diff --git a/Documentation/hwlat_detector.txt b/Documentation/hwlat_detector.txt
new file mode 100644
index 000000000000..cb61516483d3
--- /dev/null
+++ b/Documentation/hwlat_detector.txt
@@ -0,0 +1,64 @@
+Introduction:
+-------------
+
+The module hwlat_detector is a special purpose kernel module that is used to
+detect large system latencies induced by the behavior of certain underlying
+hardware or firmware, independent of Linux itself. The code was developed
+originally to detect SMIs (System Management Interrupts) on x86 systems,
+however there is nothing x86 specific about this patchset. It was
+originally written for use by the "RT" patch since the Real Time
+kernel is highly latency sensitive.
+
+SMIs are usually not serviced by the Linux kernel, which typically does not
+even know that they are occuring. SMIs are instead are set up by BIOS code
+and are serviced by BIOS code, usually for "critical" events such as
+management of thermal sensors and fans. Sometimes though, SMIs are used for
+other tasks and those tasks can spend an inordinate amount of time in the
+handler (sometimes measured in milliseconds). Obviously this is a problem if
+you are trying to keep event service latencies down in the microsecond range.
+
+The hardware latency detector works by hogging all of the cpus for configurable
+amounts of time (by calling stop_machine()), polling the CPU Time Stamp Counter
+for some period, then looking for gaps in the TSC data. Any gap indicates a
+time when the polling was interrupted and since the machine is stopped and
+interrupts turned off the only thing that could do that would be an SMI.
+
+Note that the SMI detector should *NEVER* be used in a production environment.
+It is intended to be run manually to determine if the hardware platform has a
+problem with long system firmware service routines.
+
+Usage:
+------
+
+Loading the module hwlat_detector passing the parameter "enabled=1" (or by
+setting the "enable" entry in "hwlat_detector" debugfs toggled on) is the only
+step required to start the hwlat_detector. It is possible to redefine the
+threshold in microseconds (us) above which latency spikes will be taken
+into account (parameter "threshold=").
+
+Example:
+
+	# modprobe hwlat_detector enabled=1 threshold=100
+
+After the module is loaded, it creates a directory named "hwlat_detector" under
+the debugfs mountpoint, "/debug/hwlat_detector" for this text. It is necessary
+to have debugfs mounted, which might be on /sys/debug on your system.
+
+The /debug/hwlat_detector interface contains the following files:
+
+count			- number of latency spikes observed since last reset
+enable			- a global enable/disable toggle (0/1), resets count
+max			- maximum hardware latency actually observed (usecs)
+sample			- a pipe from which to read current raw sample data
+			  in the format <timestamp> <latency observed usecs>
+			  (can be opened O_NONBLOCK for a single sample)
+threshold		- minimum latency value to be considered (usecs)
+width			- time period to sample with CPUs held (usecs)
+			  must be less than the total window size (enforced)
+window			- total period of sampling, width being inside (usecs)
+
+By default we will set width to 500,000 and window to 1,000,000, meaning that
+we will sample every 1,000,000 usecs (1s) for 500,000 usecs (0.5s). If we
+observe any latencies that exceed the threshold (initially 100 usecs),
+then we write to a global sample ring buffer of 8K samples, which is
+consumed by reading from the "sample" (pipe) debugfs file interface.
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index c360f80c3473..5489dea355a2 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1636,6 +1636,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	ip=		[IP_PNP]
 			See Documentation/filesystems/nfs/nfsroot.txt.
 
+	irqaffinity=	[SMP] Set the default irq affinity mask
+			Format:
+			<cpu number>,...,<cpu number>
+			or
+			<cpu number>-<cpu number>
+			(must be a positive range in ascending order)
+			or a mixture
+			<cpu number>,...,<cpu number>-<cpu number>
+
 	irqfixup	[HW]
 			When an interrupt is not handled search all handlers
 			for it. Intended to get systems with badly broken
diff --git a/Documentation/sysrq.txt b/Documentation/sysrq.txt
index 13f5619b2203..f64d075ba647 100644
--- a/Documentation/sysrq.txt
+++ b/Documentation/sysrq.txt
@@ -59,10 +59,17 @@ On PowerPC - Press 'ALT - Print Screen (or F13) - <command key>,
 On other - If you know of the key combos for other architectures, please
            let me know so I can add them to this section.
 
-On all -  write a character to /proc/sysrq-trigger.  e.g.:
-
+On all -  write a character to /proc/sysrq-trigger, e.g.:
 		echo t > /proc/sysrq-trigger
 
