi_state_list(struct task_stru
  * the pi_state against the user space value. If correct, attach to
  * it.
  */
-static int attach_to_pi_state(u32 uval, struct futex_pi_state *pi_state,
+static int attach_to_pi_state(u32 __user *uaddr, u32 uval,
+			      struct futex_pi_state *pi_state,
 			      struct futex_pi_state **ps)
 {
 	pid_t pid = uval & FUTEX_TID_MASK;
+	u32 uval2;
+	int ret;
 
 	/*
 	 * Userspace might have messed up non-PI and PI futexes [3]
@@ -990,9 +1035,39 @@ static int attach_to_pi_state(u32 uval,
 	if (unlikely(!pi_state))
 		return -EINVAL;
 
+	/*
+	 * We get here with hb->lock held, and having found a
+	 * futex_top_waiter(). This means that futex_lock_pi() of said futex_q
+	 * has dropped the hb->lock in between queue_me() and unqueue_me_pi(),
+	 * which in turn means that futex_lock_pi() still has a reference on
+	 * our pi_state.
+	 *
+	 * The waiter holding a reference on @pi_state also protects against
+	 * the unlocked put_pi_state() in futex_unlock_pi(), futex_lock_pi()
+	 * and futex_wait_requeue_pi() as it cannot go to 0 and consequently
+	 * free pi_state before we can take a reference ourselves.
+	 */
 	WARN_ON(!atomic_read(&pi_state->refcount));
 
 	/*
+	 * Now that we have a pi_state, we can acquire wait_lock
+	 * and do the state validation.
+	 */
+	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+
+	/*
+	 * Since {uval, pi_state} is serialized by wait_lock, and our current
+	 * uval was read without holding it, it can have changed. Verify it
+	 * still is what we expect it to be, otherwise retry the entire
+	 * operation.
+	 */
+	if (get_futex_value_locked(&uval2, uaddr))
+		goto out_efault;
+
+	if (uval != uval2)
+		goto out_eagain;
+
+	/*
 	 * Handle the owner died case:
 	 */
 	if (uval & FUTEX_OWNER_DIED) {
@@ -1007,11 +1082,11 @@ static int attach_to_pi_state(u32 uval,
 			 * is not 0. Inconsistent state. [5]
 			 */
 			if (pid)
-				return -EINVAL;
+				goto out_einval;
 			/*
 			 * Take a ref on the state and return success. [4]
 			 */
-			goto out_state;
+			goto out_attach;
 		}
 
 		/*
@@ -1023,14 +1098,14 @@ static int attach_to_pi_state(u32 uval,
 		 * Take a ref on the state and return success. [6]
 		 */
 		if (!pid)
-			goto out_state;
+			goto out_attach;
 	} else {
 		/*
 		 * If the owner died bit is not set, then the pi_state
 		 * must have an owner. [7]
 		 */
 		if (!pi_state->owner)
-			return -EINVAL;
+			goto out_einval;
 	}
 
 	/*
@@ -1039,11 +1114,29 @@ static int attach_to_pi_state(u32 uval,
 	 * user space TID. [9/10]
 	 */
 	if (pid != task_pid_vnr(pi_state->owner))
-		return -EINVAL;
-out_state:
-	atomic_inc(&pi_state->refcount);
+		goto out_einval;
+
+out_attach:
+	get_pi_state(pi_state);
+	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 	*ps = pi_state;
 	return 0;
+
+out_einval:
+	ret = -EINVAL;
+	goto out_error;
+
+out_eagain:
+	ret = -EAGAIN;
+	goto out_error;
+
+out_efault:
+	ret = -EFAULT;
+	goto out_error;
+
+out_error:
+	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
+	return ret;
 }
 
 /*
@@ -1094,6 +1187,9 @@ static int attach_to_pi_owner(u32 uval,
 
 	/*
 	 * No existing pi state. First waiter. [2]
+	 *
+	 * This creates pi_state, we have hb->lock held, this means nothing can
+	 * observe this state, wait_lock is irrelevant.
 	 */
 	pi_state = alloc_pi_state();
 
@@ -1118,17 +1214,18 @@ static int attach_to_pi_owner(u32 uval,
 	return 0;
 }
 
-static int lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
+static int lookup_pi_state(u32 __user *uaddr, u32 uval,
+			   struct futex_hash_bucket *hb,
 			   union futex_key *key, struct futex_pi_state **ps)
 {
-	struct futex_q *match = futex_top_waiter(hb, key);
+	struct futex_q *top_waiter = futex_top_waiter(hb, key);
 
 	/*
 	 * If there is a waiter on that futex, validate it and
 	 * attach to the pi_state when the validation succeeds.
 	 */
-	if (match)
-		return attach_to_pi_state(uval, match->pi_state, ps);
+	if (top_waiter)
+		return attach_to_pi_state(uaddr, uval, top_waiter->pi_state, ps);
 
 	/*
 	 * We are the first waiter - try to look up the owner based on
@@ -1147,7 +1244,7 @@ static int lock_pi_update_atomic(u32 __u
 	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
 		return -EFAULT;
 
-	/*If user space value changed, let the caller retry */
+	/* If user space value changed, let the caller retry */
 	return curval != uval ? -EAGAIN : 0;
 }
 
@@ -1175,7 +1272,7 @@ static int futex_lock_pi_atomic(u32 __us
 				struct task_struct *task, int set_waiters)
 {
 	u32 uval, newval, vpid = task_pid_vnr(task);
-	struct futex_q *match;
+	struct futex_q *top_waiter;
 	int ret;
 
 	/*
@@ -1201,9 +1298,9 @@ static int futex_lock_pi_atomic(u32 __us
 	 * Lookup existing state first. If it exists, try to attach to
 	 * its pi_state.
 	 */
-	match = futex_top_waiter(hb, key);
-	if (match)
-		return attach_to_pi_state(uval, match->pi_state, ps);
+	top_waiter = futex_top_waiter(hb, key);
+	if (top_waiter)
+		return attach_to_pi_state(uaddr, uval, top_waiter->pi_state, ps);
 
 	/*
 	 * No waiter and user TID is 0. We are here because the
@@ -1284,50 +1381,45 @@ static void mark_wake_futex(struct wake_
 	wake_q_add(wake_q, p);
 	__unqueue_futex(q);
 	/*
-	 * The waiting task can free the futex_q as soon as
-	 * q->lock_ptr = NULL is written, without taking any locks. A
-	 * memory barrier is required here to prevent the following
-	 * store to lock_ptr from getting ahead of the plist_del.
+	 * The waiting task can free the futex_q as soon as q->lock_ptr = NULL
+	 * is written, without taking any locks. This is possible in the event
+	 * of a spurious wakeup, for example. A memory barrier is required here
+	 * to prevent the following store to lock_ptr from getting ahead of the
+	 * plist_del in __unqueue_futex().
 	 */
-	smp_wmb();
-	q->lock_ptr = NULL;
+	smp_store_release(&q->lock_ptr, NULL);
 }
 
-static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
-			 struct futex_hash_bucket *hb)
+/*
+ * Caller must hold a reference on @pi_state.
+ */
+static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_state)
 {
-	struct task_struct *new_owner;
-	struct futex_pi_state *pi_state = this->pi_state;
 	u32 uninitialized_var(curval), newval;
+	struct task_struct *new_owner;
+	bool postunlock = false;
 	WAKE_Q(wake_q);
-	bool deboost;
+	WAKE_Q(wake_sleeper_q);
 	int ret = 0;
 
-	if (!pi_state)
-		return -EINVAL;
-
-	/*
-	 * If current does not own the pi_state then the futex is
-	 * inconsistent and user space fiddled with the futex value.
-	 */
-	if (pi_state->owner != current)
-		return -EINVAL;
-
-	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 	new_owner = rt_mutex_next_owner(&pi_state->pi_mutex);
+	if (WARN_ON_ONCE(!new_owner)) {
+		/*
+		 * As per the comment in futex_unlock_pi() this should not happen.
+		 *
+		 * When this happens, give up our locks and try again, giving
+		 * the futex_lock_pi() instance time to complete, either by
+		 * waiting on the rtmutex or removing itself from the futex
+		 * queue.
+		 */
+		ret = -EAGAIN;
+		goto out_unlock;
+	}
 
 	/*
-	 * It is possible that the next waiter (the one that brought
-	 * this owner to the kernel) timed out and is no longer
-	 * waiting on the lock.
-	 */
-	if (!new_owner)
-		new_owner = this->task;
-
-	/*
-	 * We pass it to the next owner. The WAITERS bit is always
-	 * kept enabled while there is PI state around. We cleanup the
-	 * owner died bit, because we are the owner.
+	 * We pass it to the next owner. The WAITERS bit is always kept
+	 * enabled while there is PI state around. We cleanup the owner
+	 * died bit, because we are the owner.
 	 */
 	newval = FUTEX_WAITERS | task_pid_vnr(new_owner);
 
@@ -1336,6 +1428,7 @@ static int wake_futex_pi(u32 __user *uad
 
 	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)) {
 		ret = -EFAULT;
+
 	} else if (curval != uval) {
 		/*
 		 * If a unconditional UNLOCK_PI operation (user space did not
@@ -1348,10 +1441,14 @@ static int wake_futex_pi(u32 __user *uad
 		else
 			ret = -EINVAL;
 	}
-	if (ret) {
-		raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
-		return ret;
-	}
+
+	if (ret)
+		goto out_unlock;
+
+	/*
+	 * This is a point of no return; once we modify the uval there is no
+	 * going back and subsequent operations must not fail.
+	 */
 
 	raw_spin_lock(&pi_state->owner->pi_lock);
 	WARN_ON(list_empty(&pi_state->list));
@@ -1364,22 +1461,15 @@ static int wake_futex_pi(u32 __user *uad
 	pi_state->owner = new_owner;
 	raw_spin_unlock(&new_owner->pi_lock);
 
+	postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q,
+					     &wake_sleeper_q);
+out_unlock:
 	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 
-	deboost = rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q);
+	if (postunlock)
+		rt_mutex_postunlock(&wake_q, &wake_sleeper_q);
 
-	/*
-	 * First unlock HB so the waiter does not spin on it once he got woken
-	 * up. Second wake up the waiter before the priority is adjusted. If we
-	 * deboost first (and lose our higher priority), then the task might get
-	 * scheduled away before the wake up can take place.
-	 */
-	spin_unlock(&hb->lock);
-	wake_up_q(&wake_q);
-	if (deboost)
-		rt_mutex_adjust_prio(current);
-
-	return 0;
+	return ret;
 }
 
 /*
@@ -1825,7 +1915,7 @@ retry_private:
 			 * If that call succeeds then we have pi_state and an
 			 * initial refcount on it.
 			 */
-			ret = lookup_pi_state(ret, hb2, &key2, &pi_state);
+			ret = lookup_pi_state(uaddr2, ret, hb2, &key2, &pi_state);
 		}
 
 		switch (ret) {
@@ -1908,7 +1998,7 @@ retry_private:
 			 * refcount on the pi_state and store the pointer in
 			 * the futex_q object of the waiter.
 			 */
-			atomic_inc(&pi_state->refcount);
+			get_pi_state(pi_state);
 			this->pi_state = pi_state;
 			ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex,
 							this->rt_waiter,
@@ -1925,6 +2015,16 @@ retry_private:
 				requeue_pi_wake_futex(this, &key2, hb2);
 				drop_count++;
 				continue;
+			} else if (ret == -EAGAIN) {
+				/*
+				 * Waiter was woken by timeout or
+				 * signal and has set pi_blocked_on to
+				 * PI_WAKEUP_INPROGRESS before we
+				 * tried to enqueue it on the rtmutex.
+				 */
+				this->pi_state = NULL;
+				put_pi_state(pi_state);
+				continue;
 			} else if (ret) {
 				/*
 				 * rt_mutex_start_proxy_lock() detected a
@@ -2008,20 +2108,7 @@ queue_unlock(struct futex_hash_bucket *h
 	hb_waiters_dec(hb);
 }
 
-/**
- * queue_me() - Enqueue the futex_q on the futex_hash_bucket
- * @q:	The futex_q to enqueue
- * @hb:	The destination hash bucket
- *
- * The hb->lock must be held by the caller, and is released here. A call to
- * queue_me() is typically paired with exactly one call to unqueue_me().  The
- * exceptions involve the PI related operations, which may use unqueue_me_pi()
- * or nothing if the unqueue is done as part of the wake process and the unqueue
- * state is implicit in the state of woken task (see futex_wait_requeue_pi() for
- * an example).
- */
-static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
-	__releases(&hb->lock)
+static inline void __queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
 {
 	int prio;
 
@@ -2038,6 +2125,24 @@ static inline void queue_me(struct futex
 	plist_node_init(&q->list, prio);
 	plist_add(&q->list, &hb->chain);
 	q->task = current;
+}
+
+/**
+ * queue_me() - Enqueue the futex_q on the futex_hash_bucket
+ * @q:	The futex_q to enqueue
+ * @hb:	The destination hash bucket
+ *
+ * The hb->lock must be held by the caller, and is released here. A call to
+ * queue_me() is typically paired with exactly one call to unqueue_me().  The
+ * exceptions involve the PI related operations, which may use unqueue_me_pi()
+ * or nothing if the unqueue is done as part of the wake process and the unqueue
+ * state is implicit in the state of woken task (see futex_wait_requeue_pi() for
+ * an example).
+ */
+static inline void queue_me(struct futex_q *q, struct futex_hash_bucket *hb)
+	__releases(&hb->lock)
+{
+	__queue_me(q, hb);
 	spin_unlock(&hb->lock);
 }
 
@@ -2124,10 +2229,13 @@ static int fixup_pi_state_owner(u32 __us
 {
 	u32 newtid = task_pid_vnr(newowner) | FUTEX_WAITERS;
 	struct futex_pi_state *pi_state = q->pi_state;
-	struct task_struct *oldowner = pi_state->owner;
 	u32 uval, uninitialized_var(curval), newval;
+	struct task_struct *oldowner;
 	int ret;
 
+	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+
+	oldowner = pi_state->owner;
 	/* Owner died? */
 	if (!pi_state->owner)
 		newtid |= FUTEX_OWNER_DIED;
@@ -2135,7 +2243,8 @@ static int fixup_pi_state_owner(u32 __us
 	/*
 	 * We are here either because we stole the rtmutex from the
 	 * previous highest priority waiter or we are the highest priority
-	 * waiter but failed to get the rtmutex the first time.
+	 * waiter but have failed to get the rtmutex the first time.
+	 *
 	 * We have to replace the newowner TID in the user space variable.
 	 * This must be atomic as we have to preserve the owner died bit here.
 	 *
@@ -2143,17 +2252,16 @@ static int fixup_pi_state_owner(u32 __us
 	 * because we can fault here. Imagine swapped out pages or a fork
 	 * that marked all the anonymous memory readonly for cow.
 	 *
-	 * Modifying pi_state _before_ the user space value would
-	 * leave the pi_state in an inconsistent state when we fault
-	 * here, because we need to drop the hash bucket lock to
-	 * handle the fault. This might be observed in the PID check
-	 * in lookup_pi_state.
+	 * Modifying pi_state _before_ the user space value would leave the
+	 * pi_state in an inconsistent state when we fault here, because we
+	 * need to drop the locks to handle the fault. This might be observed
+	 * in the PID check in lookup_pi_state.
 	 */
 retry:
 	if (get_futex_value_locked(&uval, uaddr))
 		goto handle_fault;
 
-	while (1) {
+	for (;;) {
 		newval = (uval & FUTEX_OWNER_DIED) | newtid;
 
 		if (cmpxchg_futex_value_locked(&curval, uaddr, uval, newval))
@@ -2168,47 +2276,60 @@ retry:
 	 * itself.
 	 */
 	if (pi_state->owner != NULL) {
-		raw_spin_lock_irq(&pi_state->owner->pi_lock);
+		raw_spin_lock(&pi_state->owner->pi_lock);
 		WARN_ON(list_empty(&pi_state->list));
 		list_del_init(&pi_state->list);
-		raw_spin_unlock_irq(&pi_state->owner->pi_lock);
+		raw_spin_unlock(&pi_state->owner->pi_lock);
 	}
 
 	pi_state->owner = newowner;
 
-	raw_spin_lock_irq(&newowner->pi_lock);
+	raw_spin_lock(&newowner->pi_lock);
 	WARN_ON(!list_empty(&pi_state->list));
 	list_add(&pi_state->list, &newowner->pi_state_list);
-	raw_spin_unlock_irq(&newowner->pi_lock);
+	raw_spin_unlock(&newowner->pi_lock);
+	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
+
 	return 0;
 
 	/*
-	 * To handle the page fault we need to drop the hash bucket
-	 * lock here. That gives the other task (either the highest priority
-	 * waiter itself or the task which stole the rtmutex) the
-	 * chance to try the fixup of the pi_state. So once we are
-	 * back from handling the fault we need to check the pi_state
-	 * after reacquiring the hash bucket lock and before trying to
-	 * do another fixup. When the fixup has been done already we
-	 * simply return.
+	 * To handle the page fault we need to drop the locks here. That gives
+	 * the other task (either the highest priority waiter itself or the
+	 * task which stole the rtmutex) the chance to try the fixup of the
+	 * pi_state. So once we are back from handling the fault we need to
+	 * check the pi_state after reacquiring the locks and before trying to
+	 * do another fixup. When the fixup has been done already we simply
+	 * return.
+	 *
+	 * Note: we hold both hb->lock and pi_mutex->wait_lock. We can safely
+	 * drop hb->lock since the caller owns the hb -> futex_q relation.
+	 * Dropping the pi_mutex->wait_lock requires the state revalidate.
 	 */
 handle_fault:
+	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 	spin_unlock(q->lock_ptr);
 
 	ret = fault_in_user_writeable(uaddr);
 
 	spin_lock(q->lock_ptr);
+	raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
 
 	/*
 	 * Check if someone else fixed it for us:
 	 */
-	if (pi_state->owner != oldowner)
-		return 0;
+	if (pi_state->owner != oldowner) {
+		ret = 0;
+		goto out_unlock;
+	}
 
 	if (ret)
-		return ret;
+		goto out_unlock;
 
 	goto retry;
+
+out_unlock:
+	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
+	return ret;
 }
 
 static long futex_wait_restart(struct restart_block *restart);
@@ -2230,13 +2351,16 @@ static long futex_wait_restart(struct re
  */
 static int fixup_owner(u32 __user *uaddr, struct futex_q *q, int locked)
 {
-	struct task_struct *owner;
 	int ret = 0;
 
 	if (locked) {
 		/*
 		 * Got the lock. We might not be the anticipated owner if we
 		 * did a lock-steal - fix up the PI-state in that case:
+		 *
+		 * We can safely read pi_state->owner without holding wait_lock
+		 * because we now own the rt_mutex, only the owner will attempt
+		 * to change it.
 		 */
 		if (q->pi_state->owner != current)
 			ret = fixup_pi_state_owner(uaddr, q, current);
@@ -2244,43 +2368,15 @@ static int fixup_owner(u32 __user *uaddr
 	}
 