+On all - Enable network SysRq by writing a cookie to icmp_echo_sysrq, e.g.
+		echo 0x01020304 >/proc/sys/net/ipv4/icmp_echo_sysrq
+	 Send an ICMP echo request with this pattern plus the particular
+	 SysRq command key. Example:
+		# ping -c1 -s57 -p0102030468
+	 will trigger the SysRq-H (help) command.
+
+
 *  What are the 'command' keys?
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 'b'     - Will immediately reboot the system without syncing or unmounting
diff --git a/Documentation/trace/histograms.txt b/Documentation/trace/histograms.txt
new file mode 100644
index 000000000000..6f2aeabf7faa
--- /dev/null
+++ b/Documentation/trace/histograms.txt
@@ -0,0 +1,186 @@
+		Using the Linux Kernel Latency Histograms
+
+
+This document gives a short explanation how to enable, configure and use
+latency histograms. Latency histograms are primarily relevant in the
+context of real-time enabled kernels (CONFIG_PREEMPT/CONFIG_PREEMPT_RT)
+and are used in the quality management of the Linux real-time
+capabilities.
+
+
+* Purpose of latency histograms
+
+A latency histogram continuously accumulates the frequencies of latency
+data. There are two types of histograms
+- potential sources of latencies
+- effective latencies
+
+
+* Potential sources of latencies
+
+Potential sources of latencies are code segments where interrupts,
+preemption or both are disabled (aka critical sections). To create
+histograms of potential sources of latency, the kernel stores the time
+stamp at the start of a critical section, determines the time elapsed
+when the end of the section is reached, and increments the frequency
+counter of that latency value - irrespective of whether any concurrently
+running process is affected by latency or not.
+- Configuration items (in the Kernel hacking/Tracers submenu)
+  CONFIG_INTERRUPT_OFF_LATENCY
+  CONFIG_PREEMPT_OFF_LATENCY
+
+
+* Effective latencies
+
+Effective latencies are actually occuring during wakeup of a process. To
+determine effective latencies, the kernel stores the time stamp when a
+process is scheduled to be woken up, and determines the duration of the
+wakeup time shortly before control is passed over to this process. Note
+that the apparent latency in user space may be somewhat longer, since the
+process may be interrupted after control is passed over to it but before
+the execution in user space takes place. Simply measuring the interval
+between enqueuing and wakeup may also not appropriate in cases when a
+process is scheduled as a result of a timer expiration. The timer may have
+missed its deadline, e.g. due to disabled interrupts, but this latency
+would not be registered. Therefore, the offsets of missed timers are
+recorded in a separate histogram. If both wakeup latency and missed timer
+offsets are configured and enabled, a third histogram may be enabled that
+records the overall latency as a sum of the timer latency, if any, and the
+wakeup latency. This histogram is called "timerandwakeup".
+- Configuration items (in the Kernel hacking/Tracers submenu)
+  CONFIG_WAKEUP_LATENCY
+  CONFIG_MISSED_TIMER_OFSETS
+
+
+* Usage
+
+The interface to the administration of the latency histograms is located
+in the debugfs file system. To mount it, either enter
+
+mount -t sysfs nodev /sys
+mount -t debugfs nodev /sys/kernel/debug
+
+from shell command line level, or add
+
+nodev	/sys			sysfs	defaults	0 0
+nodev	/sys/kernel/debug	debugfs	defaults	0 0
+
+to the file /etc/fstab. All latency histogram related files are then
+available in the directory /sys/kernel/debug/tracing/latency_hist. A
+particular histogram type is enabled by writing non-zero to the related
+variable in the /sys/kernel/debug/tracing/latency_hist/enable directory.
+Select "preemptirqsoff" for the histograms of potential sources of
+latencies and "wakeup" for histograms of effective latencies etc. The
+histogram data - one per CPU - are available in the files
+
+/sys/kernel/debug/tracing/latency_hist/preemptoff/CPUx
+/sys/kernel/debug/tracing/latency_hist/irqsoff/CPUx
+/sys/kernel/debug/tracing/latency_hist/preemptirqsoff/CPUx
+/sys/kernel/debug/tracing/latency_hist/wakeup/CPUx
+/sys/kernel/debug/tracing/latency_hist/wakeup/sharedprio/CPUx
+/sys/kernel/debug/tracing/latency_hist/missed_timer_offsets/CPUx
+/sys/kernel/debug/tracing/latency_hist/timerandwakeup/CPUx
+
+The histograms are reset by writing non-zero to the file "reset" in a
+particular latency directory. To reset all latency data, use
+
+#!/bin/sh
+
+TRACINGDIR=/sys/kernel/debug/tracing
+HISTDIR=$TRACINGDIR/latency_hist
+
+if test -d $HISTDIR
+then
+  cd $HISTDIR
+  for i in `find . | grep /reset$`
+  do
+    echo 1 >$i
+  done
+fi
+
+
+* Data format
+
+Latency data are stored with a resolution of one microsecond. The
+maximum latency is 10,240 microseconds. The data are only valid, if the
+overflow register is empty. Every output line contains the latency in
+microseconds in the first row and the number of samples in the second
+row. To display only lines with a positive latency count, use, for
+example,
+
+grep -v " 0$" /sys/kernel/debug/tracing/latency_hist/preemptoff/CPU0
+
+#Minimum latency: 0 microseconds.
+#Average latency: 0 microseconds.
+#Maximum latency: 25 microseconds.
+#Total samples: 3104770694
+#There are 0 samples greater or equal than 10240 microseconds
+#usecs	         samples
+    0	      2984486876
+    1	        49843506
+    2	        58219047
+    3	         5348126
+    4	         2187960
+    5	         3388262
+    6	          959289
+    7	          208294
+    8	           40420
+    9	            4485
+   10	           14918
+   11	           18340
+   12	           25052
+   13	           19455
+   14	            5602
+   15	             969
+   16	              47
+   17	              18
+   18	              14
+   19	               1
+   20	               3
+   21	               2
+   22	               5
+   23	               2
+   25	               1
+
+
+* Wakeup latency of a selected process
+
+To only collect wakeup latency data of a particular process, write the
+PID of the requested process to
+
+/sys/kernel/debug/tracing/latency_hist/wakeup/pid
+
+PIDs are not considered, if this variable is set to 0.
+
+
+* Details of the process with the highest wakeup latency so far
+
+Selected data of the process that suffered from the highest wakeup
+latency that occurred in a particular CPU are available in the file
+
+/sys/kernel/debug/tracing/latency_hist/wakeup/max_latency-CPUx.
+
+In addition, other relevant system data at the time when the
+latency occurred are given.
+
+The format of the data is (all in one line):
+<PID> <Priority> <Latency> (<Timeroffset>) <Command> \
+<- <PID> <Priority> <Command> <Timestamp>
+
+The value of <Timeroffset> is only relevant in the combined timer
+and wakeup latency recording. In the wakeup recording, it is
+always 0, in the missed_timer_offsets recording, it is the same
+as <Latency>.
+
+When retrospectively searching for the origin of a latency and
+tracing was not enabled, it may be helpful to know the name and
+some basic data of the task that (finally) was switching to the
+late real-tlme task. In addition to the victim's data, also the
+data of the possible culprit are therefore displayed after the
+"<-" symbol.
+
+Finally, the timestamp of the time when the latency occurred
+in <seconds>.<microseconds> after the most recent system boot
+is provided.
+
+These data are also reset when the wakeup histogram is reset.
diff --git a/Makefile b/Makefile
index 88d26a632bef..4e7faf17dd71 100644
--- a/Makefile
+++ b/Makefile
@@ -785,6 +785,9 @@ KBUILD_CFLAGS   += $(call cc-option,-Werror=strict-prototypes)
 # Prohibit date/time macros, which would make the build non-deterministic
 KBUILD_CFLAGS   += $(call cc-option,-Werror=date-time)
 
+# enforce correct pointer usage
+KBUILD_CFLAGS   += $(call cc-option,-Werror=incompatible-pointer-types)
+
 # use the deterministic mode of AR if available
 KBUILD_ARFLAGS := $(call ar-option,D)
 
diff --git a/arch/Kconfig b/arch/Kconfig
index 4e949e58b192..3b26d76933fb 100644
--- a/arch/Kconfig
+++ b/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
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 34e1569a11ee..79c4603e9453 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -33,7 +33,7 @@ config ARM
 	select HARDIRQS_SW_RESEND
 	select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT)
 	select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
-	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32
+	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && !PREEMPT_RT_BASE
 	select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32
 	select HAVE_ARCH_SECCOMP_FILTER if (AEABI && !OABI_COMPAT)
 	select HAVE_ARCH_TRACEHOOK
@@ -68,6 +68,7 @@ config ARM
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
+	select HAVE_PREEMPT_LAZY
 	select HAVE_RCU_TABLE_FREE if (SMP && ARM_LPAE)
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_SYSCALL_TRACEPOINTS
diff --git a/arch/arm/include/asm/switch_to.h b/arch/arm/include/asm/switch_to.h
index 12ebfcc1d539..c962084605bc 100644
--- a/arch/arm/include/asm/switch_to.h
+++ b/arch/arm/include/asm/switch_to.h
@@ -3,6 +3,13 @@
 
 #include <linux/thread_info.h>
 
+#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(struct task_struct *, struct thread_info
 #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)
 
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 776757d1604a..1f36a4eccc72 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/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(struct user_vfp __user *,
 #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(struct user_vfp __user *,
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
+#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(struct user_vfp __user *,
  * 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 */
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 871b8267d211..4dbe70de7318 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -65,6 +65,7 @@ int main(void)
   BLANK();
   DEFINE(TI_FLAGS,		offsetof(struct thread_info, flags));
   DEFINE(TI_PREEMPT,		offsetof(struct thread_info, preempt_count));
+  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));
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 3ce377f7251f..d044cea59f54 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -215,11 +215,18 @@ __irq_svc:
 #ifdef CONFIG_PREEMPT
 	get_thread_info tsk
 	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
@@ -234,8 +241,14 @@ 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:
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 30a7228eaceb..c3bd6cbfce4b 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/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)
 
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 4adfb46e3ee9..15f1d94b47c5 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -319,6 +319,30 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
 }
 
 #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
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 7b8f2141427b..96541e00b74a 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -572,7 +572,8 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
 	 */
 	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)))
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index b26361355dae..e5754e3b03c4 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -230,8 +230,6 @@ int __cpu_disable(void)
 	flush_cache_louis();
 	local_flush_tlb_all();
 
-	clear_tasks_mm_cpumask(cpu);
-
 	return 0;
 }
 
@@ -247,6 +245,9 @@ 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);
 
 	/*
diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c
index 0bee233fef9a..314cfb232a63 100644
--- a/arch/arm/kernel/unwind.c
+++ b/arch/arm/kernel/unwind.c
@@ -93,7 +93,7 @@ extern const struct unwind_idx __start_unwind_idx[];
 static const struct unwind_idx *__origin_unwind_idx;
 extern const struct unwind_idx __stop_unwind_idx[];
 
-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_find_idx(unsigned long addr)
 		/* 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_find_idx(unsigned long addr)
 				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(unsigned long start, unsigned long size,
 	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_table *tab)
 	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);
 }
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index d7bef2144760..36a3e51492f7 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -496,18 +496,18 @@ static void kvm_arm_resume_guest(struct kvm *kvm)
 	struct kvm_vcpu *vcpu;
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
-		wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu);
+		struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
 
 		vcpu->arch.pause = false;
-		wake_up_interruptible(wq);
+		swake_up(wq);
 	}
 }
 
 static void vcpu_sleep(struct kvm_vcpu *vcpu)
 {
-	wait_queue_head_t *wq = kvm_arch_vcpu_wq(vcpu);
+	struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
 
-	wait_event_interruptible(*wq, ((!vcpu->arch.power_off) &&
+	swait_event_interruptible(*wq, ((!vcpu->arch.power_off) &&
 				       (!vcpu->arch.pause)));
 }
 
@@ -566,7 +566,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		 * involves poking the GIC, which must be done in a
 		 * non-preemptible context.
 		 */
-		preempt_disable();
+		migrate_disable();
 		kvm_timer_flush_hwstate(vcpu);
 		kvm_vgic_flush_hwstate(vcpu);
 
@@ -585,7 +585,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 			local_irq_enable();
 			kvm_timer_sync_hwstate(vcpu);
 			kvm_vgic_sync_hwstate(vcpu);
-			preempt_enable();
+			migrate_enable();
 			continue;
 		}
 
@@ -639,7 +639,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 		kvm_vgic_sync_hwstate(vcpu);
 
-		preempt_enable();
+		migrate_enable();
 
 		ret = handle_exit(vcpu, run, ret);
 	}
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index a9b3b905e661..c2b131527a64 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -70,7 +70,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 {
 	struct kvm *kvm = source_vcpu->kvm;
 	struct kvm_vcpu *vcpu = NULL;
-	wait_queue_head_t *wq;
+	struct swait_queue_head *wq;
 	unsigned long cpu_id;
 	unsigned long context_id;
 	phys_addr_t target_pc;
@@ -119,7 +119,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	smp_mb();		/* Make sure the above is visible */
 
 	wq = kvm_arch_vcpu_wq(vcpu);
-	wake_up_interruptible(wq);
+	swake_up(wq);
 
 	return PSCI_RET_SUCCESS;
 }
diff --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig
index 28656c2b54a0..3f501305ca26 100644
--- a/arch/arm/mach-at91/Kconfig
+++ b/arch/arm/mach-at91/Kconfig
@@ -99,6 +99,7 @@ config HAVE_AT91_USB_CLK
 config COMMON_CLK_AT91
 	bool
 	select COMMON_CLK
+	select MFD_SYSCON
 
 config HAVE_AT91_SMD
 	bool
diff --git a/arch/arm/mach-at91/at91rm9200.c b/arch/arm/mach-at91/at91rm9200.c
index c1a7c6cc00e1..63b4fa25b48a 100644
--- a/arch/arm/mach-at91/at91rm9200.c
+++ b/arch/arm/mach-at91/at91rm9200.c
@@ -12,7 +12,6 @@
 #include <linux/of_platform.h>
 
 #include <asm/mach/arch.h>
-#include <asm/system_misc.h>
 
 #include "generic.h"
 #include "soc.h"
@@ -33,7 +32,6 @@ static void __init at91rm9200_dt_device_init(void)
 
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, soc_dev);
 
-	arm_pm_idle = at91rm9200_idle;
 	at91rm9200_pm_init();
 }
 
diff --git a/arch/arm/mach-at91/at91sam9.c b/arch/arm/mach-at91/at91sam9.c
index 7eb64f763034..cada2a6412b3 100644
--- a/arch/arm/mach-at91/at91sam9.c
+++ b/arch/arm/mach-at91/at91sam9.c
@@ -62,8 +62,6 @@ static void __init at91sam9_common_init(void)
 		soc_dev = soc_device_to_device(soc);
 
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, soc_dev);
-
-	arm_pm_idle = at91sam9_idle;
 }
 
 static void __init at91sam9_dt_device_init(void)
diff --git a/arch/arm/mach-at91/generic.h b/arch/arm/mach-at91/generic.h
index b0fa7dc7286d..28ca57a2060f 100644
--- a/arch/arm/mach-at91/generic.h
+++ b/arch/arm/mach-at91/generic.h
@@ -11,27 +11,18 @@
 #ifndef _AT91_GENERIC_H
 #define _AT91_GENERIC_H
 
-#include <linux/of.h>
-#include <linux/reboot.h>
-
- /* Map io */
-extern void __init at91_map_io(void);
-extern void __init at91_alt_map_io(void);
-
-/* idle */
-extern void at91rm9200_idle(void);
-extern void at91sam9_idle(void);
-
 #ifdef CONFIG_PM
 extern void __init at91rm9200_pm_init(void);
 extern void __init at91sam9260_pm_init(void);
 extern void __init at91sam9g45_pm_init(void);
 extern void __init at91sam9x5_pm_init(void);
+extern void __init sama5_pm_init(void);
 #else
 static inline void __init at91rm9200_pm_init(void) { }
 static inline void __init at91sam9260_pm_init(void) { }
 static inline void __init at91sam9g45_pm_init(void) { }
 static inline void __init at91sam9x5_pm_init(void) { }
+static inline void __init sama5_pm_init(void) { }
 #endif
 
 #endif /* _AT91_GENERIC_H */
diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c
index 23726fb31741..f06270198bf1 100644
--- a/arch/arm/mach-at91/pm.c
+++ b/arch/arm/mach-at91/pm.c
@@ -31,10 +31,13 @@
 #include <asm/mach/irq.h>
 #include <asm/fncpy.h>
 #include <asm/cacheflush.h>
+#include <asm/system_misc.h>
 
 #include "generic.h"
 #include "pm.h"
 
+static void __iomem *pmc;
+
 /*
  * FIXME: this is needed to communicate between the pinctrl driver and
  * the PM implementation in the machine. Possibly part of the PM
@@ -87,7 +90,7 @@ static int at91_pm_verify_clocks(void)
 	unsigned long scsr;
 	int i;
 
-	scsr = at91_pmc_read(AT91_PMC_SCSR);
+	scsr = readl(pmc + AT91_PMC_SCSR);
 
 	/* USB must not be using PLLB */
 	if ((scsr & at91_pm_data.uhp_udp_mask) != 0) {
@@ -101,8 +104,7 @@ static int at91_pm_verify_clocks(void)
 
 		if ((scsr & (AT91_PMC_PCK0 << i)) == 0)
 			continue;
-
-		css = at91_pmc_read(AT91_PMC_PCKR(i)) & AT91_PMC_CSS;
+		css = readl(pmc + AT91_PMC_PCKR(i)) & AT91_PMC_CSS;
 		if (css != AT91_PMC_CSS_SLOW) {
 			pr_err("AT91: PM - Suspend-to-RAM with PCK%d src %d\n", i, css);
 			return 0;
@@ -145,8 +147,8 @@ static void at91_pm_suspend(suspend_state_t state)
 	flush_cache_all();
 	outer_disable();
 
-	at91_suspend_sram_fn(at91_pmc_base, at91_ramc_base[0],
-				at91_ramc_base[1], pm_data);
+	at91_suspend_sram_fn(pmc, at91_ramc_base[0],
+			     at91_ramc_base[1], pm_data);
 
 	outer_resume();
 }
@@ -353,6 +355,21 @@ static __init void at91_dt_ramc(void)
 	at91_pm_set_standby(standby);
 }
 
+void at91rm9200_idle(void)
+{
+	/*
+	 * Disable the processor clock.  The processor will be automatically
+	 * re-enabled by an interrupt or by a reset.
+	 */
+	writel(AT91_PMC_PCK, pmc + AT91_PMC_SCDR);
+}
+
+void at91sam9_idle(void)
+{
+	writel(AT91_PMC_PCK, pmc + AT91_PMC_SCDR);
+	cpu_do_idle();
+}
+
 static void __init at91_pm_sram_init(void)
 {
 	struct gen_pool *sram_pool;
@@ -399,13 +416,36 @@ static void __init at91_pm_sram_init(void)
 			&at91_pm_suspend_in_sram, at91_pm_suspend_in_sram_sz);
 }
 