 	/*
-	 * Catch the rare case, where the lock was released when we were on the
-	 * way back before we locked the hash bucket.
-	 */
-	if (q->pi_state->owner == current) {
-		/*
-		 * Try to get the rt_mutex now. This might fail as some other
-		 * task acquired the rt_mutex after we removed ourself from the
-		 * rt_mutex waiters list.
-		 */
-		if (rt_mutex_trylock(&q->pi_state->pi_mutex)) {
-			locked = 1;
-			goto out;
-		}
-
-		/*
-		 * pi_state is incorrect, some other task did a lock steal and
-		 * we returned due to timeout or signal without taking the
-		 * rt_mutex. Too late.
-		 */
-		raw_spin_lock_irq(&q->pi_state->pi_mutex.wait_lock);
-		owner = rt_mutex_owner(&q->pi_state->pi_mutex);
-		if (!owner)
-			owner = rt_mutex_next_owner(&q->pi_state->pi_mutex);
-		raw_spin_unlock_irq(&q->pi_state->pi_mutex.wait_lock);
-		ret = fixup_pi_state_owner(uaddr, q, owner);
-		goto out;
-	}
-
-	/*
 	 * Paranoia check. If we did not take the lock, then we should not be
 	 * the owner of the rt_mutex.
 	 */
-	if (rt_mutex_owner(&q->pi_state->pi_mutex) == current)
+	if (rt_mutex_owner(&q->pi_state->pi_mutex) == current) {
 		printk(KERN_ERR "fixup_owner: ret = %d pi-mutex: %p "
 				"pi-state %p\n", ret,
 				q->pi_state->pi_mutex.owner,
 				q->pi_state->owner);
+	}
 
 out:
 	return ret ? ret : locked;
@@ -2504,6 +2600,8 @@ static int futex_lock_pi(u32 __user *uad
 			 ktime_t *time, int trylock)
 {
 	struct hrtimer_sleeper timeout, *to = NULL;
+	struct futex_pi_state *pi_state = NULL;
+	struct rt_mutex_waiter rt_waiter;
 	struct futex_hash_bucket *hb;
 	struct futex_q q = futex_q_init;
 	int res, ret;
@@ -2556,25 +2654,77 @@ retry_private:
 		}
 	}
 
+	WARN_ON(!q.pi_state);
+
 	/*
 	 * Only actually queue now that the atomic ops are done:
 	 */
-	queue_me(&q, hb);
+	__queue_me(&q, hb);
 
-	WARN_ON(!q.pi_state);
-	/*
-	 * Block on the PI mutex:
-	 */
-	if (!trylock) {
-		ret = rt_mutex_timed_futex_lock(&q.pi_state->pi_mutex, to);
-	} else {
-		ret = rt_mutex_trylock(&q.pi_state->pi_mutex);
+	if (trylock) {
+		ret = rt_mutex_futex_trylock(&q.pi_state->pi_mutex);
 		/* Fixup the trylock return value: */
 		ret = ret ? 0 : -EWOULDBLOCK;
+		goto no_block;
 	}
 
+	rt_mutex_init_waiter(&rt_waiter, false);
+
+	/*
+	 * On PREEMPT_RT_FULL, when hb->lock becomes an rt_mutex, we must not
+	 * hold it while doing rt_mutex_start_proxy(), because then it will
+	 * include hb->lock in the blocking chain, even through we'll not in
+	 * fact hold it while blocking. This will lead it to report -EDEADLK
+	 * and BUG when futex_unlock_pi() interleaves with this.
+	 *
+	 * Therefore acquire wait_lock while holding hb->lock, but drop the
+	 * latter before calling rt_mutex_start_proxy_lock(). This still fully
+	 * serializes against futex_unlock_pi() as that does the exact same
+	 * lock handoff sequence.
+	 */
+	raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock);
+	/*
+	 * the migrate_disable() here disables migration in the in_atomic() fast
+	 * path which is enabled again in the following spin_unlock(). We have
+	 * one migrate_disable() pending in the slow-path which is reversed
+	 * after the raw_spin_unlock_irq() where we leave the atomic context.
+	 */
+	migrate_disable();
+
+	spin_unlock(q.lock_ptr);
+	ret = __rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current);
+	raw_spin_unlock_irq(&q.pi_state->pi_mutex.wait_lock);
+	migrate_enable();
+
+	if (ret) {
+		if (ret == 1)
+			ret = 0;
+
+		spin_lock(q.lock_ptr);
+		goto no_block;
+	}
+
+
+	if (unlikely(to))
+		hrtimer_start_expires(&to->timer, HRTIMER_MODE_ABS);
+
+	ret = rt_mutex_wait_proxy_lock(&q.pi_state->pi_mutex, to, &rt_waiter);
+
 	spin_lock(q.lock_ptr);
 	/*
+	 * If we failed to acquire the lock (signal/timeout), we must
+	 * first acquire the hb->lock before removing the lock from the
+	 * rt_mutex waitqueue, such that we can keep the hb and rt_mutex
+	 * wait lists consistent.
+	 *
+	 * In particular; it is important that futex_unlock_pi() can not
+	 * observe this inconsistency.
+	 */
+	if (ret && !rt_mutex_cleanup_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter))
+		ret = 0;
+
+no_block:
+	/*
 	 * Fixup the pi_state owner and possibly acquire the lock if we
 	 * haven't already.
 	 */
@@ -2590,12 +2740,19 @@ retry_private:
 	 * If fixup_owner() faulted and was unable to handle the fault, unlock
 	 * it and return the fault to userspace.
 	 */
-	if (ret && (rt_mutex_owner(&q.pi_state->pi_mutex) == current))
-		rt_mutex_unlock(&q.pi_state->pi_mutex);
+	if (ret && (rt_mutex_owner(&q.pi_state->pi_mutex) == current)) {
+		pi_state = q.pi_state;
+		get_pi_state(pi_state);
+	}
 
 	/* Unqueue and drop the lock */
 	unqueue_me_pi(&q);
 
+	if (pi_state) {
+		rt_mutex_futex_unlock(&pi_state->pi_mutex);
+		put_pi_state(pi_state);
+	}
+
 	goto out_put_key;
 
 out_unlock_put_key:
@@ -2604,8 +2761,10 @@ out_unlock_put_key:
 out_put_key:
 	put_futex_key(&q.key);
 out:
-	if (to)
+	if (to) {
+		hrtimer_cancel(&to->timer);
 		destroy_hrtimer_on_stack(&to->timer);
+	}
 	return ret != -EINTR ? ret : -ERESTARTNOINTR;
 
 uaddr_faulted:
@@ -2632,7 +2791,7 @@ static int futex_unlock_pi(u32 __user *u
 	u32 uninitialized_var(curval), uval, vpid = task_pid_vnr(current);
 	union futex_key key = FUTEX_KEY_INIT;
 	struct futex_hash_bucket *hb;
-	struct futex_q *match;
+	struct futex_q *top_waiter;
 	int ret;
 
 retry:
@@ -2656,12 +2815,48 @@ retry:
 	 * all and we at least want to know if user space fiddled
 	 * with the futex value instead of blindly unlocking.
 	 */
-	match = futex_top_waiter(hb, &key);
-	if (match) {
-		ret = wake_futex_pi(uaddr, uval, match, hb);
+	top_waiter = futex_top_waiter(hb, &key);
+	if (top_waiter) {
+		struct futex_pi_state *pi_state = top_waiter->pi_state;
+
+		ret = -EINVAL;
+		if (!pi_state)
+			goto out_unlock;
+
 		/*
-		 * In case of success wake_futex_pi dropped the hash
-		 * bucket lock.
+		 * If current does not own the pi_state then the futex is
+		 * inconsistent and user space fiddled with the futex value.
+		 */
+		if (pi_state->owner != current)
+			goto out_unlock;
+
+		get_pi_state(pi_state);
+		/*
+		 * By taking wait_lock while still holding hb->lock, we ensure
+		 * there is no point where we hold neither; and therefore
+		 * wake_futex_pi() must observe a state consistent with what we
+		 * observed.
+		 */
+		raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+		/*
+		 * Magic trickery for now to make the RT migrate disable
+		 * logic happy. The following spin_unlock() happens with
+		 * interrupts disabled so the internal migrate_enable()
+		 * won't undo the migrate_disable() which was issued when
+		 * locking hb->lock.
+		 */
+		migrate_disable();
+		spin_unlock(&hb->lock);
+
+		/* Drops pi_state->pi_mutex.wait_lock */
+		ret = wake_futex_pi(uaddr, uval, pi_state);
+
+		migrate_enable();
+
+		put_pi_state(pi_state);
+
+		/*
+		 * Success, we're done! No tricky corner cases.
 		 */
 		if (!ret)
 			goto out_putkey;
@@ -2676,7 +2871,6 @@ retry:
 		 * setting the FUTEX_WAITERS bit. Try again.
 		 */
 		if (ret == -EAGAIN) {
-			spin_unlock(&hb->lock);
 			put_futex_key(&key);
 			goto retry;
 		}
@@ -2684,7 +2878,7 @@ retry:
 		 * wake_futex_pi has detected invalid state. Tell user
 		 * space.
 		 */
-		goto out_unlock;
+		goto out_putkey;
 	}
 
 	/*
@@ -2694,8 +2888,10 @@ retry:
 	 * preserve the WAITERS bit not the OWNER_DIED one. We are the
 	 * owner.
 	 */
-	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, 0))
+	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, 0)) {
+		spin_unlock(&hb->lock);
 		goto pi_faulted;
+	}
 
 	/*
 	 * If uval has changed, let user space handle it.
@@ -2709,7 +2905,6 @@ out_putkey:
 	return ret;
 
 pi_faulted:
-	spin_unlock(&hb->lock);
 	put_futex_key(&key);
 
 	ret = fault_in_user_writeable(uaddr);
@@ -2813,8 +3008,9 @@ static int futex_wait_requeue_pi(u32 __u
 				 u32 __user *uaddr2)
 {
 	struct hrtimer_sleeper timeout, *to = NULL;
+	struct futex_pi_state *pi_state = NULL;
 	struct rt_mutex_waiter rt_waiter;
-	struct futex_hash_bucket *hb;
+	struct futex_hash_bucket *hb, *hb2;
 	union futex_key key2 = FUTEX_KEY_INIT;
 	struct futex_q q = futex_q_init;
 	int res, ret;
@@ -2839,10 +3035,7 @@ static int futex_wait_requeue_pi(u32 __u
 	 * The waiter is allocated on our stack, manipulated by the requeue
 	 * code while we sleep on uaddr.
 	 */
-	debug_rt_mutex_init_waiter(&rt_waiter);
-	RB_CLEAR_NODE(&rt_waiter.pi_tree_entry);
-	RB_CLEAR_NODE(&rt_waiter.tree_entry);
-	rt_waiter.task = NULL;
+	rt_mutex_init_waiter(&rt_waiter, false);
 
 	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE);
 	if (unlikely(ret != 0))
@@ -2873,20 +3066,55 @@ static int futex_wait_requeue_pi(u32 __u
 	/* Queue the futex_q, drop the hb lock, wait for wakeup. */
 	futex_wait_queue_me(hb, &q, to);
 
-	spin_lock(&hb->lock);
-	ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to);
-	spin_unlock(&hb->lock);
-	if (ret)
-		goto out_put_keys;
+	/*
+	 * On RT we must avoid races with requeue and trying to block
+	 * on two mutexes (hb->lock and uaddr2's rtmutex) by
+	 * serializing access to pi_blocked_on with pi_lock.
+	 */
+	raw_spin_lock_irq(&current->pi_lock);
+	if (current->pi_blocked_on) {
+		/*
+		 * We have been requeued or are in the process of
+		 * being requeued.
+		 */
+		raw_spin_unlock_irq(&current->pi_lock);
+	} else {
+		/*
+		 * Setting pi_blocked_on to PI_WAKEUP_INPROGRESS
+		 * prevents a concurrent requeue from moving us to the
+		 * uaddr2 rtmutex. After that we can safely acquire
+		 * (and possibly block on) hb->lock.
+		 */
+		current->pi_blocked_on = PI_WAKEUP_INPROGRESS;
+		raw_spin_unlock_irq(&current->pi_lock);
+
+		spin_lock(&hb->lock);
+
+		/*
+		 * Clean up pi_blocked_on. We might leak it otherwise
+		 * when we succeeded with the hb->lock in the fast
+		 * path.
+		 */
+		raw_spin_lock_irq(&current->pi_lock);
+		current->pi_blocked_on = NULL;
+		raw_spin_unlock_irq(&current->pi_lock);
+
+		ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to);
+		spin_unlock(&hb->lock);
+		if (ret)
+			goto out_put_keys;
+	}
 
 	/*
-	 * In order for us to be here, we know our q.key == key2, and since
-	 * we took the hb->lock above, we also know that futex_requeue() has
-	 * completed and we no longer have to concern ourselves with a wakeup
-	 * race with the atomic proxy lock acquisition by the requeue code. The
-	 * futex_requeue dropped our key1 reference and incremented our key2
-	 * reference count.
+	 * In order to be here, we have either been requeued, are in
+	 * the process of being requeued, or requeue successfully
+	 * acquired uaddr2 on our behalf.  If pi_blocked_on was
+	 * non-null above, we may be racing with a requeue.  Do not
+	 * rely on q->lock_ptr to be hb2->lock until after blocking on
+	 * hb->lock or hb2->lock. The futex_requeue dropped our key1
+	 * reference and incremented our key2 reference count.
 	 */
+	hb2 = hash_futex(&key2);
 
 	/* Check if the requeue code acquired the second futex for us. */
 	if (!q.rt_waiter) {
@@ -2895,16 +3123,19 @@ static int futex_wait_requeue_pi(u32 __u
 		 * did a lock-steal - fix up the PI-state in that case.
 		 */
 		if (q.pi_state && (q.pi_state->owner != current)) {
-			spin_lock(q.lock_ptr);
+			spin_lock(&hb2->lock);
+			BUG_ON(&hb2->lock != q.lock_ptr);
 			ret = fixup_pi_state_owner(uaddr2, &q, current);
-			if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current)
-				rt_mutex_unlock(&q.pi_state->pi_mutex);
+			if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) {
+				pi_state = q.pi_state;
+				get_pi_state(pi_state);
+			}
 			/*
 			 * Drop the reference to the pi state which
 			 * the requeue_pi() code acquired for us.
 			 */
 			put_pi_state(q.pi_state);
-			spin_unlock(q.lock_ptr);
+			spin_unlock(&hb2->lock);
 		}
 	} else {
 		struct rt_mutex *pi_mutex;
@@ -2916,10 +3147,14 @@ static int futex_wait_requeue_pi(u32 __u
 		 */
 		WARN_ON(!q.pi_state);
 		pi_mutex = &q.pi_state->pi_mutex;
-		ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter);
-		debug_rt_mutex_free_waiter(&rt_waiter);
+		ret = rt_mutex_wait_proxy_lock(pi_mutex, to, &rt_waiter);
 
-		spin_lock(q.lock_ptr);
+		spin_lock(&hb2->lock);
+		BUG_ON(&hb2->lock != q.lock_ptr);
+		if (ret && !rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter))
+			ret = 0;
+
+		debug_rt_mutex_free_waiter(&rt_waiter);
 		/*
 		 * Fixup the pi_state owner and possibly acquire the lock if we
 		 * haven't already.
@@ -2937,13 +3172,20 @@ static int futex_wait_requeue_pi(u32 __u
 		 * the fault, unlock the rt_mutex and return the fault to
 		 * userspace.
 		 */
-		if (ret && rt_mutex_owner(pi_mutex) == current)
-			rt_mutex_unlock(pi_mutex);
+		if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) {
+			pi_state = q.pi_state;
+			get_pi_state(pi_state);
+		}
 
 		/* Unqueue and drop the lock. */
 		unqueue_me_pi(&q);
 	}
 
+	if (pi_state) {
+		rt_mutex_futex_unlock(&pi_state->pi_mutex);
+		put_pi_state(pi_state);
+	}
+
 	if (ret == -EINTR) {
 		/*
 		 * We've already been requeued, but cannot restart by calling
Index: linux-4.9.20-rt16/kernel/irq/handle.c
===================================================================
--- linux-4.9.20-rt16.orig/kernel/irq/handle.c
+++ linux-4.9.20-rt16/kernel/irq/handle.c
@@ -181,10 +181,16 @@ irqreturn_t handle_irq_event_percpu(stru
 {
 	irqreturn_t retval;
 	unsigned int flags = 0;
+	struct pt_regs *regs = get_irq_regs();
+	u64 ip = regs ? instruction_pointer(regs) : 0;
 
 	retval = __handle_irq_event_percpu(desc, &flags);
 
-	add_interrupt_randomness(desc->irq_data.irq, flags);
+#ifdef CONFIG_PREEMPT_RT_FULL
+	desc->random_ip = ip;
+#else
+	add_interrupt_randomness(desc->irq_data.irq, flags, ip);
+#endif
 
 	if (!noirqdebug)
 		note_interrupt(desc, retval);
Index: linux-4.9.20-rt16/kernel/irq/manage.c
===================================================================
--- linux-4.9.20-rt16.orig/kernel/irq/manage.c
+++ linux-4.9.20-rt16/kernel/irq/manage.c
@@ -22,6 +22,7 @@
 #include "internals.h"
 
 #ifdef CONFIG_IRQ_FORCED_THREADING
+# ifndef CONFIG_PREEMPT_RT_BASE
 __read_mostly bool force_irqthreads;
 
 static int __init setup_forced_irqthreads(char *arg)
@@ -30,6 +31,7 @@ static int __init setup_forced_irqthread
 	return 0;
 }
 early_param("threadirqs", setup_forced_irqthreads);
+# endif
 #endif
 
 static void __synchronize_hardirq(struct irq_desc *desc)
@@ -233,7 +235,12 @@ int irq_set_affinity_locked(struct irq_d
 
 	if (desc->affinity_notify) {
 		kref_get(&desc->affinity_notify->kref);
+
+#ifdef CONFIG_PREEMPT_RT_BASE
+		swork_queue(&desc->affinity_notify->swork);
+#else
 		schedule_work(&desc->affinity_notify->work);
+#endif
 	}
 	irqd_set(data, IRQD_AFFINITY_SET);
 
@@ -271,10 +278,8 @@ int irq_set_affinity_hint(unsigned int i
 }
 EXPORT_SYMBOL_GPL(irq_set_affinity_hint);
 
-static void irq_affinity_notify(struct work_struct *work)
+static void _irq_affinity_notify(struct irq_affinity_notify *notify)
 {
-	struct irq_affinity_notify *notify =
-		container_of(work, struct irq_affinity_notify, work);
 	struct irq_desc *desc = irq_to_desc(notify->irq);
 	cpumask_var_t cpumask;
 	unsigned long flags;
@@ -296,6 +301,35 @@ out:
 	kref_put(&notify->kref, notify->release);
 }
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+static void init_helper_thread(void)
+{
+	static int init_sworker_once;
+
+	if (init_sworker_once)
+		return;
+	if (WARN_ON(swork_get()))
+		return;
+	init_sworker_once = 1;
+}
+
+static void irq_affinity_notify(struct swork_event *swork)
+{
+	struct irq_affinity_notify *notify =
+		container_of(swork, struct irq_affinity_notify, swork);
+	_irq_affinity_notify(notify);
+}
+
+#else
+
+static void irq_affinity_notify(struct work_struct *work)
+{
+	struct irq_affinity_notify *notify =
+		container_of(work, struct irq_affinity_notify, work);
+	_irq_affinity_notify(notify);
+}
+#endif
+
 /**
  *	irq_set_affinity_notifier - control notification of IRQ affinity changes
  *	@irq:		Interrupt for which to enable/disable notification
@@ -324,7 +358,12 @@ irq_set_affinity_notifier(unsigned int i
 	if (notify) {
 		notify->irq = irq;
 		kref_init(&notify->kref);
+#ifdef CONFIG_PREEMPT_RT_BASE
+		INIT_SWORK(&notify->swork, irq_affinity_notify);
+		init_helper_thread();
+#else
 		INIT_WORK(&notify->work, irq_affinity_notify);
+#endif
 	}
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
@@ -879,7 +918,15 @@ irq_forced_thread_fn(struct irq_desc *de
 	local_bh_disable();
 	ret = action->thread_fn(action->irq, action->dev_id);
 	irq_finalize_oneshot(desc, action);
-	local_bh_enable();
+	/*
+	 * Interrupts which have real time requirements can be set up
+	 * to avoid softirq processing in the thread handler. This is
+	 * safe as these interrupts do not raise soft interrupts.
+	 */
+	if (irq_settings_no_softirq_call(desc))
+		_local_bh_enable();
+	else
+		local_bh_enable();
 	return ret;
 }
 
@@ -976,6 +1023,12 @@ static int irq_thread(void *data)
 		if (action_ret == IRQ_WAKE_THREAD)
 			irq_wake_secondary(desc, action);
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+		migrate_disable();
+		add_interrupt_randomness(action->irq, 0,
+				 desc->random_ip ^ (unsigned long) action);
+		migrate_enable();
+#endif
 		wake_threads_waitq(desc);
 	}
 
@@ -1338,6 +1391,9 @@ __setup_irq(unsigned int irq, struct irq
 			irqd_set(&desc->irq_data, IRQD_NO_BALANCING);
 		}
 
+		if (new->flags & IRQF_NO_SOFTIRQ_CALL)
+			irq_settings_set_no_softirq_call(desc);
+
 		/* Set default affinity mask once everything is setup */
 		setup_affinity(desc, mask);
 
@@ -2063,7 +2119,7 @@ EXPORT_SYMBOL_GPL(irq_get_irqchip_state)
  *	This call sets the internal irqchip state of an interrupt,
  *	depending on the value of @which.
  *
- *	This function should be called with preemption disabled if the
+ *	This function should be called with migration disabled if the
  *	interrupt controller has per-cpu registers.
  */
 int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which,
Index: linux-4.9.20-rt16/kernel/irq/settings.h
===================================================================
--- linux-4.9.20-rt16.orig/kernel/irq/settings.h
+++ linux-4.9.20-rt16/kernel/irq/settings.h
@@ -16,6 +16,7 @@ enum {
 	_IRQ_PER_CPU_DEVID	= IRQ_PER_CPU_DEVID,
 	_IRQ_IS_POLLED		= IRQ_IS_POLLED,
 	_IRQ_DISABLE_UNLAZY	= IRQ_DISABLE_UNLAZY,
+	_IRQ_NO_SOFTIRQ_CALL	= IRQ_NO_SOFTIRQ_CALL,
 	_IRQF_MODIFY_MASK	= IRQF_MODIFY_MASK,
 };
 
@@ -30,6 +31,7 @@ enum {
 #define IRQ_PER_CPU_DEVID	GOT_YOU_MORON
 #define IRQ_IS_POLLED		GOT_YOU_MORON
 #define IRQ_DISABLE_UNLAZY	GOT_YOU_MORON
+#define IRQ_NO_SOFTIRQ_CALL	GOT_YOU_MORON
 #undef IRQF_MODIFY_MASK
 #define IRQF_MODIFY_MASK	GOT_YOU_MORON
 
@@ -40,6 +42,16 @@ irq_settings_clr_and_set(struct irq_desc
 	desc->status_use_accessors |= (set & _IRQF_MODIFY_MASK);
 }
 
+static inline bool irq_settings_no_softirq_call(struct irq_desc *desc)
+{
+	return desc->status_use_accessors & _IRQ_NO_SOFTIRQ_CALL;
+}
+
+static inline void irq_settings_set_no_softirq_call(struct irq_desc *desc)
+{
+	desc->status_use_accessors |= _IRQ_NO_SOFTIRQ_CALL;
+}
+
 static inline bool irq_settings_is_per_cpu(struct irq_desc *desc)
 {
 	return desc->status_use_accessors & _IRQ_PER_CPU;
Index: linux-4.9.20-rt16/kernel/irq/spurious.c
===================================================================
--- linux-4.9.20-rt16.orig/kernel/irq/spurious.c
+++ linux-4.9.20-rt16/kernel/irq/spurious.c
@@ -442,6 +442,10 @@ MODULE_PARM_DESC(noirqdebug, "Disable ir
 
 static int __init irqfixup_setup(char *str)
 {
+#ifdef CONFIG_PREEMPT_RT_BASE
+	pr_warn("irqfixup boot option not supported w/ CONFIG_PREEMPT_RT_BASE\n");
+	return 1;
+#endif
 	irqfixup = 1;
 	printk(KERN_WARNING "Misrouted IRQ fixup support enabled.\n");
 	printk(KERN_WARNING "This may impact system performance.\n");
@@ -454,6 +458,10 @@ module_param(irqfixup, int, 0644);
 
 static int __init irqpoll_setup(char *str)
 {
+#ifdef CONFIG_PREEMPT_RT_BASE
+	pr_warn("irqpoll boot option not supported w/ CONFIG_PREEMPT_RT_BASE\n");
+	return 1;
+#endif
 	irqfixup = 2;
 	printk(KERN_WARNING "Misrouted IRQ fixup and polling support "
 				"enabled\n");
Index: linux-4.9.20-rt16/kernel/irq_work.c
===================================================================
--- linux-4.9.20-rt16.orig/kernel/irq_work.c
+++ linux-4.9.20-rt16/kernel/irq_work.c
@@ -17,6 +17,7 @@
 #include <linux/cpu.h>
 #include <linux/notifier.h>
 #include <linux/smp.h>
+#include <linux/interrupt.h>
 #include <asm/processor.h>
 
 
@@ -65,6 +66,8 @@ void __weak arch_irq_work_raise(void)
  */
 bool irq_work_queue_on(struct irq_work *work, int cpu)
 {
+	struct llist_head *list;
+
 	/* All work should have been flushed before going offline */
 	WARN_ON_ONCE(cpu_is_offline(cpu));
 
@@ -75,7 +78,12 @@ bool irq_work_queue_on(struct irq_work *
 	if (!irq_work_claim(work))
 		return false;
 
-	if (llist_add(&work->llnode, &per_cpu(raised_list, cpu)))
+	if (IS_ENABLED(CONFIG_PREEMPT_RT_FULL) && !(work->flags & IRQ_WORK_HARD_IRQ))
+		list = &per_cpu(lazy_list, cpu);
+	else
+		list = &per_cpu(raised_list, cpu);
+
+	if (llist_add(&work->llnode, list))
 		arch_send_call_function_single_ipi(cpu);
 
 	return true;
@@ -86,6 +94,9 @@ EXPORT_SYMBOL_GPL(irq_work_queue_on);
 /* Enqueue the irq work @work on the current CPU */
 bool irq_work_queue(struct irq_work *work)
 {
+	struct llist_head *list;
+	bool lazy_work, realtime = IS_ENABLED(CONFIG_PREEMPT_RT_FULL);
+
 	/* Only queue if not already pending */
 	if (!irq_work_claim(work))
 		return false;
@@ -93,13 +104,15 @@ bool irq_work_queue(struct irq_work *wor
 	/* Queue the entry and raise the IPI if needed. */
 	preempt_disable();
 
-	/* If the work is "lazy", handle it from next tick if any */
-	if (work->flags & IRQ_WORK_LAZY) {
-		if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) &&
-		    tick_nohz_tick_stopped())
-			arch_irq_work_raise();
-	} else {
-		if (llist_add(&work->llnode, this_cpu_ptr(&raised_list)))
+	lazy_work = work->flags & IRQ_WORK_LAZY;
+
+	if (lazy_work || (realtime && !(work->flags & IRQ_WORK_HARD_IRQ)))
+		list = this_cpu_ptr(&lazy_list);
+	else
+		list = this_cpu_ptr(&raised_list);
+
+	if (llist_add(&work->llnode, list)) {
+		if (!lazy_work || tick_nohz_tick_stopped())
 			arch_irq_work_raise();
 	}
 
@@ -116,9 +129,8 @@ bool irq_work_needs_cpu(void)
 	raised = this_cpu_ptr(&raised_list);
 	lazy = this_cpu_ptr(&lazy_list);
 
-	if (llist_empty(raised) || arch_irq_work_has_interrupt())
-		if (llist_empty(lazy))
-			return false;
+	if (llist_empty(raised) && llist_empty(lazy))
+		return false;
 
 	/* All work should have been flushed before going offline */
 	WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
@@ -132,7 +144,7 @@ static void irq_work_run_list(struct lli
 	struct irq_work *work;
 	struct llist_node *llnode;
 
-	BUG_ON(!irqs_disabled());
+	BUG_ON_NONRT(!irqs_disabled());
 
 	if (llist_empty(list))
 		return;
@@ -169,7 +181,16 @@ static void irq_work_run_list(struct lli
 void irq_work_run(void)
 {
 	irq_work_run_list(this_cpu_ptr(&raised_list));
-	irq_work_run_list(this_cpu_ptr(&lazy_list));
+	if (IS_ENABLED(CONFIG_PREEMPT_RT_FULL)) {
+		/*
+		 * NOTE: we raise softirq via IPI for safety,
+		 * and execute in irq_work_tick() to move the
+		 * overhead from hard to soft irq context.
+		 */
+		if (!llist_empty(this_cpu_ptr(&lazy_list)))
+			raise_softirq(TIMER_SOFTIRQ);
+	} else
+		irq_work_run_list(this_cpu_ptr(&lazy_list));
 }
 EXPORT_SYMBOL_GPL(irq_work_run);
 
@@ -179,8 +200,17 @@ void irq_work_tick(void)
 
 	if (!llist_empty(raised) && !arch_irq_work_has_interrupt())
 		irq_work_run_list(raised);
+
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT_FULL))
+		irq_work_run_list(this_cpu_ptr(&lazy_list));
+}
+
+#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL)
+void irq_work_tick_soft(void)
+{
 	irq_work_run_list(this_cpu_ptr(&lazy_list));
 }
+#endif
 
 /*
  * Synchronize against the irq_work @entry, ensures the entry is not
Index: linux-4.9.20-rt16/kernel/ksysfs.c
===================================================================
--- linux-4.9.20-rt16.orig/kernel/ksysfs.c
+++ linux-4.9.20-rt16/kernel/ksysfs.c
@@ -136,6 +136,15 @@ KERNEL_ATTR_RO(vmcoreinfo);
 
 #endif /* CONFIG_KEXEC_CORE */
 
+#if defined(CONFIG_PREEMPT_RT_FULL)
+static ssize_t  realtime_show(struct kobject *kobj,
+			      struct kobj_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", 1);
+}
+KERNEL_ATTR_RO(realtime);
+#endif
+
 /* whether file capabilities are enabled */
 static ssize_t fscaps_show(struct kobject *kobj,
 				  struct kobj_attribute *attr, char *buf)
@@ -225,6 +234,9 @@ static struct attribute * kernel_attrs[]
 	&rcu_expedited_attr.attr,
 	&rcu_normal_attr.attr,
 #endif
+#ifdef CONFIG_PREEMPT_RT_FULL
+	&realtime_attr.attr,
+#endif
 	NULL
 };
 
Index: linux-4.9.20-rt16/kernel/locking/Makefile
===================================================================
--- linux-4.9.20-rt16.orig/kernel/locking/Makefile
+++ linux-4.9.20-rt16/kernel/locking/Makefile
@@ -2,7 +2,7 @@
 # and is generally not a function of system call inputs.
 KCOV_INSTRUMENT		:= n
 
-obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o
+obj-y += semaphore.o percpu-rwsem.o
 
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE)
@@ -11,7 +11,11 @@ CFLAGS_REMOVE_mutex-debug.o = $(CC_FLAGS
 CFLAGS_REMOVE_rtmutex-debug.o = $(CC_FLAGS_FTRACE)
 endif
 
+ifneq ($(CONFIG_PREEMPT_RT_FULL),y)
+obj-y += mutex.o
 obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o
+endif
+obj-y += rwsem.o
 obj-$(CONFIG_LOCKDEP) += lockdep.o
 ifeq ($(CONFIG_PROC_FS),y)
 obj-$(CONFIG_LOCKDEP) += lockdep_proc.o
@@ -24,7 +28,10 @@ obj-$(CONFIG_RT_MUTEXES) += rtmutex.o
 obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
+ifneq ($(CONFIG_PREEMPT_RT_FULL),y)
 obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
 obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o
+endif
+obj-$(CONFIG_PREEMPT_RT_FULL) += rt.o rwsem-rt.o
 obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o
 obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o
Index: linux-4.9.20-rt16/kernel/locking/lockdep.c
===================================================================
--- linux-4.9.20-rt16.orig/kernel/locking/lockdep.c
+++ linux-4.9.20-rt16/kernel/locking/lockdep.c
@@ -658,6 +658,7 @@ look_up_lock_class(struct lockdep_map *l
 	struct lockdep_subclass_key *key;
 	struct hlist_head *hash_head;
 	struct lock_class *class;
+	bool is_static = false;
 
 	if (unlikely(subclass >= MAX_LOCKDEP_SUBCLASSES)) {
 		debug_locks_off();
@@ -671,10 +672,23 @@ look_up_lock_class(struct lockdep_map *l
 
 	/*
 	 * Static locks do not have their class-keys yet - for them the key
-	 * is the lock object itself:
-	 */
-	if (unlikely(!lock->key))
-		lock->key = (void *)lock;
+	 * is the lock object itself. If the lock is in the per cpu area,
+	 * the canonical address of the lock (per cpu offset removed) is
+	 * used.
+	 */
+	if (unlikely(!lock->key)) {
+		unsigned long can_addr, addr = (unsigned long)lock;
+
+		if (__is_kernel_percpu_address(addr, &can_addr))
+			lock->key = (void *)can_addr;
+		else if (__is_module_percpu_address(addr, &can_addr))
+			lock->key = (void *)can_addr;
+		else if (static_obj(lock))
+			lock->key = (void *)lock;
+		else
+			return ERR_PTR(-EINVAL);
+		is_static = true;
+	}
 
 	/*
 	 * NOTE: the class-key must be unique. For dynamic locks, a static
@@ -706,7 +720,7 @@ look_up_lock_class(struct lockdep_map *l
 		}
 	}
 
-	return NULL;
+	return is_static || static_obj(lock->key) ? NULL : ERR_PTR(-EINVAL);
 }
 
 /*
@@ -724,19 +738,18 @@ register_lock_class(struct lockdep_map *
 	DEBUG_LOCKS_WARN_ON(!irqs_disabled());
 
 	class = look_up_lock_class(lock, subclass);
-	if (likely(class))
+	if (likely(!IS_ERR_OR_NULL(class)))
 		goto out_set_class_cache;
 
 	/*
 	 * Debug-check: all keys must be persistent!
- 	 */
-	if (!static_obj(lock->key)) {
+	 */
+	if (IS_ERR(class)) {
 		debug_locks_off();
 		printk("INFO: trying to register non-static key.\n");
 		printk("the code is fine but needs lockdep annotation.\n");
 		printk("turning off the locking correctness validator.\n");
 		dump_stack();
-
 		return NULL;
 	}
 
@@ -3410,7 +3423,7 @@ static int match_held_lock(struct held_l
 		 * Clearly if the lock hasn't been acquired _ever_, we're not
 		 * holding it either, so report failure.
 		 */
-		if (!class)
+		if (IS_ERR_OR_NULL(class))
 			return 0;
 
 		/*
@@ -3689,6 +3702,7 @@ static void check_flags(unsigned long fl
 		}
 	}
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 	/*
 	 * We dont accurately track softirq state in e.g.
 	 * hardirq contexts (such as on 4KSTACKS), so only
@@ -3703,6 +3717,7 @@ static void check_flags(unsigned long fl
 			DEBUG_LOCKS_WARN_ON(!current->softirqs_enabled);
 		}
 	}
+#endif
 
 	if (!debug_locks)
 		print_irqtrace_events(current);
@@ -4159,7 +4174,7 @@ void lockdep_reset_lock(struct lockdep_m
 		 * If the class exists we look it up and zap it:
 		 */
 		class = look_up_lock_class(lock, j);
-		if (class)
+		if (!IS_ERR_OR_NULL(class))
 			zap_class(class);
 	}
 	/*
Index: linux-4.9.20-rt16/kernel/locking/locktorture.c
===================================================================
--- linux-4.9.20-rt16.orig/kernel/locking/locktorture.c
+++ linux-4.9.20-rt16/kernel/locking/locktorture.c
@@ -26,7 +26,6 @@
 #include <linux/kthread.h>
 #include <linux/sched/rt.h>
 #include <linux/spinlock.h>
-#include <linux/rwlock.h>
 #include <linux/mutex.h>
 #include <linux/rwsem.h>
 #include <linux/smp.h>
Index: linux-4.9.20-rt16/kernel/locking/percpu-rwsem.c
===================================================================
--- linux-4.9.20-rt16.orig/kernel/locking/percpu-rwsem.c
+++ linux-4.9.20-rt16/kernel/locking/percpu-rwsem.c
@@ -18,7 +18,7 @@ int __percpu_init_rwsem(struct percpu_rw
 	/* ->rw_sem represents the whole percpu_rw_semaphore for lockdep */
 	rcu_sync_init(&sem->rss, RCU_SCHED_SYNC);
 	__init_rwsem(&sem->rw_sem, name, rwsem_key);
-	init_waitqueue_head(&sem->writer);
+	init_swait_queue_head(&sem->writer);
 	sem->readers_block = 0;
 	return 0;
 }
@@ -103,7 +103,7 @@ void __percpu_up_read(struct percpu_rw_s
 	__this_cpu_dec(*sem->read_count);
 