-static void __init at91_pm_init(void)
+static const struct of_device_id atmel_pmc_ids[] __initconst = {
+	{ .compatible = "atmel,at91rm9200-pmc"  },
+	{ .compatible = "atmel,at91sam9260-pmc" },
+	{ .compatible = "atmel,at91sam9g45-pmc" },
+	{ .compatible = "atmel,at91sam9n12-pmc" },
+	{ .compatible = "atmel,at91sam9x5-pmc" },
+	{ .compatible = "atmel,sama5d3-pmc" },
+	{ .compatible = "atmel,sama5d2-pmc" },
+	{ /* sentinel */ },
+};
+
+static void __init at91_pm_init(void (*pm_idle)(void))
 {
-	at91_pm_sram_init();
+	struct device_node *pmc_np;
 
 	if (at91_cpuidle_device.dev.platform_data)
 		platform_device_register(&at91_cpuidle_device);
 
+	pmc_np = of_find_matching_node(NULL, atmel_pmc_ids);
+	pmc = of_iomap(pmc_np, 0);
+	if (!pmc) {
+		pr_err("AT91: PM not supported, PMC not found\n");
+		return;
+	}
+
+	if (pm_idle)
+		arm_pm_idle = pm_idle;
+
+	at91_pm_sram_init();
+
 	if (at91_suspend_sram_fn)
 		suspend_set_ops(&at91_pm_ops);
 	else
@@ -424,7 +464,7 @@ void __init at91rm9200_pm_init(void)
 	at91_pm_data.uhp_udp_mask = AT91RM9200_PMC_UHP | AT91RM9200_PMC_UDP;
 	at91_pm_data.memctrl = AT91_MEMCTRL_MC;
 
-	at91_pm_init();
+	at91_pm_init(at91rm9200_idle);
 }
 
 void __init at91sam9260_pm_init(void)
@@ -432,7 +472,7 @@ void __init at91sam9260_pm_init(void)
 	at91_dt_ramc();
 	at91_pm_data.memctrl = AT91_MEMCTRL_SDRAMC;
 	at91_pm_data.uhp_udp_mask = AT91SAM926x_PMC_UHP | AT91SAM926x_PMC_UDP;
-	return at91_pm_init();
+	at91_pm_init(at91sam9_idle);
 }
 
 void __init at91sam9g45_pm_init(void)
@@ -440,7 +480,7 @@ void __init at91sam9g45_pm_init(void)
 	at91_dt_ramc();
 	at91_pm_data.uhp_udp_mask = AT91SAM926x_PMC_UHP;
 	at91_pm_data.memctrl = AT91_MEMCTRL_DDRSDR;
-	return at91_pm_init();
+	at91_pm_init(at91sam9_idle);
 }
 
 void __init at91sam9x5_pm_init(void)
@@ -448,5 +488,13 @@ void __init at91sam9x5_pm_init(void)
 	at91_dt_ramc();
 	at91_pm_data.uhp_udp_mask = AT91SAM926x_PMC_UHP | AT91SAM926x_PMC_UDP;
 	at91_pm_data.memctrl = AT91_MEMCTRL_DDRSDR;
-	return at91_pm_init();
+	at91_pm_init(at91sam9_idle);
+}
+
+void __init sama5_pm_init(void)
+{
+	at91_dt_ramc();
+	at91_pm_data.uhp_udp_mask = AT91SAM926x_PMC_UHP | AT91SAM926x_PMC_UDP;
+	at91_pm_data.memctrl = AT91_MEMCTRL_DDRSDR;
+	at91_pm_init(NULL);
 }
diff --git a/arch/arm/mach-at91/sama5.c b/arch/arm/mach-at91/sama5.c
index d9cf6799aec0..df8fdf1cf66d 100644
--- a/arch/arm/mach-at91/sama5.c
+++ b/arch/arm/mach-at91/sama5.c
@@ -51,7 +51,7 @@ static void __init sama5_dt_device_init(void)
 		soc_dev = soc_device_to_device(soc);
 
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, soc_dev);
-	at91sam9x5_pm_init();
+	sama5_pm_init();
 }
 
 static const char *const sama5_dt_board_compat[] __initconst = {
diff --git a/arch/arm/mach-exynos/platsmp.c b/arch/arm/mach-exynos/platsmp.c
index 98a2c0cbb833..310dce500d3e 100644
--- a/arch/arm/mach-exynos/platsmp.c
+++ b/arch/arm/mach-exynos/platsmp.c
@@ -230,7 +230,7 @@ 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)
 {
@@ -243,8 +243,8 @@ static void exynos_secondary_init(unsigned int cpu)
 	/*
 	 * 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)
@@ -308,7 +308,7 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle)
 	 * 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
@@ -335,7 +335,7 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle)
 
 		if (timeout == 0) {
 			printk(KERN_ERR "cpu1 power enable failed");
-			spin_unlock(&boot_lock);
+			raw_spin_unlock(&boot_lock);
 			return -ETIMEDOUT;
 		}
 	}
@@ -381,7 +381,7 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle)
 	 * calibrations, then wait for it to finish
 	 */
 fail:
-	spin_unlock(&boot_lock);
+	raw_spin_unlock(&boot_lock);
 
 	return pen_release != -1 ? ret : 0;
 }
diff --git a/arch/arm/mach-hisi/platmcpm.c b/arch/arm/mach-hisi/platmcpm.c
index b5f8f5ffda79..9753a84df9c4 100644
--- a/arch/arm/mach-hisi/platmcpm.c
+++ b/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 int l_cpu, struct task_struct *idle)
 	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 int l_cpu, struct task_struct *idle)
 
 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)
 	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_cpu)
 	}
 
 	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)
 	       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_cpu)
 		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_cpu)
 		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
diff --git a/arch/arm/mach-imx/Kconfig b/arch/arm/mach-imx/Kconfig
index 8ceda2844c4f..08bcf8fb76f2 100644
--- a/arch/arm/mach-imx/Kconfig
+++ b/arch/arm/mach-imx/Kconfig
@@ -524,7 +524,7 @@ config SOC_IMX6Q
 	bool "i.MX6 Quad/DualLite support"
 	select ARM_ERRATA_764369 if SMP
 	select HAVE_ARM_SCU if SMP
-	select HAVE_ARM_TWD if SMP
+	select HAVE_ARM_TWD
 	select PCI_DOMAINS if PCI
 	select PINCTRL_IMX6Q
 	select SOC_IMX6
diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c
index 79e1f876d1c9..7e625c17f78e 100644
--- a/arch/arm/mach-omap2/omap-smp.c
+++ b/arch/arm/mach-omap2/omap-smp.c
@@ -43,7 +43,7 @@
 /* SCU base address */
 static void __iomem *scu_base;
 