 	/* Prod writer to recheck readers_active */
-	wake_up(&sem->writer);
+	swake_up(&sem->writer);
 }
 EXPORT_SYMBOL_GPL(__percpu_up_read);
 
@@ -160,7 +160,7 @@ void percpu_down_write(struct percpu_rw_
 	 */
 
 	/* Wait for all now active readers to complete. */
-	wait_event(sem->writer, readers_active_check(sem));
+	swait_event(sem->writer, readers_active_check(sem));
 }
 EXPORT_SYMBOL_GPL(percpu_down_write);
 
Index: linux-4.9.20-rt16/kernel/locking/rt.c
===================================================================
--- /dev/null
+++ linux-4.9.20-rt16/kernel/locking/rt.c
@@ -0,0 +1,331 @@
+/*
+ * kernel/rt.c
+ *
+ * Real-Time Preemption Support
+ *
+ * started by Ingo Molnar:
+ *
+ *  Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ *  Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com>
+ *
+ * historic credit for proving that Linux spinlocks can be implemented via
+ * RT-aware mutexes goes to many people: The Pmutex project (Dirk Grambow
+ * and others) who prototyped it on 2.4 and did lots of comparative
+ * research and analysis; TimeSys, for proving that you can implement a
+ * fully preemptible kernel via the use of IRQ threading and mutexes;
+ * Bill Huey for persuasively arguing on lkml that the mutex model is the
+ * right one; and to MontaVista, who ported pmutexes to 2.6.
+ *
+ * This code is a from-scratch implementation and is not based on pmutexes,
+ * but the idea of converting spinlocks to mutexes is used here too.
+ *
+ * lock debugging, locking tree, deadlock detection:
+ *
+ *  Copyright (C) 2004, LynuxWorks, Inc., Igor Manyilov, Bill Huey
+ *  Released under the General Public License (GPL).
+ *
+ * Includes portions of the generic R/W semaphore implementation from:
+ *
+ *  Copyright (c) 2001   David Howells (dhowells@redhat.com).
+ *  - Derived partially from idea by Andrea Arcangeli <andrea@suse.de>
+ *  - Derived also from comments by Linus
+ *
+ * Pending ownership of locks and ownership stealing:
+ *
+ *  Copyright (C) 2005, Kihon Technologies Inc., Steven Rostedt
+ *
+ *   (also by Steven Rostedt)
+ *    - Converted single pi_lock to individual task locks.
+ *
+ * By Esben Nielsen:
+ *    Doing priority inheritance with help of the scheduler.
+ *
+ *  Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com>
+ *  - major rework based on Esben Nielsens initial patch
+ *  - replaced thread_info references by task_struct refs
+ *  - removed task->pending_owner dependency
+ *  - BKL drop/reacquire for semaphore style locks to avoid deadlocks
+ *    in the scheduler return path as discussed with Steven Rostedt
+ *
+ *  Copyright (C) 2006, Kihon Technologies Inc.
+ *    Steven Rostedt <rostedt@goodmis.org>
+ *  - debugged and patched Thomas Gleixner's rework.
+ *  - added back the cmpxchg to the rework.
+ *  - turned atomic require back on for SMP.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/rtmutex.h>
+#include <linux/sched.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/kallsyms.h>
+#include <linux/syscalls.h>
+#include <linux/interrupt.h>
+#include <linux/plist.h>
+#include <linux/fs.h>
+#include <linux/futex.h>
+#include <linux/hrtimer.h>
+
+#include "rtmutex_common.h"
+
+/*
+ * struct mutex functions
+ */
+void __mutex_do_init(struct mutex *mutex, const char *name,
+		     struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/*
+	 * Make sure we are not reinitializing a held lock:
+	 */
+	debug_check_no_locks_freed((void *)mutex, sizeof(*mutex));
+	lockdep_init_map(&mutex->dep_map, name, key, 0);
+#endif
+	mutex->lock.save_state = 0;
+}
+EXPORT_SYMBOL(__mutex_do_init);
+
+void __lockfunc _mutex_lock(struct mutex *lock)
+{
+	mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+	rt_mutex_lock(&lock->lock);
+}
+EXPORT_SYMBOL(_mutex_lock);
+
+int __lockfunc _mutex_lock_interruptible(struct mutex *lock)
+{
+	int ret;
+
+	mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+	ret = rt_mutex_lock_interruptible(&lock->lock);
+	if (ret)
+		mutex_release(&lock->dep_map, 1, _RET_IP_);
+	return ret;
+}
+EXPORT_SYMBOL(_mutex_lock_interruptible);
+
+int __lockfunc _mutex_lock_killable(struct mutex *lock)
+{
+	int ret;
+
+	mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+	ret = rt_mutex_lock_killable(&lock->lock);
+	if (ret)
+		mutex_release(&lock->dep_map, 1, _RET_IP_);
+	return ret;
+}
+EXPORT_SYMBOL(_mutex_lock_killable);
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass)
+{
+	mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_);
+	rt_mutex_lock(&lock->lock);
+}
+EXPORT_SYMBOL(_mutex_lock_nested);
+
+void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest)
+{
+	mutex_acquire_nest(&lock->dep_map, 0, 0, nest, _RET_IP_);
+	rt_mutex_lock(&lock->lock);
+}
+EXPORT_SYMBOL(_mutex_lock_nest_lock);
+
+int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass)
+{
+	int ret;
+
+	mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_);
+	ret = rt_mutex_lock_interruptible(&lock->lock);
+	if (ret)
+		mutex_release(&lock->dep_map, 1, _RET_IP_);
+	return ret;
+}
+EXPORT_SYMBOL(_mutex_lock_interruptible_nested);
+
+int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass)
+{
+	int ret;
+
+	mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
+	ret = rt_mutex_lock_killable(&lock->lock);
+	if (ret)
+		mutex_release(&lock->dep_map, 1, _RET_IP_);
+	return ret;
+}
+EXPORT_SYMBOL(_mutex_lock_killable_nested);
+#endif
+
+int __lockfunc _mutex_trylock(struct mutex *lock)
+{
+	int ret = rt_mutex_trylock(&lock->lock);
+
+	if (ret)
+		mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+
+	return ret;
+}
+EXPORT_SYMBOL(_mutex_trylock);
+
+void __lockfunc _mutex_unlock(struct mutex *lock)
+{
+	mutex_release(&lock->dep_map, 1, _RET_IP_);
+	rt_mutex_unlock(&lock->lock);
+}
+EXPORT_SYMBOL(_mutex_unlock);
+
+/*
+ * rwlock_t functions
+ */
+int __lockfunc rt_write_trylock(rwlock_t *rwlock)
+{
+	int ret;
+
+	migrate_disable();
+	ret = rt_mutex_trylock(&rwlock->lock);
+	if (ret)
+		rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_);
+	else
+		migrate_enable();
+
+	return ret;
+}
+EXPORT_SYMBOL(rt_write_trylock);
+
+int __lockfunc rt_write_trylock_irqsave(rwlock_t *rwlock, unsigned long *flags)
+{
+	int ret;
+
+	*flags = 0;
+	ret = rt_write_trylock(rwlock);
+	return ret;
+}
+EXPORT_SYMBOL(rt_write_trylock_irqsave);
+
+int __lockfunc rt_read_trylock(rwlock_t *rwlock)
+{
+	struct rt_mutex *lock = &rwlock->lock;
+	int ret = 1;
+
+	/*
+	 * recursive read locks succeed when current owns the lock,
+	 * but not when read_depth == 0 which means that the lock is
+	 * write locked.
+	 */
+	if (rt_mutex_owner(lock) != current) {
+		migrate_disable();
+		ret = rt_mutex_trylock(lock);
+		if (ret)
+			rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_);
+		else
+			migrate_enable();
+
+	} else if (!rwlock->read_depth) {
+		ret = 0;
+	}
+
+	if (ret)
+		rwlock->read_depth++;
+
+	return ret;
+}
+EXPORT_SYMBOL(rt_read_trylock);
+
+void __lockfunc rt_write_lock(rwlock_t *rwlock)
+{
+	rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_);
+	__rt_spin_lock(&rwlock->lock);
+}
+EXPORT_SYMBOL(rt_write_lock);
+
+void __lockfunc rt_read_lock(rwlock_t *rwlock)
+{
+	struct rt_mutex *lock = &rwlock->lock;
+
+
+	/*
+	 * recursive read locks succeed when current owns the lock
+	 */
+	if (rt_mutex_owner(lock) != current) {
+		rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_);
+		__rt_spin_lock(lock);
+	}
+	rwlock->read_depth++;
+}
+
+EXPORT_SYMBOL(rt_read_lock);
+
+void __lockfunc rt_write_unlock(rwlock_t *rwlock)
+{
+	/* NOTE: we always pass in '1' for nested, for simplicity */
+	rwlock_release(&rwlock->dep_map, 1, _RET_IP_);
+	__rt_spin_unlock(&rwlock->lock);
+	migrate_enable();
+}
+EXPORT_SYMBOL(rt_write_unlock);
+
+void __lockfunc rt_read_unlock(rwlock_t *rwlock)
+{
+	/* Release the lock only when read_depth is down to 0 */
+	if (--rwlock->read_depth == 0) {
+		rwlock_release(&rwlock->dep_map, 1, _RET_IP_);
+		__rt_spin_unlock(&rwlock->lock);
+		migrate_enable();
+	}
+}
+EXPORT_SYMBOL(rt_read_unlock);
+
+unsigned long __lockfunc rt_write_lock_irqsave(rwlock_t *rwlock)
+{
+	rt_write_lock(rwlock);
+
+	return 0;
+}
+EXPORT_SYMBOL(rt_write_lock_irqsave);
+
+unsigned long __lockfunc rt_read_lock_irqsave(rwlock_t *rwlock)
+{
+	rt_read_lock(rwlock);
+
+	return 0;
+}
+EXPORT_SYMBOL(rt_read_lock_irqsave);
+
+void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/*
+	 * Make sure we are not reinitializing a held lock:
+	 */
+	debug_check_no_locks_freed((void *)rwlock, sizeof(*rwlock));
+	lockdep_init_map(&rwlock->dep_map, name, key, 0);
+#endif
+	rwlock->lock.save_state = 1;
+	rwlock->read_depth = 0;
+}
+EXPORT_SYMBOL(__rt_rwlock_init);
+
+/**
+ * atomic_dec_and_mutex_lock - return holding mutex if we dec to 0
+ * @cnt: the atomic which we are to dec
+ * @lock: the mutex to return holding if we dec to 0
+ *
+ * return true and hold lock if we dec to 0, return false otherwise
+ */
+int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock)
+{
+	/* dec if we can't possibly hit 0 */
+	if (atomic_add_unless(cnt, -1, 1))
+		return 0;
+	/* we might hit 0, so take the lock */
+	mutex_lock(lock);
+	if (!atomic_dec_and_test(cnt)) {
+		/* when we actually did the dec, we didn't hit 0 */
+		mutex_unlock(lock);
+		return 0;
+	}
+	/* we hit 0, and we hold the lock */
+	return 1;
+}
+EXPORT_SYMBOL(atomic_dec_and_mutex_lock);
Index: linux-4.9.20-rt16/kernel/locking/rtmutex-debug.c
===================================================================
--- linux-4.9.20-rt16.orig/kernel/locking/rtmutex-debug.c
+++ linux-4.9.20-rt16/kernel/locking/rtmutex-debug.c
@@ -173,12 +173,3 @@ void debug_rt_mutex_init(struct rt_mutex
 	lock->name = name;
 }
 
-void
-rt_mutex_deadlock_account_lock(struct rt_mutex *lock, struct task_struct *task)
-{
-}
-
-void rt_mutex_deadlock_account_unlock(struct task_struct *task)
-{
-}
-
Index: linux-4.9.20-rt16/kernel/locking/rtmutex-debug.h
===================================================================
--- linux-4.9.20-rt16.orig/kernel/locking/rtmutex-debug.h
+++ linux-4.9.20-rt16/kernel/locking/rtmutex-debug.h
@@ -9,9 +9,6 @@
  * This file contains macros used solely by rtmutex.c. Debug version.
  */
 
-extern void
-rt_mutex_deadlock_account_lock(struct rt_mutex *lock, struct task_struct *task);
-extern void rt_mutex_deadlock_account_unlock(struct task_struct *task);
 extern void debug_rt_mutex_init_waiter(struct rt_mutex_waiter *waiter);
 extern void debug_rt_mutex_free_waiter(struct rt_mutex_waiter *waiter);
 extern void debug_rt_mutex_init(struct rt_mutex *lock, const char *name);
Index: linux-4.9.20-rt16/kernel/locking/rtmutex.c
===================================================================
--- linux-4.9.20-rt16.orig/kernel/locking/rtmutex.c
+++ linux-4.9.20-rt16/kernel/locking/rtmutex.c
@@ -7,6 +7,11 @@
  *  Copyright (C) 2005-2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com>
  *  Copyright (C) 2005 Kihon Technologies Inc., Steven Rostedt
  *  Copyright (C) 2006 Esben Nielsen
+ *  Adaptive Spinlocks:
+ *  Copyright (C) 2008 Novell, Inc., Gregory Haskins, Sven Dietrich,
+ *				     and Peter Morreale,
+ * Adaptive Spinlocks simplification:
+ *  Copyright (C) 2008 Red Hat, Inc., Steven Rostedt <srostedt@redhat.com>
  *
  *  See Documentation/locking/rt-mutex-design.txt for details.
  */
@@ -16,6 +21,7 @@
 #include <linux/sched/rt.h>
 #include <linux/sched/deadline.h>
 #include <linux/timer.h>
+#include <linux/ww_mutex.h>
 
 #include "rtmutex_common.h"
 
@@ -133,6 +139,12 @@ static void fixup_rt_mutex_waiters(struc
 		WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS);
 }
 
+static int rt_mutex_real_waiter(struct rt_mutex_waiter *waiter)
+{
+	return waiter && waiter != PI_WAKEUP_INPROGRESS &&
+		waiter != PI_REQUEUE_INPROGRESS;
+}
+
 /*
  * We can speed up the acquire/release, if there's no debugging state to be
  * set up.
@@ -222,12 +234,25 @@ static inline bool unlock_rt_mutex_safe(
 }
 #endif
 
+#define STEAL_NORMAL  0
+#define STEAL_LATERAL 1
+/*
+ * Only use with rt_mutex_waiter_{less,equal}()
+ */
+#define task_to_waiter(p)	\
+	&(struct rt_mutex_waiter){ .prio = (p)->prio, .deadline = (p)->dl.deadline }
+
 static inline int
 rt_mutex_waiter_less(struct rt_mutex_waiter *left,
-		     struct rt_mutex_waiter *right)
+		     struct rt_mutex_waiter *right, int mode)
 {
-	if (left->prio < right->prio)
-		return 1;
+	if (mode == STEAL_NORMAL) {
+		if (left->prio < right->prio)
+			return 1;
+	} else {
+		if (left->prio <= right->prio)
+			return 1;
+	}
 
 	/*
 	 * If both waiters have dl_prio(), we check the deadlines of the
@@ -236,12 +261,30 @@ rt_mutex_waiter_less(struct rt_mutex_wai
 	 * then right waiter has a dl_prio() too.
 	 */
 	if (dl_prio(left->prio))
-		return dl_time_before(left->task->dl.deadline,
-				      right->task->dl.deadline);
+		return dl_time_before(left->deadline, right->deadline);
 
 	return 0;
 }
 
+static inline int
+rt_mutex_waiter_equal(struct rt_mutex_waiter *left,
+		      struct rt_mutex_waiter *right)
+{
+	if (left->prio != right->prio)
+		return 0;
+
+	/*
+	 * If both waiters have dl_prio(), we check the deadlines of the
+	 * associated tasks.
+	 * If left waiter has a dl_prio(), and we didn't return 0 above,
+	 * then right waiter has a dl_prio() too.
+	 */
+	if (dl_prio(left->prio))
+		return left->deadline == right->deadline;
+
+	return 1;
+}
+
 static void
 rt_mutex_enqueue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
 {
@@ -253,7 +296,7 @@ rt_mutex_enqueue(struct rt_mutex *lock,
 	while (*link) {
 		parent = *link;
 		entry = rb_entry(parent, struct rt_mutex_waiter, tree_entry);
-		if (rt_mutex_waiter_less(waiter, entry)) {
+		if (rt_mutex_waiter_less(waiter, entry, STEAL_NORMAL)) {
 			link = &parent->rb_left;
 		} else {
 			link = &parent->rb_right;
@@ -292,7 +335,7 @@ rt_mutex_enqueue_pi(struct task_struct *
 	while (*link) {
 		parent = *link;
 		entry = rb_entry(parent, struct rt_mutex_waiter, pi_tree_entry);
-		if (rt_mutex_waiter_less(waiter, entry)) {
+		if (rt_mutex_waiter_less(waiter, entry, STEAL_NORMAL)) {
 			link = &parent->rb_left;
 		} else {
 			link = &parent->rb_right;
@@ -320,72 +363,16 @@ rt_mutex_dequeue_pi(struct task_struct *
 	RB_CLEAR_NODE(&waiter->pi_tree_entry);
 }
 
-/*
- * Calculate task priority from the waiter tree priority
- *
- * Return task->normal_prio when the waiter tree is empty or when
- * the waiter is not allowed to do priority boosting
- */
-int rt_mutex_getprio(struct task_struct *task)
-{
-	if (likely(!task_has_pi_waiters(task)))
-		return task->normal_prio;
-
-	return min(task_top_pi_waiter(task)->prio,
-		   task->normal_prio);
-}
-
-struct task_struct *rt_mutex_get_top_task(struct task_struct *task)
-{
-	if (likely(!task_has_pi_waiters(task)))
-		return NULL;
-
-	return task_top_pi_waiter(task)->task;
-}
-
-/*
- * Called by sched_setscheduler() to get the priority which will be
- * effective after the change.
- */
-int rt_mutex_get_effective_prio(struct task_struct *task, int newprio)
-{
-	if (!task_has_pi_waiters(task))
-		return newprio;
-
-	if (task_top_pi_waiter(task)->task->prio <= newprio)
-		return task_top_pi_waiter(task)->task->prio;
-	return newprio;
-}
-
-/*
- * Adjust the priority of a task, after its pi_waiters got modified.
- *
- * This can be both boosting and unboosting. task->pi_lock must be held.
- */
-static void __rt_mutex_adjust_prio(struct task_struct *task)
+static void rt_mutex_adjust_prio(struct task_struct *p)
 {
-	int prio = rt_mutex_getprio(task);
+	struct task_struct *pi_task = NULL;
 
-	if (task->prio != prio || dl_prio(prio))
-		rt_mutex_setprio(task, prio);
-}
+	lockdep_assert_held(&p->pi_lock);
 
-/*
- * Adjust task priority (undo boosting). Called from the exit path of
- * rt_mutex_slowunlock() and rt_mutex_slowlock().
- *
- * (Note: We do this outside of the protection of lock->wait_lock to
- * allow the lock to be taken while or before we readjust the priority
- * of task. We do not use the spin_xx_mutex() variants here as we are
- * outside of the debug path.)
- */
-void rt_mutex_adjust_prio(struct task_struct *task)
-{
-	unsigned long flags;
+	if (task_has_pi_waiters(p))
+		pi_task = task_top_pi_waiter(p)->task;
 
-	raw_spin_lock_irqsave(&task->pi_lock, flags);
-	__rt_mutex_adjust_prio(task);
-	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+	rt_mutex_setprio(p, pi_task);
 }
 
 /*
@@ -414,6 +401,14 @@ static bool rt_mutex_cond_detect_deadloc
 	return debug_rt_mutex_detect_deadlock(waiter, chwalk);
 }
 
+static void rt_mutex_wake_waiter(struct rt_mutex_waiter *waiter)
+{
+	if (waiter->savestate)
+		wake_up_lock_sleeper(waiter->task);
+	else
+		wake_up_process(waiter->task);
+}
+
 /*
  * Max number of times we'll walk the boosting chain:
  */
@@ -421,7 +416,8 @@ int max_lock_depth = 1024;
 
 static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p)
 {
-	return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL;
+	return rt_mutex_real_waiter(p->pi_blocked_on) ?
+		p->pi_blocked_on->lock : NULL;
 }
 
 /*
@@ -557,7 +553,7 @@ static int rt_mutex_adjust_prio_chain(st
 	 * reached or the state of the chain has changed while we
 	 * dropped the locks.
 	 */
-	if (!waiter)
+	if (!rt_mutex_real_waiter(waiter))
 		goto out_unlock_pi;
 
 	/*
@@ -608,7 +604,7 @@ static int rt_mutex_adjust_prio_chain(st
 	 * enabled we continue, but stop the requeueing in the chain
 	 * walk.
 	 */
-	if (waiter->prio == task->prio) {
+	if (rt_mutex_waiter_equal(waiter, task_to_waiter(task))) {
 		if (!detect_deadlock)
 			goto out_unlock_pi;
 		else
@@ -704,7 +700,26 @@ static int rt_mutex_adjust_prio_chain(st
 
 	/* [7] Requeue the waiter in the lock waiter tree. */
 	rt_mutex_dequeue(lock, waiter);
+
+	/*
+	 * Update the waiter prio fields now that we're dequeued.
+	 *
+	 * These values can have changed through either:
+	 *
+	 *   sys_sched_set_scheduler() / sys_sched_setattr()
+	 *
+	 * or
+	 *
+	 *   DL CBS enforcement advancing the effective deadline.
+	 *
+	 * Even though pi_waiters also uses these fields, and that tree is only
+	 * updated in [11], we can do this here, since we hold [L], which
+	 * serializes all pi_waiters access and rb_erase() does not care about
+	 * the values of the node being removed.
+	 */
 	waiter->prio = task->prio;
+	waiter->deadline = task->dl.deadline;
+
 	rt_mutex_enqueue(lock, waiter);
 
 	/* [8] Release the task */
@@ -719,13 +734,16 @@ static int rt_mutex_adjust_prio_chain(st
 	 * follow here. This is the end of the chain we are walking.
 	 */
 	if (!rt_mutex_owner(lock)) {
+		struct rt_mutex_waiter *lock_top_waiter;
+
 		/*
 		 * If the requeue [7] above changed the top waiter,
 		 * then we need to wake the new top waiter up to try
 		 * to get the lock.
 		 */
-		if (prerequeue_top_waiter != rt_mutex_top_waiter(lock))
-			wake_up_process(rt_mutex_top_waiter(lock)->task);
+		lock_top_waiter = rt_mutex_top_waiter(lock);
+		if (prerequeue_top_waiter != lock_top_waiter)
+			rt_mutex_wake_waiter(lock_top_waiter);
 		raw_spin_unlock_irq(&lock->wait_lock);
 		return 0;
 	}
@@ -745,7 +763,7 @@ static int rt_mutex_adjust_prio_chain(st
 		 */
 		rt_mutex_dequeue_pi(task, prerequeue_top_waiter);
 		rt_mutex_enqueue_pi(task, waiter);
-		__rt_mutex_adjust_prio(task);
+		rt_mutex_adjust_prio(task);
 
 	} else if (prerequeue_top_waiter == waiter) {
 		/*
@@ -761,7 +779,7 @@ static int rt_mutex_adjust_prio_chain(st
 		rt_mutex_dequeue_pi(task, waiter);
 		waiter = rt_mutex_top_waiter(lock);
 		rt_mutex_enqueue_pi(task, waiter);
-		__rt_mutex_adjust_prio(task);
+		rt_mutex_adjust_prio(task);
 	} else {
 		/*
 		 * Nothing changed. No need to do any priority
@@ -818,6 +836,7 @@ static int rt_mutex_adjust_prio_chain(st
 	return ret;
 }
 
+
 /*
  * Try to take an rt-mutex
  *
@@ -828,9 +847,12 @@ static int rt_mutex_adjust_prio_chain(st
  * @waiter: The waiter that is queued to the lock's wait tree if the
  *	    callsite called task_blocked_on_lock(), otherwise NULL
  */
-static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
-				struct rt_mutex_waiter *waiter)
+static int __try_to_take_rt_mutex(struct rt_mutex *lock,
+				  struct task_struct *task,
+				  struct rt_mutex_waiter *waiter, int mode)
 {
+	lockdep_assert_held(&lock->wait_lock);
+
 	/*
 	 * Before testing whether we can acquire @lock, we set the
 	 * RT_MUTEX_HAS_WAITERS bit in @lock->owner. This forces all
@@ -866,8 +888,10 @@ static int try_to_take_rt_mutex(struct r
 		 * If waiter is not the highest priority waiter of
 		 * @lock, give up.
 		 */
-		if (waiter != rt_mutex_top_waiter(lock))
+		if (waiter != rt_mutex_top_waiter(lock)) {
+			/* XXX rt_mutex_waiter_less() ? */
 			return 0;
+		}
 
 		/*
 		 * We can acquire the lock. Remove the waiter from the
@@ -885,14 +909,26 @@ static int try_to_take_rt_mutex(struct r
 		 * not need to be dequeued.
 		 */
 		if (rt_mutex_has_waiters(lock)) {
+			struct task_struct *pown = rt_mutex_top_waiter(lock)->task;
+
+			if (task != pown)
+				return 0;
+
+			/*
+			 * Note that RT tasks are excluded from lateral-steals
+			 * to prevent the introduction of an unbounded latency.
+			 */
+			if (rt_task(task))
+				mode = STEAL_NORMAL;
 			/*
 			 * If @task->prio is greater than or equal to
 			 * the top waiter priority (kernel view),
 			 * @task lost.
 			 */
-			if (task->prio >= rt_mutex_top_waiter(lock)->prio)
+			if (!rt_mutex_waiter_less(task_to_waiter(task),
+						  rt_mutex_top_waiter(lock),
+						  mode))
 				return 0;
-
 			/*
 			 * The current top waiter stays enqueued. We
 			 * don't have to change anything in the lock
@@ -936,180 +972,592 @@ takeit:
 	 */
 	rt_mutex_set_owner(lock, task);
 
-	rt_mutex_deadlock_account_lock(lock, task);
-
 	return 1;
 }
 
+#ifdef CONFIG_PREEMPT_RT_FULL
 /*
- * Task blocks on lock.
- *
- * Prepare waiter and propagate pi chain
- *
- * This must be called with lock->wait_lock held and interrupts disabled
+ * preemptible spin_lock functions:
  */
-static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
-				   struct rt_mutex_waiter *waiter,
-				   struct task_struct *task,
-				   enum rtmutex_chainwalk chwalk)
+static inline void rt_spin_lock_fastlock(struct rt_mutex *lock,
+					 void  (*slowfn)(struct rt_mutex *lock,
+							 bool mg_off),
+					 bool do_mig_dis)
 {
-	struct task_struct *owner = rt_mutex_owner(lock);
-	struct rt_mutex_waiter *top_waiter = waiter;
-	struct rt_mutex *next_lock;
-	int chain_walk = 0, res;
+	might_sleep_no_state_check();
 
-	/*
-	 * Early deadlock detection. We really don't want the task to
-	 * enqueue on itself just to untangle the mess later. It's not
-	 * only an optimization. We drop the locks, so another waiter
-	 * can come in before the chain walk detects the deadlock. So
-	 * the other will detect the deadlock and return -EDEADLOCK,
-	 * which is wrong, as the other waiter is not in a deadlock
-	 * situation.
-	 */
-	if (owner == task)
-		return -EDEADLK;
+	if (do_mig_dis)
+		migrate_disable();
 
-	raw_spin_lock(&task->pi_lock);
-	__rt_mutex_adjust_prio(task);
-	waiter->task = task;
-	waiter->lock = lock;
-	waiter->prio = task->prio;
+	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
+		return;
+	else
+		slowfn(lock, do_mig_dis);
+}
 
-	/* Get the top priority waiter on the lock */
-	if (rt_mutex_has_waiters(lock))
-		top_waiter = rt_mutex_top_waiter(lock);
-	rt_mutex_enqueue(lock, waiter);
+static inline void rt_spin_lock_fastunlock(struct rt_mutex *lock,
+					   void  (*slowfn)(struct rt_mutex *lock))
+{
+	if (likely(rt_mutex_cmpxchg_release(lock, current, NULL)))
+		return;
+	else
+		slowfn(lock);
+}
+#ifdef CONFIG_SMP
+/*
+ * Note that owner is a speculative pointer and dereferencing relies
+ * on rcu_read_lock() and the check against the lock owner.
+ */
+static int adaptive_wait(struct rt_mutex *lock,
+			 struct task_struct *owner)
+{
+	int res = 0;
 
-	task->pi_blocked_on = waiter;
+	rcu_read_lock();
+	for (;;) {
+		if (owner != rt_mutex_owner(lock))
+			break;
+		/*
+		 * Ensure that owner->on_cpu is dereferenced _after_
+		 * checking the above to be valid.
+		 */
+		barrier();
+		if (!owner->on_cpu) {
+			res = 1;
+			break;
+		}
+		cpu_relax();
+	}
+	rcu_read_unlock();
+	return res;
+}
+#else
+static int adaptive_wait(struct rt_mutex *lock,
+			 struct task_struct *orig_owner)
+{
+	return 1;
+}
+#endif
 
-	raw_spin_unlock(&task->pi_lock);
+static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
+				   struct rt_mutex_waiter *waiter,
+				   struct task_struct *task,
+				   enum rtmutex_chainwalk chwalk);
+/*
+ * Slow path lock function spin_lock style: this variant is very
+ * careful not to miss any non-lock wakeups.
+ *
+ * We store the current state under p->pi_lock in p->saved_state and
+ * the try_to_wake_up() code handles this accordingly.
+ */
+static void  noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock,
+						    bool mg_off)
+{
+	struct task_struct *lock_owner, *self = current;
+	struct rt_mutex_waiter waiter, *top_waiter;
+	unsigned long flags;
+	int ret;
 
-	if (!owner)
-		return 0;
+	rt_mutex_init_waiter(&waiter, true);
 
-	raw_spin_lock(&owner->pi_lock);
-	if (waiter == rt_mutex_top_waiter(lock)) {
-		rt_mutex_dequeue_pi(owner, top_waiter);
-		rt_mutex_enqueue_pi(owner, waiter);
+	raw_spin_lock_irqsave(&lock->wait_lock, flags);
 
-		__rt_mutex_adjust_prio(owner);
-		if (owner->pi_blocked_on)
-			chain_walk = 1;
-	} else if (rt_mutex_cond_detect_deadlock(waiter, chwalk)) {
-		chain_walk = 1;
+	if (__try_to_take_rt_mutex(lock, self, NULL, STEAL_LATERAL)) {
+		raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
+		return;
 	}
 
-	/* Store the lock on which owner is blocked or NULL */
-	next_lock = task_blocked_on_lock(owner);
+	BUG_ON(rt_mutex_owner(lock) == self);
 
-	raw_spin_unlock(&owner->pi_lock);
 	/*
-	 * Even if full deadlock detection is on, if the owner is not
-	 * blocked itself, we can avoid finding this out in the chain
-	 * walk.
+	 * We save whatever state the task is in and we'll restore it
+	 * after acquiring the lock taking real wakeups into account
+	 * as well. We are serialized via pi_lock against wakeups. See
+	 * try_to_wake_up().
 	 */
-	if (!chain_walk || !next_lock)
-		return 0;
+	raw_spin_lock(&self->pi_lock);
+	self->saved_state = self->state;
+	__set_current_state_no_track(TASK_UNINTERRUPTIBLE);
+	raw_spin_unlock(&self->pi_lock);
 
-	/*
-	 * The owner can't disappear while holding a lock,
-	 * so the owner struct is protected by wait_lock.
-	 * Gets dropped in rt_mutex_adjust_prio_chain()!
-	 */
-	get_task_struct(owner);
+	ret = task_blocks_on_rt_mutex(lock, &waiter, self, RT_MUTEX_MIN_CHAINWALK);
+	BUG_ON(ret);
 
-	raw_spin_unlock_irq(&lock->wait_lock);
+	for (;;) {
+		/* Try to acquire the lock again. */
+		if (__try_to_take_rt_mutex(lock, self, &waiter, STEAL_LATERAL))
+			break;
 
-	res = rt_mutex_adjust_prio_chain(owner, chwalk, lock,
-					 next_lock, waiter, task);
+		top_waiter = rt_mutex_top_waiter(lock);
+		lock_owner = rt_mutex_owner(lock);
 
-	raw_spin_lock_irq(&lock->wait_lock);
+		raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
-	return res;
-}
+		debug_rt_mutex_print_deadlock(&waiter);
 
-/*
- * Remove the top waiter from the current tasks pi waiter tree and
- * queue it up.
- *
- * Called with lock->wait_lock held and interrupts disabled.
- */
-static void mark_wakeup_next_waiter(struct wake_q_head *wake_q,
-				    struct rt_mutex *lock)
-{
-	struct rt_mutex_waiter *waiter;
+		if (top_waiter != &waiter || adaptive_wait(lock, lock_owner)) {
+			if (mg_off)
+				migrate_enable();
+			schedule();
+			if (mg_off)
+				migrate_disable();
+		}
 
-	raw_spin_lock(&current->pi_lock);
+		raw_spin_lock_irqsave(&lock->wait_lock, flags);
 
-	waiter = rt_mutex_top_waiter(lock);
+		raw_spin_lock(&self->pi_lock);
+		__set_current_state_no_track(TASK_UNINTERRUPTIBLE);
+		raw_spin_unlock(&self->pi_lock);
+	}
 
 	/*
-	 * Remove it from current->pi_waiters. We do not adjust a
-	 * possible priority boost right now. We execute wakeup in the
-	 * boosted mode and go back to normal after releasing
-	 * lock->wait_lock.
-	 */
-	rt_mutex_dequeue_pi(current, waiter);
+	 * Restore the task state to current->saved_state. We set it
+	 * to the original state above and the try_to_wake_up() code
+	 * has possibly updated it when a real (non-rtmutex) wakeup
+	 * happened while we were blocked. Clear saved_state so
+	 * try_to_wakeup() does not get confused.
+	 */
+	raw_spin_lock(&self->pi_lock);
+	__set_current_state_no_track(self->saved_state);
+	self->saved_state = TASK_RUNNING;
+	raw_spin_unlock(&self->pi_lock);
 
 	/*
-	 * As we are waking up the top waiter, and the waiter stays
-	 * queued on the lock until it gets the lock, this lock
-	 * obviously has waiters. Just set the bit here and this has
-	 * the added benefit of forcing all new tasks into the
-	 * slow path making sure no task of lower priority than
-	 * the top waiter can steal this lock.
+	 * try_to_take_rt_mutex() sets the waiter bit
+	 * unconditionally. We might have to fix that up:
 	 */
-	lock->owner = (void *) RT_MUTEX_HAS_WAITERS;
+	fixup_rt_mutex_waiters(lock);
 
-	raw_spin_unlock(&current->pi_lock);
+	BUG_ON(rt_mutex_has_waiters(lock) && &waiter == rt_mutex_top_waiter(lock));
+	BUG_ON(!RB_EMPTY_NODE(&waiter.tree_entry));
+
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
-	wake_q_add(wake_q, waiter->task);
+	debug_rt_mutex_free_waiter(&waiter);
 }
 
+static bool __sched __rt_mutex_unlock_common(struct rt_mutex *lock,
+					     struct wake_q_head *wake_q,
+					     struct wake_q_head *wq_sleeper);
 /*
- * Remove a waiter from a lock and give up
- *
- * Must be called with lock->wait_lock held and interrupts disabled. I must
- * have just failed to try_to_take_rt_mutex().
+ * Slow path to release a rt_mutex spin_lock style
  */
-static void remove_waiter(struct rt_mutex *lock,
-			  struct rt_mutex_waiter *waiter)
+static void  noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock)
 {
-	bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock));
-	struct task_struct *owner = rt_mutex_owner(lock);
-	struct rt_mutex *next_lock;
+	unsigned long flags;
+	WAKE_Q(wake_q);
+	WAKE_Q(wake_sleeper_q);
+	bool postunlock;
 
-	raw_spin_lock(&current->pi_lock);
-	rt_mutex_dequeue(lock, waiter);
-	current->pi_blocked_on = NULL;
-	raw_spin_unlock(&current->pi_lock);
+	raw_spin_lock_irqsave(&lock->wait_lock, flags);
+	postunlock = __rt_mutex_unlock_common(lock, &wake_q, &wake_sleeper_q);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
-	/*
-	 * Only update priority if the waiter was the highest priority
-	 * waiter of the lock and there is an owner to update.
-	 */
-	if (!owner || !is_top_waiter)
-		return;
+	if (postunlock)
+		rt_mutex_postunlock(&wake_q, &wake_sleeper_q);
+}
 
-	raw_spin_lock(&owner->pi_lock);
+void __lockfunc rt_spin_lock__no_mg(spinlock_t *lock)
+{
+	rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock, false);
+	spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+}
+EXPORT_SYMBOL(rt_spin_lock__no_mg);
 
-	rt_mutex_dequeue_pi(owner, waiter);
+void __lockfunc rt_spin_lock(spinlock_t *lock)
+{
+	rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock, true);
+	spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+}
+EXPORT_SYMBOL(rt_spin_lock);
 