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
 
 void __iomem *omap4_get_scu_base(void)
 {
@@ -74,8 +74,8 @@ static void omap4_secondary_init(unsigned int cpu)
 	/*
 	 * 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)
@@ -89,7 +89,7 @@ static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle)
 	 * 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.
@@ -166,7 +166,7 @@ static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle)
 	 * 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;
 }
diff --git a/arch/arm/mach-prima2/platsmp.c b/arch/arm/mach-prima2/platsmp.c
index e46c91094dde..dcb3ed0c26da 100644
--- a/arch/arm/mach-prima2/platsmp.c
+++ b/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(unsigned int cpu)
 	/*
 	 * 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(unsigned int cpu, struct task_struct *idle)
 	/* 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(unsigned int cpu, struct task_struct *idle)
 	 * 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;
 }
diff --git a/arch/arm/mach-qcom/platsmp.c b/arch/arm/mach-qcom/platsmp.c
index 9b00123a315d..0a49fe1bc8cf 100644
--- a/arch/arm/mach-qcom/platsmp.c
+++ b/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 int cpu)
 	/*
 	 * 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 int cpu, int (*func)(unsigned int))
 	 * 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 int cpu, int (*func)(unsigned int))
 	 * 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;
 }
diff --git a/arch/arm/mach-spear/platsmp.c b/arch/arm/mach-spear/platsmp.c
index fd4297713d67..b0553b2c2d53 100644
--- a/arch/arm/mach-spear/platsmp.c
+++ b/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(unsigned int cpu)
 	/*
 	 * 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(unsigned int cpu, struct task_struct *idle)
 	 * 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(unsigned int cpu, struct task_struct *idle)
 	 * 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;
 }
diff --git a/arch/arm/mach-sti/platsmp.c b/arch/arm/mach-sti/platsmp.c
index c4ad6eae67fa..e830b20b212f 100644
--- a/arch/arm/mach-sti/platsmp.c
+++ b/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 int cpu)
 	/*
 	 * 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 int cpu, struct task_struct *idle)
 	 * 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 int cpu, struct task_struct *idle)
 	 * 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;
 }
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index daafcf121ce0..b8aa1e9ee8ee 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -430,6 +430,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 	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, unsigned int fsr,
 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;
 }
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index d02f8187b1cc..542692dbd40a 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -34,6 +34,11 @@ static inline pte_t get_fixmap_pte(unsigned long vaddr)
 	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
diff --git a/arch/arm/plat-versatile/platsmp.c b/arch/arm/plat-versatile/platsmp.c
index 53feb90c840c..b4a8d54fc3f3 100644
--- a/arch/arm/plat-versatile/platsmp.c
+++ b/arch/arm/plat-versatile/platsmp.c
@@ -30,7 +30,7 @@ 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)
 {
@@ -43,8 +43,8 @@ void versatile_secondary_init(unsigned int cpu)
 	/*
 	 * 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)
@@ -55,7 +55,7 @@ int versatile_boot_secondary(unsigned int cpu, struct task_struct *idle)
 	 * 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
@@ -85,7 +85,7 @@ int versatile_boot_secondary(unsigned int cpu, struct task_struct *idle)
 	 * 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;
 }
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 14cdc6dea493..9196cf82f7be 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -76,6 +76,7 @@ config ARM64
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_RCU_TABLE_FREE
+	select HAVE_PREEMPT_LAZY
 	select HAVE_SYSCALL_TRACEPOINTS
 	select IOMMU_DMA if IOMMU_SUPPORT
 	select IRQ_DOMAIN
@@ -582,7 +583,7 @@ 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
 	help
 	  Say Y if you want to run Linux in a Virtual Machine on Xen on ARM64.
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index 90c7ff233735..5f4e89fbc290 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/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 */
 };
 
@@ -103,6 +104,7 @@ static inline struct thread_info *current_thread_info(void)
 #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
@@ -118,6 +120,7 @@ static inline struct thread_info *current_thread_info(void)
 #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)
@@ -126,7 +129,8 @@ static inline struct thread_info *current_thread_info(void)
 #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_SYSCALL_WORK	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
 				 _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 087cf9a65359..d74475928399 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -35,6 +35,7 @@ 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));
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 5a3753d09e20..05d73c4c03f6 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -376,11 +376,16 @@ el1_irq:
 #ifdef CONFIG_PREEMPT
 	get_thread_info tsk
 	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
@@ -394,6 +399,7 @@ 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
 
@@ -638,6 +644,7 @@ ret_fast_syscall_trace:
  */
 work_pending:
 	tbnz	x1, #TIF_NEED_RESCHED, work_resched
+	tbnz	x1, #TIF_NEED_RESCHED_LAZY, work_resched
 	/* TIF_SIGPENDING, TIF_NOTIFY_RESUME or TIF_FOREIGN_FPSTATE case */
 	ldr	x2, [sp, #S_PSTATE]
 	mov	x0, sp				// 'regs'
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index db459612de44..bd8be6a0e745 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2410,7 +2410,7 @@ config CPU_R4400_WORKAROUNDS
 #
 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
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index e86b7499921a..b2a2f678c5dc 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -454,8 +454,8 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
 
 	dvcpu->arch.wait = 0;
 
-	if (waitqueue_active(&dvcpu->wq))
-		wake_up_interruptible(&dvcpu->wq);
+	if (swait_active(&dvcpu->wq))
+		swake_up(&dvcpu->wq);
 
 	return 0;
 }
@@ -1183,8 +1183,8 @@ static void kvm_mips_comparecount_func(unsigned long data)
 	kvm_mips_callbacks->queue_timer_int(vcpu);
 
 	vcpu->arch.wait = 0;
-	if (waitqueue_active(&vcpu->wq))
-		wake_up_interruptible(&vcpu->wq);
+	if (swait_active(&vcpu->wq))
+		swake_up(&vcpu->wq);
 }
 
 /* low level hrtimer wake routine */
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index db49e0d796b1..1d2be228661c 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -60,10 +60,11 @@ 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
@@ -141,6 +142,7 @@ 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
@@ -319,7 +321,7 @@ 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
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index cfa758c6b4f6..f8673ff84b31 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -286,7 +286,7 @@ struct kvmppc_vcore {
 	struct list_head runnable_threads;
 	struct list_head preempt_list;
 	spinlock_t lock;
-	wait_queue_head_t wq;
+	struct swait_queue_head wq;
 	spinlock_t stoltb_lock;	/* protects stolen_tb and preempt_tb */
 	u64 stolen_tb;
 	u64 preempt_tb;
@@ -626,7 +626,7 @@ struct kvm_vcpu_arch {
 	u8 prodded;
 	u32 last_inst;
 
-	wait_queue_head_t *wqp;
+	struct swait_queue_head *wqp;
 	struct kvmppc_vcore *vcore;
 	int ret;
 	int trap;
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 7efee4a3240b..40e6fa1b85b2 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -42,6 +42,8 @@ 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 */
 
 	/* low level flags - has atomic operations done on it */
@@ -82,8 +84,7 @@ static inline struct thread_info *current_thread_info(void)
 #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 */
@@ -101,6 +102,8 @@ static inline struct thread_info *current_thread_info(void)
 #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)
@@ -119,14 +122,16 @@ static inline struct thread_info *current_thread_info(void)
 #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 */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 221d584d089f..d6d0c59ef8ae 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -160,6 +160,7 @@ 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));
 
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 2405631e91a2..c21b4b42eaa0 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -818,7 +818,14 @@ 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 */
@@ -829,11 +836,11 @@ 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
@@ -1154,7 +1161,7 @@ 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 */
@@ -1175,7 +1182,7 @@ 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
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index edba294620db..1aae3fdb0c2a 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -683,7 +683,7 @@ _GLOBAL(ret_from_except_lite)
 #else
 	beq	restore
 #endif
-1:	andi.	r0,r4,_TIF_NEED_RESCHED
+1:	andi.	r0,r4,_TIF_NEED_RESCHED_MASK
 	beq	2f
 	bl	restore_interrupts
 	SCHEDULE_USER
@@ -745,10 +745,18 @@ 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
@@ -765,7 +773,7 @@ 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
 
 	/*
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 290559df1e8b..070afa6da35d 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -614,6 +614,7 @@ void irq_ctx_init(void)
 	}
 }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 void do_softirq_own_stack(void)
 {
 	struct thread_info *curtp, *irqtp;
@@ -631,6 +632,7 @@ 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)
 {
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index ed3ab509faca..8b261416c070 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -40,6 +40,7 @@
  * 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)
@@ -56,6 +57,7 @@ _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);
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index db475d41b57a..96b7ef80e05d 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -30,6 +30,7 @@
 