-	if (rt_mutex_has_waiters(lock))
-		rt_mutex_enqueue_pi(owner, rt_mutex_top_waiter(lock));
+void __lockfunc __rt_spin_lock(struct rt_mutex *lock)
+{
+	rt_spin_lock_fastlock(lock, rt_spin_lock_slowlock, true);
+}
+EXPORT_SYMBOL(__rt_spin_lock);
 
-	__rt_mutex_adjust_prio(owner);
+void __lockfunc __rt_spin_lock__no_mg(struct rt_mutex *lock)
+{
+	rt_spin_lock_fastlock(lock, rt_spin_lock_slowlock, false);
+}
+EXPORT_SYMBOL(__rt_spin_lock__no_mg);
 
-	/* Store the lock on which owner is blocked or NULL */
-	next_lock = task_blocked_on_lock(owner);
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass)
+{
+	spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
+	rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock, true);
+}
+EXPORT_SYMBOL(rt_spin_lock_nested);
+#endif
 
-	raw_spin_unlock(&owner->pi_lock);
+void __lockfunc rt_spin_unlock__no_mg(spinlock_t *lock)
+{
+	/* NOTE: we always pass in '1' for nested, for simplicity */
+	spin_release(&lock->dep_map, 1, _RET_IP_);
+	rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock);
+}
+EXPORT_SYMBOL(rt_spin_unlock__no_mg);
 
-	/*
-	 * Don't walk the chain, if the owner task is not blocked
-	 * itself.
-	 */
+void __lockfunc rt_spin_unlock(spinlock_t *lock)
+{
+	/* NOTE: we always pass in '1' for nested, for simplicity */
+	spin_release(&lock->dep_map, 1, _RET_IP_);
+	rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock);
+	migrate_enable();
+}
+EXPORT_SYMBOL(rt_spin_unlock);
+
+void __lockfunc __rt_spin_unlock(struct rt_mutex *lock)
+{
+	rt_spin_lock_fastunlock(lock, rt_spin_lock_slowunlock);
+}
+EXPORT_SYMBOL(__rt_spin_unlock);
+
+/*
+ * Wait for the lock to get unlocked: instead of polling for an unlock
+ * (like raw spinlocks do), we lock and unlock, to force the kernel to
+ * schedule if there's contention:
+ */
+void __lockfunc rt_spin_unlock_wait(spinlock_t *lock)
+{
+	spin_lock(lock);
+	spin_unlock(lock);
+}
+EXPORT_SYMBOL(rt_spin_unlock_wait);
+
+int __lockfunc rt_spin_trylock__no_mg(spinlock_t *lock)
+{
+	int ret;
+
+	ret = rt_mutex_trylock(&lock->lock);
+	if (ret)
+		spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+	return ret;
+}
+EXPORT_SYMBOL(rt_spin_trylock__no_mg);
+
+int __lockfunc rt_spin_trylock(spinlock_t *lock)
+{
+	int ret;
+
+	migrate_disable();
+	ret = rt_mutex_trylock(&lock->lock);
+	if (ret)
+		spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+	else
+		migrate_enable();
+	return ret;
+}
+EXPORT_SYMBOL(rt_spin_trylock);
+
+int __lockfunc rt_spin_trylock_bh(spinlock_t *lock)
+{
+	int ret;
+
+	local_bh_disable();
+	ret = rt_mutex_trylock(&lock->lock);
+	if (ret) {
+		migrate_disable();
+		spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+	} else
+		local_bh_enable();
+	return ret;
+}
+EXPORT_SYMBOL(rt_spin_trylock_bh);
+
+int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags)
+{
+	int ret;
+
+	*flags = 0;
+	ret = rt_mutex_trylock(&lock->lock);
+	if (ret) {
+		migrate_disable();
+		spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+	}
+	return ret;
+}
+EXPORT_SYMBOL(rt_spin_trylock_irqsave);
+
+int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock)
+{
+	/* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */
+	if (atomic_add_unless(atomic, -1, 1))
+		return 0;
+	rt_spin_lock(lock);
+	if (atomic_dec_and_test(atomic))
+		return 1;
+	rt_spin_unlock(lock);
+	return 0;
+}
+EXPORT_SYMBOL(atomic_dec_and_spin_lock);
+
+	void
+__rt_spin_lock_init(spinlock_t *lock, char *name, struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/*
+	 * Make sure we are not reinitializing a held lock:
+	 */
+	debug_check_no_locks_freed((void *)lock, sizeof(*lock));
+	lockdep_init_map(&lock->dep_map, name, key, 0);
+#endif
+}
+EXPORT_SYMBOL(__rt_spin_lock_init);
+
+#endif /* PREEMPT_RT_FULL */
+
+#ifdef CONFIG_PREEMPT_RT_FULL
+	static inline int __sched
+__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx)
+{
+	struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock);
+	struct ww_acquire_ctx *hold_ctx = ACCESS_ONCE(ww->ctx);
+
+	if (!hold_ctx)
+		return 0;
+
+	if (unlikely(ctx == hold_ctx))
+		return -EALREADY;
+
+	if (ctx->stamp - hold_ctx->stamp <= LONG_MAX &&
+	    (ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) {
+#ifdef CONFIG_DEBUG_MUTEXES
+		DEBUG_LOCKS_WARN_ON(ctx->contending_lock);
+		ctx->contending_lock = ww;
+#endif
+		return -EDEADLK;
+	}
+
+	return 0;
+}
+#else
+	static inline int __sched
+__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx)
+{
+	BUG();
+	return 0;
+}
+
+#endif
+
+static inline int
+try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
+		     struct rt_mutex_waiter *waiter)
+{
+	return __try_to_take_rt_mutex(lock, task, waiter, STEAL_NORMAL);
+}
+
+/*
+ * Task blocks on lock.
+ *
+ * Prepare waiter and propagate pi chain
+ *
+ * This must be called with lock->wait_lock held and interrupts disabled
+ */
+static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
+				   struct rt_mutex_waiter *waiter,
+				   struct task_struct *task,
+				   enum rtmutex_chainwalk chwalk)
+{
+	struct task_struct *owner = rt_mutex_owner(lock);
+	struct rt_mutex_waiter *top_waiter = waiter;
+	struct rt_mutex *next_lock;
+	int chain_walk = 0, res;
+
+	lockdep_assert_held(&lock->wait_lock);
+
+	/*
+	 * Early deadlock detection. We really don't want the task to
+	 * enqueue on itself just to untangle the mess later. It's not
+	 * only an optimization. We drop the locks, so another waiter
+	 * can come in before the chain walk detects the deadlock. So
+	 * the other will detect the deadlock and return -EDEADLOCK,
+	 * which is wrong, as the other waiter is not in a deadlock
+	 * situation.
+	 */
+	if (owner == task)
+		return -EDEADLK;
+
+	raw_spin_lock(&task->pi_lock);
+
+	/*
+	 * In the case of futex requeue PI, this will be a proxy
+	 * lock. The task will wake unaware that it is enqueueed on
+	 * this lock. Avoid blocking on two locks and corrupting
+	 * pi_blocked_on via the PI_WAKEUP_INPROGRESS
+	 * flag. futex_wait_requeue_pi() sets this when it wakes up
+	 * before requeue (due to a signal or timeout). Do not enqueue
+	 * the task if PI_WAKEUP_INPROGRESS is set.
+	 */
+	if (task != current && task->pi_blocked_on == PI_WAKEUP_INPROGRESS) {
+		raw_spin_unlock(&task->pi_lock);
+		return -EAGAIN;
+	}
+
+	BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on));
+
+	rt_mutex_adjust_prio(task);
+	waiter->task = task;
+	waiter->lock = lock;
+	waiter->prio = task->prio;
+	waiter->deadline = task->dl.deadline;
+
+	/* Get the top priority waiter on the lock */
+	if (rt_mutex_has_waiters(lock))
+		top_waiter = rt_mutex_top_waiter(lock);
+	rt_mutex_enqueue(lock, waiter);
+
+	task->pi_blocked_on = waiter;
+
+	raw_spin_unlock(&task->pi_lock);
+
+	if (!owner)
+		return 0;
+
+	raw_spin_lock(&owner->pi_lock);
+	if (waiter == rt_mutex_top_waiter(lock)) {
+		rt_mutex_dequeue_pi(owner, top_waiter);
+		rt_mutex_enqueue_pi(owner, waiter);
+
+		rt_mutex_adjust_prio(owner);
+		if (rt_mutex_real_waiter(owner->pi_blocked_on))
+			chain_walk = 1;
+	} else if (rt_mutex_cond_detect_deadlock(waiter, chwalk)) {
+		chain_walk = 1;
+	}
+
+	/* Store the lock on which owner is blocked or NULL */
+	next_lock = task_blocked_on_lock(owner);
+
+	raw_spin_unlock(&owner->pi_lock);
+	/*
+	 * Even if full deadlock detection is on, if the owner is not
+	 * blocked itself, we can avoid finding this out in the chain
+	 * walk.
+	 */
+	if (!chain_walk || !next_lock)
+		return 0;
+
+	/*
+	 * The owner can't disappear while holding a lock,
+	 * so the owner struct is protected by wait_lock.
+	 * Gets dropped in rt_mutex_adjust_prio_chain()!
+	 */
+	get_task_struct(owner);
+
+	raw_spin_unlock_irq(&lock->wait_lock);
+
+	res = rt_mutex_adjust_prio_chain(owner, chwalk, lock,
+					 next_lock, waiter, task);
+
+	raw_spin_lock_irq(&lock->wait_lock);
+
+	return res;
+}
+
+/*
+ * Remove the top waiter from the current tasks pi waiter tree and
+ * queue it up.
+ *
+ * Called with lock->wait_lock held and interrupts disabled.
+ */
+static void mark_wakeup_next_waiter(struct wake_q_head *wake_q,
+				    struct wake_q_head *wake_sleeper_q,
+				    struct rt_mutex *lock)
+{
+	struct rt_mutex_waiter *waiter;
+
+	raw_spin_lock(&current->pi_lock);
+
+	waiter = rt_mutex_top_waiter(lock);
+
+	/*
+	 * Remove it from current->pi_waiters and deboost.
+	 *
+	 * We must in fact deboost here in order to ensure we call
+	 * rt_mutex_setprio() to update p->pi_top_task before the
+	 * task unblocks.
+	 */
+	rt_mutex_dequeue_pi(current, waiter);
+	rt_mutex_adjust_prio(current);
+
+	/*
+	 * As we are waking up the top waiter, and the waiter stays
+	 * queued on the lock until it gets the lock, this lock
+	 * obviously has waiters. Just set the bit here and this has
+	 * the added benefit of forcing all new tasks into the
+	 * slow path making sure no task of lower priority than
+	 * the top waiter can steal this lock.
+	 */
+	lock->owner = (void *) RT_MUTEX_HAS_WAITERS;
+
+	/*
+	 * We deboosted before waking the top waiter task such that we don't
+	 * run two tasks with the 'same' priority (and ensure the
+	 * p->pi_top_task pointer points to a blocked task). This however can
+	 * lead to priority inversion if we would get preempted after the
+	 * deboost but before waking our donor task, hence the preempt_disable()
+	 * before unlock.
+	 *
+	 * Pairs with preempt_enable() in rt_mutex_postunlock();
+	 */
+	preempt_disable();
+	if (waiter->savestate)
+		wake_q_add_sleeper(wake_sleeper_q, waiter->task);
+	else
+		wake_q_add(wake_q, waiter->task);
+	raw_spin_unlock(&current->pi_lock);
+}
+
+/*
+ * Remove a waiter from a lock and give up
+ *
+ * Must be called with lock->wait_lock held and interrupts disabled. I must
+ * have just failed to try_to_take_rt_mutex().
+ */
+static void remove_waiter(struct rt_mutex *lock,
+			  struct rt_mutex_waiter *waiter)
+{
+	bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock));
+	struct task_struct *owner = rt_mutex_owner(lock);
+	struct rt_mutex *next_lock = NULL;
+
+	lockdep_assert_held(&lock->wait_lock);
+
+	raw_spin_lock(&current->pi_lock);
+	rt_mutex_dequeue(lock, waiter);
+	current->pi_blocked_on = NULL;
+	raw_spin_unlock(&current->pi_lock);
+
+	/*
+	 * Only update priority if the waiter was the highest priority
+	 * waiter of the lock and there is an owner to update.
+	 */
+	if (!owner || !is_top_waiter)
+		return;
+
+	raw_spin_lock(&owner->pi_lock);
+
+	rt_mutex_dequeue_pi(owner, waiter);
+
+	if (rt_mutex_has_waiters(lock))
+		rt_mutex_enqueue_pi(owner, rt_mutex_top_waiter(lock));
+
+	rt_mutex_adjust_prio(owner);
+
+	/* Store the lock on which owner is blocked or NULL */
+	if (rt_mutex_real_waiter(owner->pi_blocked_on))
+		next_lock = task_blocked_on_lock(owner);
+
+	raw_spin_unlock(&owner->pi_lock);
+
+	/*
+	 * Don't walk the chain, if the owner task is not blocked
+	 * itself.
+	 */
 	if (!next_lock)
 		return;
 
@@ -1138,21 +1586,30 @@ void rt_mutex_adjust_pi(struct task_stru
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
 
 	waiter = task->pi_blocked_on;
-	if (!waiter || (waiter->prio == task->prio &&
-			!dl_prio(task->prio))) {
+	if (!rt_mutex_real_waiter(waiter) ||
+	    rt_mutex_waiter_equal(waiter, task_to_waiter(task))) {
 		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 		return;
 	}
 	next_lock = waiter->lock;
-	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 
 	/* gets dropped in rt_mutex_adjust_prio_chain()! */
 	get_task_struct(task);
 
+	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 	rt_mutex_adjust_prio_chain(task, RT_MUTEX_MIN_CHAINWALK, NULL,
 				   next_lock, NULL, task);
 }
 
+void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter, bool savestate)
+{
+	debug_rt_mutex_init_waiter(waiter);
+	RB_CLEAR_NODE(&waiter->pi_tree_entry);
+	RB_CLEAR_NODE(&waiter->tree_entry);
+	waiter->task = NULL;
+	waiter->savestate = savestate;
+}
+
 /**
  * __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop
  * @lock:		 the rt_mutex to take
@@ -1166,7 +1623,8 @@ void rt_mutex_adjust_pi(struct task_stru
 static int __sched
 __rt_mutex_slowlock(struct rt_mutex *lock, int state,
 		    struct hrtimer_sleeper *timeout,
-		    struct rt_mutex_waiter *waiter)
+		    struct rt_mutex_waiter *waiter,
+		    struct ww_acquire_ctx *ww_ctx)
 {
 	int ret = 0;
 
@@ -1175,16 +1633,17 @@ __rt_mutex_slowlock(struct rt_mutex *loc
 		if (try_to_take_rt_mutex(lock, current, waiter))
 			break;
 
-		/*
-		 * TASK_INTERRUPTIBLE checks for signals and
-		 * timeout. Ignored otherwise.
-		 */
-		if (unlikely(state == TASK_INTERRUPTIBLE)) {
-			/* Signal pending? */
-			if (signal_pending(current))
-				ret = -EINTR;
-			if (timeout && !timeout->task)
-				ret = -ETIMEDOUT;
+		if (timeout && !timeout->task) {
+			ret = -ETIMEDOUT;
+			break;
+		}
+		if (signal_pending_state(state, current)) {
+			ret = -EINTR;
+			break;
+		}
+
+		if (ww_ctx && ww_ctx->acquired > 0) {
+			ret = __mutex_lock_check_stamp(lock, ww_ctx);
 			if (ret)
 				break;
 		}
@@ -1207,51 +1666,110 @@ static void rt_mutex_handle_deadlock(int
 				     struct rt_mutex_waiter *w)
 {
 	/*
-	 * If the result is not -EDEADLOCK or the caller requested
-	 * deadlock detection, nothing to do here.
+	 * If the result is not -EDEADLOCK or the caller requested
+	 * deadlock detection, nothing to do here.
+	 */
+	if (res != -EDEADLOCK || detect_deadlock)
+		return;
+
+	/*
+	 * Yell lowdly and stop the task right here.
+	 */
+	rt_mutex_print_deadlock(w);
+	while (1) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		schedule();
+	}
+}
+
+static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww,
+						   struct ww_acquire_ctx *ww_ctx)
+{
+#ifdef CONFIG_DEBUG_MUTEXES
+	/*
+	 * If this WARN_ON triggers, you used ww_mutex_lock to acquire,
+	 * but released with a normal mutex_unlock in this call.
+	 *
+	 * This should never happen, always use ww_mutex_unlock.
+	 */
+	DEBUG_LOCKS_WARN_ON(ww->ctx);
+
+	/*
+	 * Not quite done after calling ww_acquire_done() ?
+	 */
+	DEBUG_LOCKS_WARN_ON(ww_ctx->done_acquire);
+
+	if (ww_ctx->contending_lock) {
+		/*
+		 * After -EDEADLK you tried to
+		 * acquire a different ww_mutex? Bad!
+		 */
+		DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock != ww);
+
+		/*
+		 * You called ww_mutex_lock after receiving -EDEADLK,
+		 * but 'forgot' to unlock everything else first?
+		 */
+		DEBUG_LOCKS_WARN_ON(ww_ctx->acquired > 0);
+		ww_ctx->contending_lock = NULL;
+	}
+
+	/*
+	 * Naughty, using a different class will lead to undefined behavior!
+	 */
+	DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class);
+#endif
+	ww_ctx->acquired++;
+}
+
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void ww_mutex_account_lock(struct rt_mutex *lock,
+				  struct ww_acquire_ctx *ww_ctx)
+{
+	struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock);
+	struct rt_mutex_waiter *waiter, *n;
+
+	/*
+	 * This branch gets optimized out for the common case,
+	 * and is only important for ww_mutex_lock.
 	 */
-	if (res != -EDEADLOCK || detect_deadlock)
-		return;
+	ww_mutex_lock_acquired(ww, ww_ctx);
+	ww->ctx = ww_ctx;
 
 	/*
-	 * Yell lowdly and stop the task right here.
+	 * Give any possible sleeping processes the chance to wake up,
+	 * so they can recheck if they have to back off.
 	 */
-	rt_mutex_print_deadlock(w);
-	while (1) {
-		set_current_state(TASK_INTERRUPTIBLE);
-		schedule();
+	rbtree_postorder_for_each_entry_safe(waiter, n, &lock->waiters,
+					     tree_entry) {
+		/* XXX debug rt mutex waiter wakeup */
+
+		BUG_ON(waiter->lock != lock);
+		rt_mutex_wake_waiter(waiter);
 	}
 }
 