 	.text
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 _GLOBAL(call_do_softirq)
 	mflr	r0
 	std	r0,16(r1)
@@ -40,6 +41,7 @@ _GLOBAL(call_do_softirq)
 	ld	r0,16(r1)
 	mtlr	r0
 	blr
+#endif
 
 _GLOBAL(call_do_irq)
 	mflr	r0
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index c2024ac9d4e8..2303788da7e1 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -172,6 +172,7 @@ 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
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index a7352b59e6f9..df34a6432873 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -114,11 +114,11 @@ static bool kvmppc_ipi_thread(int cpu)
 static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
 {
 	int cpu;
-	wait_queue_head_t *wqp;
+	struct swait_queue_head *wqp;
 
 	wqp = kvm_arch_vcpu_wq(vcpu);
-	if (waitqueue_active(wqp)) {
-		wake_up_interruptible(wqp);
+	if (swait_active(wqp)) {
+		swake_up(wqp);
 		++vcpu->stat.halt_wakeup;
 	}
 
@@ -707,8 +707,8 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 		tvcpu->arch.prodded = 1;
 		smp_mb();
 		if (vcpu->arch.ceded) {
-			if (waitqueue_active(&vcpu->wq)) {
-				wake_up_interruptible(&vcpu->wq);
+			if (swait_active(&vcpu->wq)) {
+				swake_up(&vcpu->wq);
 				vcpu->stat.halt_wakeup++;
 			}
 		}
@@ -1447,7 +1447,7 @@ static struct kvmppc_vcore *kvmppc_vcore_create(struct kvm *kvm, int core)
 	INIT_LIST_HEAD(&vcore->runnable_threads);
 	spin_lock_init(&vcore->lock);
 	spin_lock_init(&vcore->stoltb_lock);
-	init_waitqueue_head(&vcore->wq);
+	init_swait_queue_head(&vcore->wq);
 	vcore->preempt_tb = TB_NIL;
 	vcore->lpcr = kvm->arch.lpcr;
 	vcore->first_vcpuid = core * threads_per_subcore;
@@ -2519,10 +2519,9 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 {
 	struct kvm_vcpu *vcpu;
 	int do_sleep = 1;
+	DECLARE_SWAITQUEUE(wait);
 
-	DEFINE_WAIT(wait);
-
-	prepare_to_wait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
+	prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
 
 	/*
 	 * Check one last time for pending exceptions and ceded state after
@@ -2536,7 +2535,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 	}
 
 	if (!do_sleep) {
-		finish_wait(&vc->wq, &wait);
+		finish_swait(&vc->wq, &wait);
 		return;
 	}
 
@@ -2544,7 +2543,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 	trace_kvmppc_vcore_blocked(vc, 0);
 	spin_unlock(&vc->lock);
 	schedule();
-	finish_wait(&vc->wq, &wait);
+	finish_swait(&vc->wq, &wait);
 	spin_lock(&vc->lock);
 	vc->vcore_state = VCORE_INACTIVE;
 	trace_kvmppc_vcore_blocked(vc, 1);
@@ -2600,7 +2599,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 			kvmppc_start_thread(vcpu, vc);
 			trace_kvm_guest_enter(vcpu);
 		} else if (vc->vcore_state == VCORE_SLEEPING) {
-			wake_up(&vc->wq);
+			swake_up(&vc->wq);
 		}
 
 	}
diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c
index 3f175e8aedb4..c4c02f91904c 100644
--- a/arch/powerpc/platforms/ps3/device-init.c
+++ b/arch/powerpc/platforms/ps3/device-init.c
@@ -752,7 +752,7 @@ static int ps3_notification_read_write(struct ps3_notification_device *dev,
 	}
 	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;
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index e9a983f40a24..bbdc539fb3c6 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -427,7 +427,7 @@ struct kvm_s390_irq_payload {
 struct kvm_s390_local_interrupt {
 	spinlock_t lock;
 	struct kvm_s390_float_interrupt *float_int;
-	wait_queue_head_t *wq;
+	struct swait_queue_head *wq;
 	atomic_t *cpuflags;
 	DECLARE_BITMAP(sigp_emerg_pending, KVM_MAX_VCPUS);
 	struct kvm_s390_irq_payload irq;
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 6a75352f453c..cc862c486002 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -868,13 +868,13 @@ no_timer:
 
 void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
 {
-	if (waitqueue_active(&vcpu->wq)) {
+	if (swait_active(&vcpu->wq)) {
 		/*
 		 * The vcpu gave up the cpu voluntarily, mark it as a good
 		 * yield-candidate.
 		 */
 		vcpu->preempted = true;
-		wake_up_interruptible(&vcpu->wq);
+		swake_up(&vcpu->wq);
 		vcpu->stat.halt_wakeup++;
 	}
 }
diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c
index 6c0378c0b8b5..abd58b4dff97 100644
--- a/arch/sh/kernel/irq.c
+++ b/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)
 {
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 56442d2d7bbc..8c9598f534c9 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -189,12 +189,10 @@ 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
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index e22416ce56ea..d359de71153a 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -854,6 +854,7 @@ void __irq_entry handler_irq(int pil, struct pt_regs *regs)
 	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)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 436639a31624..6ee1dd0deadc 100644
--- a/arch/x86/Kconfig
+++ b/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
@@ -212,8 +213,11 @@ 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
@@ -848,7 +852,7 @@ 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.
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 3633ad6145c5..c6d5458ee7f9 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -383,14 +383,14 @@ static int ecb_encrypt(struct blkcipher_desc *desc,
 	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;
 }
@@ -407,14 +407,14 @@ static int ecb_decrypt(struct blkcipher_desc *desc,
 	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;
 }
@@ -431,14 +431,14 @@ static int cbc_encrypt(struct blkcipher_desc *desc,
 	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;
 }
@@ -455,14 +455,14 @@ static int cbc_decrypt(struct blkcipher_desc *desc,
 	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;
 }
@@ -514,18 +514,20 @@ static int ctr_crypt(struct blkcipher_desc *desc,
 	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;
 }
diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c
index 8648158f3916..d7699130ee36 100644
--- a/arch/x86/crypto/cast5_avx_glue.c
+++ b/arch/x86/crypto/cast5_avx_glue.c
@@ -59,7 +59,7 @@ static inline void cast5_fpu_end(bool fpu_enabled)
 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_desc *desc, struct blkcipher_walk *walk,
 		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_desc *desc, struct blkcipher_walk *walk,
 		} 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 *desc, struct scatterlist *dst,
 	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_desc *desc, struct scatterlist *dst,
 	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);
diff --git a/arch/x86/crypto/glue_helper.c b/arch/x86/crypto/glue_helper.c
index 6a85598931b5..3a506ce7ed93 100644
--- a/arch/x86/crypto/glue_helper.c
+++ b/arch/x86/crypto/glue_helper.c
@@ -39,7 +39,7 @@ static int __glue_ecb_crypt_128bit(const struct common_glue_ctx *gctx,
 	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 struct common_glue_ctx *gctx,
 		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 struct common_glue_ctx *gctx,
 		}
 
 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 common_glue_ctx *gctx,
 			    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 common_glue_ctx *gctx,
 
 	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 common_glue_ctx *gctx,
 			  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 common_glue_ctx *gctx,
 
 	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 common_glue_ctx *gctx,
 			  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 common_glue_ctx *gctx,
 
 	/* 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);
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 1a4477cedc49..75a301b6a5b6 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -220,7 +220,7 @@ long syscall_trace_enter(struct pt_regs *regs)
 
 #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)
 {
@@ -236,9 +236,16 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
 		/* 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);
 