-/*
- * Slow path lock function:
- */
-static int __sched
-rt_mutex_slowlock(struct rt_mutex *lock, int state,
-		  struct hrtimer_sleeper *timeout,
-		  enum rtmutex_chainwalk chwalk)
-{
-	struct rt_mutex_waiter waiter;
-	unsigned long flags;
-	int ret = 0;
+#else
 
-	debug_rt_mutex_init_waiter(&waiter);
-	RB_CLEAR_NODE(&waiter.pi_tree_entry);
-	RB_CLEAR_NODE(&waiter.tree_entry);
+static void ww_mutex_account_lock(struct rt_mutex *lock,
+				  struct ww_acquire_ctx *ww_ctx)
+{
+	BUG();
+}
+#endif
 
-	/*
-	 * Technically we could use raw_spin_[un]lock_irq() here, but this can
-	 * be called in early boot if the cmpxchg() fast path is disabled
-	 * (debug, no architecture support). In this case we will acquire the
-	 * rtmutex with lock->wait_lock held. But we cannot unconditionally
-	 * enable interrupts in that early boot case. So we need to use the
-	 * irqsave/restore variants.
-	 */
-	raw_spin_lock_irqsave(&lock->wait_lock, flags);
+int __sched rt_mutex_slowlock_locked(struct rt_mutex *lock, int state,
+				     struct hrtimer_sleeper *timeout,
+				     enum rtmutex_chainwalk chwalk,
+				     struct ww_acquire_ctx *ww_ctx,
+				     struct rt_mutex_waiter *waiter)
+{
+	int ret;
 
 	/* Try to acquire the lock again: */
 	if (try_to_take_rt_mutex(lock, current, NULL)) {
-		raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
+		if (ww_ctx)
+			ww_mutex_account_lock(lock, ww_ctx);
 		return 0;
 	}
 
@@ -1261,17 +1779,27 @@ rt_mutex_slowlock(struct rt_mutex *lock,
 	if (unlikely(timeout))
 		hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);
 
-	ret = task_blocks_on_rt_mutex(lock, &waiter, current, chwalk);
+	ret = task_blocks_on_rt_mutex(lock, waiter, current, chwalk);
 
-	if (likely(!ret))
+	if (likely(!ret)) {
 		/* sleep on the mutex */
-		ret = __rt_mutex_slowlock(lock, state, timeout, &waiter);
+		ret = __rt_mutex_slowlock(lock, state, timeout, waiter,
+					  ww_ctx);
+	} else if (ww_ctx) {
+		/* ww_mutex received EDEADLK, let it become EALREADY */
+		ret = __mutex_lock_check_stamp(lock, ww_ctx);
+		BUG_ON(!ret);
+	}
 
 	if (unlikely(ret)) {
 		__set_current_state(TASK_RUNNING);
 		if (rt_mutex_has_waiters(lock))
-			remove_waiter(lock, &waiter);
-		rt_mutex_handle_deadlock(ret, chwalk, &waiter);
+			remove_waiter(lock, waiter);
+		/* ww_mutex want to report EDEADLK/EALREADY, let them */
+		if (!ww_ctx)
+			rt_mutex_handle_deadlock(ret, chwalk, waiter);
+	} else if (ww_ctx) {
+		ww_mutex_account_lock(lock, ww_ctx);
 	}
 
 	/*
@@ -1279,6 +1807,36 @@ rt_mutex_slowlock(struct rt_mutex *lock,
 	 * unconditionally. We might have to fix that up.
 	 */
 	fixup_rt_mutex_waiters(lock);
+	return ret;
+}
+
+/*
+ * Slow path lock function:
+ */
+static int __sched
+rt_mutex_slowlock(struct rt_mutex *lock, int state,
+		  struct hrtimer_sleeper *timeout,
+		  enum rtmutex_chainwalk chwalk,
+		  struct ww_acquire_ctx *ww_ctx)
+{
+	struct rt_mutex_waiter waiter;
+	unsigned long flags;
+	int ret = 0;
+
+	rt_mutex_init_waiter(&waiter, false);
+
+	/*
+	 * Technically we could use raw_spin_[un]lock_irq() here, but this can
+	 * be called in early boot if the cmpxchg() fast path is disabled
+	 * (debug, no architecture support). In this case we will acquire the
+	 * rtmutex with lock->wait_lock held. But we cannot unconditionally
+	 * enable interrupts in that early boot case. So we need to use the
+	 * irqsave/restore variants.
+	 */
+	raw_spin_lock_irqsave(&lock->wait_lock, flags);
+
+	ret = rt_mutex_slowlock_locked(lock, state, timeout, chwalk, ww_ctx,
+				       &waiter);
 
 	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
@@ -1328,10 +1886,12 @@ static inline int rt_mutex_slowtrylock(s
 
 /*
  * Slow path to release a rt-mutex.
- * Return whether the current task needs to undo a potential priority boosting.
+ *
+ * Return whether the current task needs to call rt_mutex_postunlock().
  */
 static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
-					struct wake_q_head *wake_q)
+					struct wake_q_head *wake_q,
+					struct wake_q_head *wake_sleeper_q)
 {
 	unsigned long flags;
 
@@ -1340,8 +1900,6 @@ static bool __sched rt_mutex_slowunlock(
 
 	debug_rt_mutex_unlock(lock);
 
-	rt_mutex_deadlock_account_unlock(current);
-
 	/*
 	 * We must be careful here if the fast path is enabled. If we
 	 * have no waiters queued we cannot set owner to NULL here
@@ -1387,12 +1945,10 @@ static bool __sched rt_mutex_slowunlock(
 	 *
 	 * Queue the next waiter for wakeup once we release the wait_lock.
 	 */
-	mark_wakeup_next_waiter(wake_q, lock);
-
+	mark_wakeup_next_waiter(wake_q, wake_sleeper_q, lock);
 	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
-	/* check PI boosting */
-	return true;
+	return true; /* call rt_mutex_postunlock() */
 }
 
 /*
@@ -1403,63 +1959,85 @@ static bool __sched rt_mutex_slowunlock(
  */
 static inline int
 rt_mutex_fastlock(struct rt_mutex *lock, int state,
+		  struct ww_acquire_ctx *ww_ctx,
 		  int (*slowfn)(struct rt_mutex *lock, int state,
 				struct hrtimer_sleeper *timeout,
-				enum rtmutex_chainwalk chwalk))
+				enum rtmutex_chainwalk chwalk,
+				struct ww_acquire_ctx *ww_ctx))
 {
-	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) {
-		rt_mutex_deadlock_account_lock(lock, current);
+	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
 		return 0;
-	} else
-		return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK);
+
+	return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK, ww_ctx);
 }
 
 static inline int
 rt_mutex_timed_fastlock(struct rt_mutex *lock, int state,
 			struct hrtimer_sleeper *timeout,
 			enum rtmutex_chainwalk chwalk,
+			struct ww_acquire_ctx *ww_ctx,
 			int (*slowfn)(struct rt_mutex *lock, int state,
 				      struct hrtimer_sleeper *timeout,
-				      enum rtmutex_chainwalk chwalk))
+				      enum rtmutex_chainwalk chwalk,
+				      struct ww_acquire_ctx *ww_ctx))
 {
 	if (chwalk == RT_MUTEX_MIN_CHAINWALK &&
-	    likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) {
-		rt_mutex_deadlock_account_lock(lock, current);
+	    likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
 		return 0;
-	} else
-		return slowfn(lock, state, timeout, chwalk);
+
+	return slowfn(lock, state, timeout, chwalk, ww_ctx);
 }
 
 static inline int
 rt_mutex_fasttrylock(struct rt_mutex *lock,
 		     int (*slowfn)(struct rt_mutex *lock))
 {
-	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) {
-		rt_mutex_deadlock_account_lock(lock, current);
+	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
 		return 1;
-	}
+
 	return slowfn(lock);
 }
 
+/*
+ * Performs the wakeup of the the top-waiter and re-enables preemption.
+ */
+void rt_mutex_postunlock(struct wake_q_head *wake_q,
+			 struct wake_q_head *wq_sleeper)
+{
+	wake_up_q(wake_q);
+	wake_up_q_sleeper(wq_sleeper);
+
+	/* Pairs with preempt_disable() in rt_mutex_slowunlock() */
+	preempt_enable();
+}
+
 static inline void
 rt_mutex_fastunlock(struct rt_mutex *lock,
 		    bool (*slowfn)(struct rt_mutex *lock,
-				   struct wake_q_head *wqh))
+				   struct wake_q_head *wqh,
+				   struct wake_q_head *wq_sleeper))
 {
 	WAKE_Q(wake_q);
+	WAKE_Q(wake_sleeper_q);
 
-	if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) {
-		rt_mutex_deadlock_account_unlock(current);
+	if (likely(rt_mutex_cmpxchg_release(lock, current, NULL)))
+		return;
 
-	} else {
-		bool deboost = slowfn(lock, &wake_q);
+	if (slowfn(lock, &wake_q,  &wake_sleeper_q))
+		rt_mutex_postunlock(&wake_q, &wake_sleeper_q);
+}
 
-		wake_up_q(&wake_q);
+/**
+ * rt_mutex_lock_state - lock a rt_mutex with a given state
+ *
+ * @lock:	The rt_mutex to be locked
+ * @state:	The state to set when blocking on the rt_mutex
+ */
+int __sched rt_mutex_lock_state(struct rt_mutex *lock, int state)
+{
+	might_sleep();
 
-		/* Undo pi boosting if necessary: */
-		if (deboost)
-			rt_mutex_adjust_prio(current);
-	}
+	return rt_mutex_fastlock(lock, state, NULL, rt_mutex_slowlock);
 }
 
 /**
@@ -1469,15 +2047,13 @@ rt_mutex_fastunlock(struct rt_mutex *loc
  */
 void __sched rt_mutex_lock(struct rt_mutex *lock)
 {
-	might_sleep();
-
-	rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock);
+	rt_mutex_lock_state(lock, TASK_UNINTERRUPTIBLE);
 }
 EXPORT_SYMBOL_GPL(rt_mutex_lock);
 
 /**
  * rt_mutex_lock_interruptible - lock a rt_mutex interruptible
- *
+ **
  * @lock:		the rt_mutex to be locked
  *
  * Returns:
@@ -1486,23 +2062,32 @@ EXPORT_SYMBOL_GPL(rt_mutex_lock);
  */
 int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock)
 {
-	might_sleep();
-
-	return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, rt_mutex_slowlock);
+	return rt_mutex_lock_state(lock, TASK_INTERRUPTIBLE);
 }
 EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible);
 
-/*
- * Futex variant with full deadlock detection.
+/**
+ * rt_mutex_lock_killable - lock a rt_mutex killable
+ *
+ * @lock:              the rt_mutex to be locked
+ * @detect_deadlock:   deadlock detection on/off
+ *
+ * Returns:
+ *  0          on success
+ * -EINTR      when interrupted by a signal
  */
-int rt_mutex_timed_futex_lock(struct rt_mutex *lock,
-			      struct hrtimer_sleeper *timeout)
+int __sched rt_mutex_lock_killable(struct rt_mutex *lock)
 {
-	might_sleep();
+	return rt_mutex_lock_state(lock, TASK_KILLABLE);
+}
+EXPORT_SYMBOL_GPL(rt_mutex_lock_killable);
 
-	return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout,
-				       RT_MUTEX_FULL_CHAINWALK,
-				       rt_mutex_slowlock);
+/*
+ * Futex variant, must not use fastpath.
+ */
+int __sched rt_mutex_futex_trylock(struct rt_mutex *lock)
+{
+	return rt_mutex_slowtrylock(lock);
 }
 
 /**
@@ -1525,6 +2110,7 @@ rt_mutex_timed_lock(struct rt_mutex *loc
 
 	return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout,
 				       RT_MUTEX_MIN_CHAINWALK,
+				       NULL,
 				       rt_mutex_slowlock);
 }
 EXPORT_SYMBOL_GPL(rt_mutex_timed_lock);
@@ -1542,7 +2128,11 @@ EXPORT_SYMBOL_GPL(rt_mutex_timed_lock);
  */
 int __sched rt_mutex_trylock(struct rt_mutex *lock)
 {
+#ifdef CONFIG_PREEMPT_RT_FULL
+	if (WARN_ON_ONCE(in_irq() || in_nmi()))
+#else
 	if (WARN_ON_ONCE(in_irq() || in_nmi() || in_serving_softirq()))
+#endif
 		return 0;
 
 	return rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock);
@@ -1560,21 +2150,53 @@ void __sched rt_mutex_unlock(struct rt_m
 }
 EXPORT_SYMBOL_GPL(rt_mutex_unlock);
 
+static bool __sched __rt_mutex_unlock_common(struct rt_mutex *lock,
+					     struct wake_q_head *wake_q,
+					     struct wake_q_head *wq_sleeper)
+{
+	lockdep_assert_held(&lock->wait_lock);
+
+	debug_rt_mutex_unlock(lock);
+
+	if (!rt_mutex_has_waiters(lock)) {
+		lock->owner = NULL;
+		return false; /* done */
+	}
+
+	/*
+	 * We've already deboosted, mark_wakeup_next_waiter() will
+	 * retain preempt_disabled when we drop the wait_lock, to
+	 * avoid inversion prior to the wakeup.  preempt_disable()
+	 * therein pairs with rt_mutex_postunlock().
+	 */
+	mark_wakeup_next_waiter(wake_q, wq_sleeper, lock);
+
+	return true; /* call postunlock() */
+}
+
 /**
- * rt_mutex_futex_unlock - Futex variant of rt_mutex_unlock
- * @lock: the rt_mutex to be unlocked
- *
- * Returns: true/false indicating whether priority adjustment is
- * required or not.
+ * Futex variant, that since futex variants do not use the fast-path, can be
+ * simple and will not need to retry.
  */
-bool __sched rt_mutex_futex_unlock(struct rt_mutex *lock,
-				   struct wake_q_head *wqh)
+bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock,
+				    struct wake_q_head *wake_q,
+				    struct wake_q_head *wq_sleeper)
 {
-	if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) {
-		rt_mutex_deadlock_account_unlock(current);
-		return false;
-	}
-	return rt_mutex_slowunlock(lock, wqh);
+	return __rt_mutex_unlock_common(lock, wake_q, wq_sleeper);
+}
+
+void __sched rt_mutex_futex_unlock(struct rt_mutex *lock)
+{
+	WAKE_Q(wake_q);
+	WAKE_Q(wake_sleeper_q);
+	bool postunlock;
+
+	raw_spin_lock_irq(&lock->wait_lock);
+	postunlock = __rt_mutex_futex_unlock(lock, &wake_q, &wake_sleeper_q);
+	raw_spin_unlock_irq(&lock->wait_lock);
+
+	if (postunlock)
+		rt_mutex_postunlock(&wake_q, &wake_sleeper_q);
 }
 
 /**
@@ -1607,13 +2229,12 @@ EXPORT_SYMBOL_GPL(rt_mutex_destroy);
 void __rt_mutex_init(struct rt_mutex *lock, const char *name)
 {
 	lock->owner = NULL;
-	raw_spin_lock_init(&lock->wait_lock);
 	lock->waiters = RB_ROOT;
 	lock->waiters_leftmost = NULL;
 
 	debug_rt_mutex_init(lock, name);
 }
-EXPORT_SYMBOL_GPL(__rt_mutex_init);
+EXPORT_SYMBOL(__rt_mutex_init);
 
 /**
  * rt_mutex_init_proxy_locked - initialize and lock a rt_mutex on behalf of a
@@ -1628,10 +2249,9 @@ EXPORT_SYMBOL_GPL(__rt_mutex_init);
 void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
 				struct task_struct *proxy_owner)
 {
-	__rt_mutex_init(lock, NULL);
+	rt_mutex_init(lock);
 	debug_rt_mutex_proxy_lock(lock, proxy_owner);
 	rt_mutex_set_owner(lock, proxy_owner);
-	rt_mutex_deadlock_account_lock(lock, proxy_owner);
 }
 
 /**
@@ -1647,34 +2267,45 @@ void rt_mutex_proxy_unlock(struct rt_mut
 {
 	debug_rt_mutex_proxy_unlock(lock);
 	rt_mutex_set_owner(lock, NULL);
-	rt_mutex_deadlock_account_unlock(proxy_owner);
 }
 
-/**
- * rt_mutex_start_proxy_lock() - Start lock acquisition for another task
- * @lock:		the rt_mutex to take
- * @waiter:		the pre-initialized rt_mutex_waiter
- * @task:		the task to prepare
- *
- * Returns:
- *  0 - task blocked on lock
- *  1 - acquired the lock for task, caller should wake it up
- * <0 - error
- *
- * Special API call for FUTEX_REQUEUE_PI support.
- */
-int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
+int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 			      struct rt_mutex_waiter *waiter,
 			      struct task_struct *task)
 {
 	int ret;
 
-	raw_spin_lock_irq(&lock->wait_lock);
+	if (try_to_take_rt_mutex(lock, task, NULL))
+		return 1;
 
-	if (try_to_take_rt_mutex(lock, task, NULL)) {
+#ifdef CONFIG_PREEMPT_RT_FULL
+	/*
+	 * In PREEMPT_RT there's an added race.
+	 * If the task, that we are about to requeue, times out,
+	 * it can set the PI_WAKEUP_INPROGRESS. This tells the requeue
+	 * to skip this task. But right after the task sets
+	 * its pi_blocked_on to PI_WAKEUP_INPROGRESS it can then
+	 * block on the spin_lock(&hb->lock), which in RT is an rtmutex.
+	 * This will replace the PI_WAKEUP_INPROGRESS with the actual
+	 * lock that it blocks on. We *must not* place this task
+	 * on this proxy lock in that case.
+	 *
+	 * To prevent this race, we first take the task's pi_lock
+	 * and check if it has updated its pi_blocked_on. If it has,
+	 * we assume that it woke up and we return -EAGAIN.
+	 * Otherwise, we set the task's pi_blocked_on to
+	 * PI_REQUEUE_INPROGRESS, so that if the task is waking up
+	 * it will know that we are in the process of requeuing it.
+	 */
+	raw_spin_lock(&task->pi_lock);
+	if (task->pi_blocked_on) {
+		raw_spin_unlock(&task->pi_lock);
 		raw_spin_unlock_irq(&lock->wait_lock);
-		return 1;
+		return -EAGAIN;
 	}
+	task->pi_blocked_on = PI_REQUEUE_INPROGRESS;
+	raw_spin_unlock(&task->pi_lock);
+#endif
 
 	/* We enforce deadlock detection for futexes */
 	ret = task_blocks_on_rt_mutex(lock, waiter, task,
@@ -1690,17 +2321,41 @@ int rt_mutex_start_proxy_lock(struct rt_
 		ret = 0;
 	}
 
-	if (unlikely(ret))
+	if (ret && rt_mutex_has_waiters(lock))
 		remove_waiter(lock, waiter);
 