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index f3b6d54e0042..2d722ee01fc2 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -278,8 +278,24 @@ 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
+
+	cmpl $0,TI_preempt_lazy_count(%ebp)	# non-zero preempt_lazy_count ?
+	jnz restore_all
+
+	testl $_TIF_NEED_RESCHED_LAZY, 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
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index a55697d19824..316081a2ca85 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -579,7 +579,23 @@ 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
+
+	GET_THREAD_INFO(%rcx)
+	cmpl	$0, TI_preempt_lazy_count(%rcx)
+	jnz	1f
+
+	bt	$TIF_NEED_RESCHED_LAZY,TI_flags(%rcx)
+	jnc	1f
+do_preempt_schedule_irq:
+#endif
 	call	preempt_schedule_irq
 	jmp	0b
 1:
@@ -867,6 +883,7 @@ 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
@@ -879,6 +896,7 @@ 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
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 01bcde84d3e4..6f432adc55cd 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -79,17 +79,46 @@ static __always_inline void __preempt_count_sub(int val)
  * 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
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index 2138c9ae19ee..3f5b4ee2e2c1 100644
--- a/arch/x86/include/asm/signal.h
+++ b/arch/x86/include/asm/signal.h
@@ -23,6 +23,19 @@ typedef struct {
 	unsigned long sig[_NSIG_WORDS];
 } sigset_t;
 
+/*
+ * 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
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 58505f01962f..02fa39652cd6 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/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_stack_canary(void)
 	 * 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);
 
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index c7b551028740..ddb63bd90e3c 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -58,6 +58,8 @@ struct thread_info {
 	__u32			status;		/* thread synchronous flags */
 	__u32			cpu;		/* current CPU */
 	mm_segment_t		addr_limit;
+	int			preempt_lazy_count;	/* 0 => lazy preemptable
+							  <0 => BUG */
 	unsigned int		sig_on_uaccess_error:1;
 	unsigned int		uaccess_err:1;	/* uaccess failed */
 };
@@ -95,6 +97,7 @@ 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 */
@@ -119,6 +122,7 @@ 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)
@@ -152,6 +156,8 @@ 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)
 
 /*
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index fc808b83fccb..ebb40118abf5 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -615,9 +615,9 @@ 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;
@@ -776,15 +776,15 @@ static inline int atom_asr(short i, struct atomic_short *v)
  * 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;
 }
 
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index ea7074784cc4..01ec643ce66e 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -492,7 +492,7 @@ struct uv_blade_info {
 	unsigned short	nr_online_cpus;
 	unsigned short	pnode;
 	short		memory_nid;
-	spinlock_t	nmi_lock;	/* obsolete, see uv_hub_nmi */
+	raw_spinlock_t	nmi_lock;	/* obsolete, see uv_hub_nmi */
 	unsigned long	nmi_count;	/* obsolete, see uv_hub_nmi */
 };
 extern struct uv_blade_info *uv_blade_info;
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index e75907601a41..a29fc4f84fc4 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -87,7 +87,9 @@ static u64 acpi_lapic_addr __initdata = APIC_DEFAULT_PHYS_BASE;
  *		->ioapic_mutex
  *			->ioapic_lock
  */
+#ifdef CONFIG_X86_IO_APIC
 static DEFINE_MUTEX(acpi_ioapic_lock);
+#endif
 
 /* --------------------------------------------------------------------------
                               Boot-time Configuration
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index fdb0fbfb1197..678c711e2a16 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1711,7 +1711,8 @@ static bool io_apic_level_ack_pending(struct mp_chip_data *data)
 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;
 	}
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 4a139465f1d4..ad2afff02b36 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -947,7 +947,7 @@ void __init uv_system_init(void)
 			uv_blade_info[blade].pnode = pnode;
 			uv_blade_info[blade].nr_possible_cpus = 0;
 			uv_blade_info[blade].nr_online_cpus = 0;
-			spin_lock_init(&uv_blade_info[blade].nmi_lock);
+			raw_spin_lock_init(&uv_blade_info[blade].nmi_lock);
 			min_pnode = min(pnode, min_pnode);
 			max_pnode = max(pnode, max_pnode);
 			blade++;
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 439df975bc7a..b7954ddd6a0a 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -32,6 +32,7 @@ void common(void) {
 	OFFSET(TI_flags, thread_info, flags);
 	OFFSET(TI_status, thread_info, status);
 	OFFSET(TI_addr_limit, thread_info, addr_limit);
+	OFFSET(TI_preempt_lazy_count, thread_info, preempt_lazy_count);
 
 	BLANK();
 	OFFSET(crypto_tfm_ctx_offset, crypto_tfm, __crt_ctx);
@@ -89,4 +90,5 @@ void common(void) {
 
 	BLANK();
 	DEFINE(PTREGS_SIZE, sizeof(struct pt_regs));
+	DEFINE(_PREEMPT_ENABLED, PREEMPT_ENABLED);
 }
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 7e8a736d09db..430a4ec07811 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/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 <asm/processor.h>
 #include <asm/traps.h>
@@ -1236,7 +1238,7 @@ void mce_log_therm_throt_event(__u64 status)
 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)
 {
@@ -1245,32 +1247,18 @@ static unsigned long mce_adjust_timer_default(unsigned long interval)
 
 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_pinned(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))) {
@@ -1293,7 +1281,7 @@ static void mce_timer_fn(unsigned long data)
 
 done:
 	__this_cpu_write(mce_next_interval, iv);
-	__restart_timer(t, iv);
+	return __restart_timer(timer, iv);
 }
 
 /*
@@ -1301,7 +1289,7 @@ 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);
@@ -1316,7 +1304,7 @@ 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)
@@ -1326,6 +1314,56 @@ static void mce_do_trigger(struct work_struct *work)
 
 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
@@ -1333,19 +1371,8 @@ static DECLARE_WORK(mce_trigger_work, mce_do_trigger);
  */
 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;
@@ -1639,7 +1666,7 @@ static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c)
 	}
 }
 
-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;
 
@@ -1648,16 +1675,17 @@ static void mce_start_timer(unsigned int cpu, struct timer_list *t)
 
 	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_timer(t, mce_timer_fn, cpu);
+	hrtimer_init(t, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	t->function = mce_timer_fn;
 	mce_start_timer(cpu, t);
 }
 
@@ -2376,6 +2404,8 @@ 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();
 
@@ -2398,6 +2428,7 @@ static void mce_reenable_cpu(void *h)
 		if (b->init)
 			wrmsrl(MSR_IA32_MCx_CTL(i), b->ctl);
 	}
+	__mcheck_cpu_init_timer();
 }
 
 /* Get notified when a cpu comes on/off. Be hotplug friendly. */
@@ -2405,7 +2436,6 @@ 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:
@@ -2425,11 +2455,9 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		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;
 	}
 
@@ -2468,6 +2496,10 @@ static __init int mcheck_init_device(void)
 		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;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index ed446bdcbf31..d2ac364e2118 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -117,7 +117,7 @@ static struct perf_pmu_events_attr event_attr_##v = {			\
 };
 
 struct rapl_pmu {
-	spinlock_t	 lock;
+	raw_spinlock_t	 lock;
 	int		 n_active; /* number of active events */
 	struct list_head active_list;
 	struct pmu	 *pmu; /* pointer to rapl_pmu_class */
@@ -220,13 +220,13 @@ static enum hrtimer_restart rapl_hrtimer_handle(struct hrtimer *hrtimer)
 	if (!pmu->n_active)
 		return HRTIMER_NORESTART;
 
-	spin_lock_irqsave(&pmu->lock, flags);
+	raw_spin_lock_irqsave(&pmu->lock, flags);
 
 	list_for_each_entry(event, &pmu->active_list, active_entry) {
 		rapl_event_update(event);
 	}
 
-	spin_unlock_irqrestore(&pmu->lock, flags);
+	raw_spin_unlock_irqrestore(&pmu->lock, flags);
 
 	hrtimer_forward_now(hrtimer, pmu->timer_interval);
 
@@ -263,9 +263,9 @@ static void rapl_pmu_event_start(struct perf_event *event, int mode)
 	struct rapl_pmu *pmu = __this_cpu_read(rapl_pmu);
 	unsigned long flags;
 