-	raw_spin_unlock_irq(&lock->wait_lock);
-
 	debug_rt_mutex_print_deadlock(waiter);
 
 	return ret;
 }
 
 /**
+ * rt_mutex_start_proxy_lock() - Start lock acquisition for another task
+ * @lock:		the rt_mutex to take
+ * @waiter:		the pre-initialized rt_mutex_waiter
+ * @task:		the task to prepare
+ *
+ * Returns:
+ *  0 - task blocked on lock
+ *  1 - acquired the lock for task, caller should wake it up
+ * <0 - error
+ *
+ * Special API call for FUTEX_REQUEUE_PI support.
+ */
+int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
+			      struct rt_mutex_waiter *waiter,
+			      struct task_struct *task)
+{
+	int ret;
+
+	raw_spin_lock_irq(&lock->wait_lock);
+	ret = __rt_mutex_start_proxy_lock(lock, waiter, task);
+	raw_spin_unlock_irq(&lock->wait_lock);
+
+	return ret;
+}
+
+/**
  * rt_mutex_next_owner - return the next owner of the lock
  *
  * @lock: the rt lock query
@@ -1721,36 +2376,106 @@ struct task_struct *rt_mutex_next_owner(
 }
 
 /**
- * rt_mutex_finish_proxy_lock() - Complete lock acquisition
+ * rt_mutex_wait_proxy_lock() - Wait for lock acquisition
  * @lock:		the rt_mutex we were woken on
  * @to:			the timeout, null if none. hrtimer should already have
  *			been started.
  * @waiter:		the pre-initialized rt_mutex_waiter
  *
- * Complete the lock acquisition started our behalf by another thread.
+ * Wait for the the lock acquisition started on our behalf by
+ * rt_mutex_start_proxy_lock(). Upon failure, the caller must call
+ * rt_mutex_cleanup_proxy_lock().
  *
  * Returns:
  *  0 - success
  * <0 - error, one of -EINTR, -ETIMEDOUT
  *
- * Special API call for PI-futex requeue support
+ * Special API call for PI-futex support
  */
-int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
+int rt_mutex_wait_proxy_lock(struct rt_mutex *lock,
 			       struct hrtimer_sleeper *to,
 			       struct rt_mutex_waiter *waiter)
 {
+	struct task_struct *tsk = current;
 	int ret;
 
 	raw_spin_lock_irq(&lock->wait_lock);
-
+	/* sleep on the mutex */
 	set_current_state(TASK_INTERRUPTIBLE);
+	ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter, NULL);
+	/*
+	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
+	 * have to fix that up.
+	 */
+	fixup_rt_mutex_waiters(lock);
 
-	/* sleep on the mutex */
-	ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter);
+	/*
+	 * RT has a problem here when the wait got interrupted by a timeout
+	 * or a signal. task->pi_blocked_on is still set. The task must
+	 * acquire the hash bucket lock when returning from this function.
+	 *
+	 * If the hash bucket lock is contended then the
+	 * BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on)) in
+	 * task_blocks_on_rt_mutex() will trigger. This can be avoided by
+	 * clearing task->pi_blocked_on which removes the task from the
+	 * boosting chain of the rtmutex. That's correct because the task
+	 * is not longer blocked on it.
+	 */
+	if (ret) {
+		raw_spin_lock(&tsk->pi_lock);
+		tsk->pi_blocked_on = NULL;
+		raw_spin_unlock(&tsk->pi_lock);
+	}
+	raw_spin_unlock_irq(&lock->wait_lock);
 
-	if (unlikely(ret))
-		remove_waiter(lock, waiter);
+	return ret;
+}
+
+/**
+ * rt_mutex_cleanup_proxy_lock() - Cleanup failed lock acquisition
+ * @lock:		the rt_mutex we were woken on
+ * @waiter:		the pre-initialized rt_mutex_waiter
+ *
+ * Attempt to clean up after a failed rt_mutex_wait_proxy_lock().
+ *
+ * Unless we acquired the lock; we're still enqueued on the wait-list and can
+ * in fact still be granted ownership until we're removed. Therefore we can
+ * find we are in fact the owner and must disregard the
+ * rt_mutex_wait_proxy_lock() failure.
+ *
+ * Returns:
+ *  true  - did the cleanup, we done.
+ *  false - we acquired the lock after rt_mutex_wait_proxy_lock() returned,
+ *          caller should disregards its return value.
+ *
+ * Special API call for PI-futex support
+ */
+bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
+				 struct rt_mutex_waiter *waiter)
+{
+	bool cleanup = false;
 
+	raw_spin_lock_irq(&lock->wait_lock);
+	/*
+	 * Do an unconditional try-lock, this deals with the lock stealing
+	 * state where __rt_mutex_futex_unlock() -> mark_wakeup_next_waiter()
+	 * sets a NULL owner.
+	 *
+	 * We're not interested in the return value, because the subsequent
+	 * test on rt_mutex_owner() will infer that. If the trylock succeeded,
+	 * we will own the lock and it will have removed the waiter. If we
+	 * failed the trylock, we're still not owner and we need to remove
+	 * ourselves.
+	 */
+	try_to_take_rt_mutex(lock, current, waiter);
+	/*
+	 * Unless we're the owner; we're still enqueued on the wait_list.
+	 * So check if we became owner, if not, take us off the wait_list.
+	 */
+	if (rt_mutex_owner(lock) != current) {
+		remove_waiter(lock, waiter);
+		cleanup = true;
+	}
 	/*
 	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
 	 * have to fix that up.
@@ -1759,5 +2484,91 @@ int rt_mutex_finish_proxy_lock(struct rt
 
 	raw_spin_unlock_irq(&lock->wait_lock);
 
+	return cleanup;
+}
+
+static inline int
+ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
+{
+#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH
+	unsigned tmp;
+
+	if (ctx->deadlock_inject_countdown-- == 0) {
+		tmp = ctx->deadlock_inject_interval;
+		if (tmp > UINT_MAX/4)
+			tmp = UINT_MAX;
+		else
+			tmp = tmp*2 + tmp + tmp/2;
+
+		ctx->deadlock_inject_interval = tmp;
+		ctx->deadlock_inject_countdown = tmp;
+		ctx->contending_lock = lock;
+
+		ww_mutex_unlock(lock);
+
+		return -EDEADLK;
+	}
+#endif
+
+	return 0;
+}
+
+#ifdef CONFIG_PREEMPT_RT_FULL
+int __sched
+__ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx)
+{
+	int ret;
+
+	might_sleep();
+
+	mutex_acquire_nest(&lock->base.dep_map, 0, 0, &ww_ctx->dep_map, _RET_IP_);
+	ret = rt_mutex_slowlock(&lock->base.lock, TASK_INTERRUPTIBLE, NULL, 0, ww_ctx);
+	if (ret)
+		mutex_release(&lock->base.dep_map, 1, _RET_IP_);
+	else if (!ret && ww_ctx->acquired > 1)
+		return ww_mutex_deadlock_injection(lock, ww_ctx);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(__ww_mutex_lock_interruptible);
+
+int __sched
+__ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ww_ctx)
+{
+	int ret;
+
+	might_sleep();
+
+	mutex_acquire_nest(&lock->base.dep_map, 0, 0, &ww_ctx->dep_map, _RET_IP_);
+	ret = rt_mutex_slowlock(&lock->base.lock, TASK_UNINTERRUPTIBLE, NULL, 0, ww_ctx);
+	if (ret)
+		mutex_release(&lock->base.dep_map, 1, _RET_IP_);
+	else if (!ret && ww_ctx->acquired > 1)
+		return ww_mutex_deadlock_injection(lock, ww_ctx);
+
 	return ret;
 }
+EXPORT_SYMBOL_GPL(__ww_mutex_lock);
+
+void __sched ww_mutex_unlock(struct ww_mutex *lock)
+{
+	int nest = !!lock->ctx;
+
+	/*
+	 * The unlocking fastpath is the 0->1 transition from 'locked'
+	 * into 'unlocked' state:
+	 */
+	if (nest) {
+#ifdef CONFIG_DEBUG_MUTEXES
+		DEBUG_LOCKS_WARN_ON(!lock->ctx->acquired);
+#endif
+		if (lock->ctx->acquired > 0)
+			lock->ctx->acquired--;
+		lock->ctx = NULL;
+	}
+
+	mutex_release(&lock->base.dep_map, nest, _RET_IP_);
+	rt_mutex_unlock(&lock->base.lock);
+}
+EXPORT_SYMBOL(ww_mutex_unlock);
+#endif
Index: linux-4.9.20-rt16/kernel/locking/rtmutex.h
===================================================================
--- linux-4.9.20-rt16.orig/kernel/locking/rtmutex.h
+++ linux-4.9.20-rt16/kernel/locking/rtmutex.h
@@ -11,8 +11,6 @@
  */
 
 #define rt_mutex_deadlock_check(l)			(0)
-#define rt_mutex_deadlock_account_lock(m, t)		do { } while (0)
-#define rt_mutex_deadlock_account_unlock(l)		do { } while (0)
 #define debug_rt_mutex_init_waiter(w)			do { } while (0)
 #define debug_rt_mutex_free_waiter(w)			do { } while (0)
 #define debug_rt_mutex_lock(l)				do { } while (0)
Index: linux-4.9.20-rt16/kernel/locking/rtmutex_common.h
===================================================================
--- linux-4.9.20-rt16.orig/kernel/locking/rtmutex_common.h
+++ linux-4.9.20-rt16/kernel/locking/rtmutex_common.h
@@ -27,12 +27,14 @@ struct rt_mutex_waiter {
 	struct rb_node          pi_tree_entry;
 	struct task_struct	*task;
 	struct rt_mutex		*lock;
+	bool			savestate;
 #ifdef CONFIG_DEBUG_RT_MUTEXES
 	unsigned long		ip;
 	struct pid		*deadlock_task_pid;
 	struct rt_mutex		*deadlock_lock;
 #endif
 	int prio;
+	u64 deadline;
 };
 
 /*
@@ -98,21 +100,45 @@ enum rtmutex_chainwalk {
 /*
  * PI-futex support (proxy locking functions, etc.):
  */
+#define PI_WAKEUP_INPROGRESS	((struct rt_mutex_waiter *) 1)
+#define PI_REQUEUE_INPROGRESS	((struct rt_mutex_waiter *) 2)
+
 extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock);
 extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
 				       struct task_struct *proxy_owner);
 extern void rt_mutex_proxy_unlock(struct rt_mutex *lock,
 				  struct task_struct *proxy_owner);
+extern void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter, bool savetate);
+extern int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
+				     struct rt_mutex_waiter *waiter,
+				     struct task_struct *task);
 extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 				     struct rt_mutex_waiter *waiter,
 				     struct task_struct *task);
-extern int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
-				      struct hrtimer_sleeper *to,
-				      struct rt_mutex_waiter *waiter);
-extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to);
-extern bool rt_mutex_futex_unlock(struct rt_mutex *lock,
-				  struct wake_q_head *wqh);
-extern void rt_mutex_adjust_prio(struct task_struct *task);
+extern int rt_mutex_wait_proxy_lock(struct rt_mutex *lock,
+			       struct hrtimer_sleeper *to,
+			       struct rt_mutex_waiter *waiter);
+extern bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
+				 struct rt_mutex_waiter *waiter);
+
+extern int rt_mutex_futex_trylock(struct rt_mutex *l);
+
+extern void rt_mutex_futex_unlock(struct rt_mutex *lock);
+extern bool __rt_mutex_futex_unlock(struct rt_mutex *lock,
+				 struct wake_q_head *wqh,
+				 struct wake_q_head *wq_sleeper);
+
+extern void rt_mutex_postunlock(struct wake_q_head *wake_q,
+				struct wake_q_head *wq_sleeper);
+
+/* RW semaphore special interface */
+struct ww_acquire_ctx;
+
+int __sched rt_mutex_slowlock_locked(struct rt_mutex *lock, int state,
+				     struct hrtimer_sleeper *timeout,
+				     enum rtmutex_chainwalk chwalk,
+				     struct ww_acquire_ctx *ww_ctx,
+				     struct rt_mutex_waiter *waiter);
 
 #ifdef CONFIG_DEBUG_RT_MUTEXES
 # include "rtmutex-debug.h"
Index: linux-4.9.20-rt16/kernel/locking/rwsem-rt.c
===================================================================
--- /dev/null
+++ linux-4.9.20-rt16/kernel/locking/rwsem-rt.c
@@ -0,0 +1,268 @@
+/*
+ */
+#include <linux/rwsem.h>
+#include <linux/sched.h>
+#include <linux/export.h>
+
+#include "rtmutex_common.h"
+
+/*
+ * RT-specific reader/writer semaphores
+ *
+ * down_write()
+ *  1) Lock sem->rtmutex
+ *  2) Remove the reader BIAS to force readers into the slow path
+ *  3) Wait until all readers have left the critical region
+ *  4) Mark it write locked
+ *
+ * up_write()
+ *  1) Remove the write locked marker
+ *  2) Set the reader BIAS so readers can use the fast path again
+ *  3) Unlock sem->rtmutex to release blocked readers
+ *
+ * down_read()
+ *  1) Try fast path acquisition (reader BIAS is set)
+ *  2) Take sem->rtmutex.wait_lock which protects the writelocked flag
+ *  3) If !writelocked, acquire it for read
+ *  4) If writelocked, block on sem->rtmutex
+ *  5) unlock sem->rtmutex, goto 1)
+ *
+ * up_read()
+ *  1) Try fast path release (reader count != 1)
+ *  2) Wake the writer waiting in down_write()#3
+ *
+ * down_read()#3 has the consequence, that rw semaphores on RT are not writer
+ * fair, but writers, which should be avoided in RT tasks (think mmap_sem),
+ * are subject to the rtmutex priority/DL inheritance mechanism.
+ *
+ * It's possible to make the rw semaphores writer fair by keeping a list of
+ * active readers. A blocked writer would force all newly incoming readers to
+ * block on the rtmutex, but the rtmutex would have to be proxy locked for one
+ * reader after the other. We can't use multi-reader inheritance because there
+ * is no way to support that with SCHED_DEADLINE. Implementing the one by one
+ * reader boosting/handover mechanism is a major surgery for a very dubious
+ * value.
+ *
+ * The risk of writer starvation is there, but the pathological use cases
+ * which trigger it are not necessarily the typical RT workloads.
+ */
+
+void __rwsem_init(struct rw_semaphore *sem, const char *name,
+		  struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/*
+	 * Make sure we are not reinitializing a held semaphore:
+	 */
+	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
+	lockdep_init_map(&sem->dep_map, name, key, 0);
+#endif
+	atomic_set(&sem->readers, READER_BIAS);
+}
+EXPORT_SYMBOL(__rwsem_init);
+
+int __down_read_trylock(struct rw_semaphore *sem)
+{
+	int r, old;
+
+	/*
+	 * Increment reader count, if sem->readers < 0, i.e. READER_BIAS is
+	 * set.
+	 */
+	for (r = atomic_read(&sem->readers); r < 0;) {
+		old = atomic_cmpxchg(&sem->readers, r, r + 1);
+		if (likely(old == r))
+			return 1;
+		r = old;
+	}
+	return 0;
+}
+
+void __sched __down_read(struct rw_semaphore *sem)
+{
+	struct rt_mutex *m = &sem->rtmutex;
+	struct rt_mutex_waiter waiter;
+
+	if (__down_read_trylock(sem))
+		return;
+
+	might_sleep();
+	raw_spin_lock_irq(&m->wait_lock);
+	/*
+	 * Allow readers as long as the writer has not completely
+	 * acquired the semaphore for write.
+	 */
+	if (atomic_read(&sem->readers) != WRITER_BIAS) {
+		atomic_inc(&sem->readers);
+		raw_spin_unlock_irq(&m->wait_lock);
+		return;
+	}
+
+	/*
+	 * Call into the slow lock path with the rtmutex->wait_lock
+	 * held, so this can't result in the following race:
+	 *
+	 * Reader1		Reader2		Writer
+	 *			down_read()
+	 *					down_write()
+	 *					rtmutex_lock(m)
+	 *					swait()
+	 * down_read()
+	 * unlock(m->wait_lock)
+	 *			up_read()
+	 *			swake()
+	 *					lock(m->wait_lock)
+	 *					sem->writelocked=true
+	 *					unlock(m->wait_lock)
+	 *
+	 *					up_write()
+	 *					sem->writelocked=false
+	 *					rtmutex_unlock(m)
+	 *			down_read()
+	 *					down_write()
+	 *					rtmutex_lock(m)
+	 *					swait()
+	 * rtmutex_lock(m)
+	 *
+	 * That would put Reader1 behind the writer waiting on
+	 * Reader2 to call up_read() which might be unbound.
+	 */
+	rt_mutex_init_waiter(&waiter, false);
+	rt_mutex_slowlock_locked(m, TASK_UNINTERRUPTIBLE, NULL,
+				 RT_MUTEX_MIN_CHAINWALK, NULL,
+				 &waiter);
+	/*
+	 * The slowlock() above is guaranteed to return with the rtmutex is
+	 * now held, so there can't be a writer active. Increment the reader
+	 * count and immediately drop the rtmutex again.
+	 */
+	atomic_inc(&sem->readers);
+	raw_spin_unlock_irq(&m->wait_lock);
+	rt_mutex_unlock(m);
+
+	debug_rt_mutex_free_waiter(&waiter);
+}
+
+void __up_read(struct rw_semaphore *sem)
+{
+	struct rt_mutex *m = &sem->rtmutex;
+	struct task_struct *tsk;
+
+	/*
+	 * sem->readers can only hit 0 when a writer is waiting for the
+	 * active readers to leave the critical region.
+	 */
+	if (!atomic_dec_and_test(&sem->readers))
+		return;
+
+	might_sleep();
+	raw_spin_lock_irq(&m->wait_lock);
+	/*
+	 * Wake the writer, i.e. the rtmutex owner. It might release the
+	 * rtmutex concurrently in the fast path (due to a signal), but to
+	 * clean up the rwsem it needs to acquire m->wait_lock. The worst
+	 * case which can happen is a spurious wakeup.
+	 */
+	tsk = rt_mutex_owner(m);
+	if (tsk)
+		wake_up_process(tsk);
+
+	raw_spin_unlock_irq(&m->wait_lock);
+}
+
+static void __up_write_unlock(struct rw_semaphore *sem, int bias,
+			      unsigned long flags)
+{
+	struct rt_mutex *m = &sem->rtmutex;
+
+	atomic_add(READER_BIAS - bias, &sem->readers);
+	raw_spin_unlock_irqrestore(&m->wait_lock, flags);
+	rt_mutex_unlock(m);
+}
+
+static int __sched __down_write_common(struct rw_semaphore *sem, int state)
+{
+	struct rt_mutex *m = &sem->rtmutex;
+	unsigned long flags;
+
+	/* Take the rtmutex as a fir