-	spin_lock_irqsave(&pmu->lock, flags);
+	raw_spin_lock_irqsave(&pmu->lock, flags);
 	__rapl_pmu_event_start(pmu, event);
-	spin_unlock_irqrestore(&pmu->lock, flags);
+	raw_spin_unlock_irqrestore(&pmu->lock, flags);
 }
 
 static void rapl_pmu_event_stop(struct perf_event *event, int mode)
@@ -274,7 +274,7 @@ static void rapl_pmu_event_stop(struct perf_event *event, int mode)
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned long flags;
 
-	spin_lock_irqsave(&pmu->lock, flags);
+	raw_spin_lock_irqsave(&pmu->lock, flags);
 
 	/* mark event as deactivated and stopped */
 	if (!(hwc->state & PERF_HES_STOPPED)) {
@@ -299,7 +299,7 @@ static void rapl_pmu_event_stop(struct perf_event *event, int mode)
 		hwc->state |= PERF_HES_UPTODATE;
 	}
 
-	spin_unlock_irqrestore(&pmu->lock, flags);
+	raw_spin_unlock_irqrestore(&pmu->lock, flags);
 }
 
 static int rapl_pmu_event_add(struct perf_event *event, int mode)
@@ -308,14 +308,14 @@ static int rapl_pmu_event_add(struct perf_event *event, int mode)
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned long flags;
 
-	spin_lock_irqsave(&pmu->lock, flags);
+	raw_spin_lock_irqsave(&pmu->lock, flags);
 
 	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
 
 	if (mode & PERF_EF_START)
 		__rapl_pmu_event_start(pmu, event);
 
-	spin_unlock_irqrestore(&pmu->lock, flags);
+	raw_spin_unlock_irqrestore(&pmu->lock, flags);
 
 	return 0;
 }
@@ -603,7 +603,7 @@ static int rapl_cpu_prepare(int cpu)
 	pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
 	if (!pmu)
 		return -1;
-	spin_lock_init(&pmu->lock);
+	raw_spin_lock_init(&pmu->lock);
 
 	INIT_LIST_HEAD(&pmu->active_list);
 
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index 464ffd69b92e..00db1aad1548 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -42,7 +42,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 		unsigned long *stack, unsigned long bp,
 		const struct stacktrace_ops *ops, void *data)
 {
-	const unsigned cpu = get_cpu();
+	const unsigned cpu = get_cpu_light();
 	int graph = 0;
 	u32 *prev_esp;
 
@@ -86,7 +86,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 			break;
 		touch_nmi_watchdog();
 	}
-	put_cpu();
+	put_cpu_light();
 }
 EXPORT_SYMBOL(dump_trace);
 
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 5f1c6266eb30..c331e3fef465 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -152,7 +152,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 		unsigned long *stack, unsigned long bp,
 		const struct stacktrace_ops *ops, void *data)
 {
-	const unsigned cpu = get_cpu();
+	const unsigned cpu = get_cpu_light();
 	struct thread_info *tinfo;
 	unsigned long *irq_stack = (unsigned long *)per_cpu(irq_stack_ptr, cpu);
 	unsigned long dummy;
@@ -241,7 +241,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 	 * This handles the process stack:
 	 */
 	bp = ops->walk_stack(tinfo, stack, bp, ops, data, NULL, &graph);
-	put_cpu();
+	put_cpu_light();
 }
 EXPORT_SYMBOL(dump_trace);
 
@@ -255,7 +255,7 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
 	int cpu;
 	int i;
 
-	preempt_disable();
+	migrate_disable();
 	cpu = smp_processor_id();
 
 	irq_stack_end	= (unsigned long *)(per_cpu(irq_stack_ptr, cpu));
@@ -291,7 +291,7 @@ show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs,
 			pr_cont(" %016lx", *stack++);
 		touch_nmi_watchdog();
 	}
-	preempt_enable();
+	migrate_enable();
 
 	pr_cont("\n");
 	show_trace_log_lvl(task, regs, sp, bp, log_lvl);
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 38da8f29a9c8..ce71f7098f15 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -128,6 +128,7 @@ 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 thread_info *curstk;
@@ -146,6 +147,7 @@ void do_softirq_own_stack(void)
 
 	call_on_stack(__do_softirq, isp);
 }
+#endif
 
 bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
 {
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 47190bd399e7..807950860fb7 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -36,6 +36,7 @@
 #include <linux/kprobes.h>
 #include <linux/debugfs.h>
 #include <linux/nmi.h>
+#include <linux/swait.h>
 #include <asm/timer.h>
 #include <asm/cpu.h>
 #include <asm/traps.h>
@@ -91,14 +92,14 @@ static void kvm_io_delay(void)
 
 struct kvm_task_sleep_node {
 	struct hlist_node link;
-	wait_queue_head_t wq;
+	struct swait_queue_head wq;
 	u32 token;
 	int cpu;
 	bool halted;
 };
 
 static struct kvm_task_sleep_head {
-	spinlock_t lock;
+	raw_spinlock_t lock;
 	struct hlist_head list;
 } async_pf_sleepers[KVM_TASK_SLEEP_HASHSIZE];
 
@@ -122,17 +123,17 @@ void kvm_async_pf_task_wait(u32 token)
 	u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS);
 	struct kvm_task_sleep_head *b = &async_pf_sleepers[key];
 	struct kvm_task_sleep_node n, *e;
-	DEFINE_WAIT(wait);
+	DECLARE_SWAITQUEUE(wait);
 
 	rcu_irq_enter();
 
-	spin_lock(&b->lock);
+	raw_spin_lock(&b->lock);
 	e = _find_apf_task(b, token);
 	if (e) {
 		/* dummy entry exist -> wake up was delivered ahead of PF */
 		hlist_del(&e->link);
 		kfree(e);
-		spin_unlock(&b->lock);
+		raw_spin_unlock(&b->lock);
 
 		rcu_irq_exit();
 		return;
@@ -141,13 +142,13 @@ void kvm_async_pf_task_wait(u32 token)
 	n.token = token;
 	n.cpu = smp_processor_id();
 	n.halted = is_idle_task(current) || preempt_count() > 1;
-	init_waitqueue_head(&n.wq);
+	init_swait_queue_head(&n.wq);
 	hlist_add_head(&n.link, &b->list);
-	spin_unlock(&b->lock);
+	raw_spin_unlock(&b->lock);
 
 	for (;;) {
 		if (!n.halted)
-			prepare_to_wait(&n.wq, &wait, TASK_UNINTERRUPTIBLE);
+			prepare_to_swait(&n.wq, &wait, TASK_UNINTERRUPTIBLE);
 		if (hlist_unhashed(&n.link))
 			break;
 
@@ -166,7 +167,7 @@ void kvm_async_pf_task_wait(u32 token)
 		}
 	}
 	if (!n.halted)
-		finish_wait(&n.wq, &wait);
+		finish_swait(&n.wq, &wait);
 
 	rcu_irq_exit();
 	return;
@@ -178,8 +179,8 @@ static void apf_task_wake_one(struct kvm_task_sleep_node *n)
 	hlist_del_init(&n->link);
 	if (n->halted)
 		smp_send_reschedule(n->cpu);
-	else if (waitqueue_active(&n->wq))
-		wake_up(&n->wq);
+	else if (swait_active(&n->wq))
+		swake_up(&n->wq);
 }
 
 static void apf_task_wake_all(void)
@@ -189,14 +190,14 @@ static void apf_task_wake_all(void)
 	for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++) {
 		struct hlist_node *p, *next;
 		struct kvm_task_sleep_head *b = &async_pf_sleepers[i];
-		spin_lock(&b->lock);
+		raw_spin_lock(&b->lock);
 		hlist_for_each_safe(p, next, &b->list) {
 			struct kvm_task_sleep_node *n =
 				hlist_entry(p, typeof(*n), link);
 			if (n->cpu == smp_processor_id())
 				apf_task_wake_one(n);
 		}
-		spin_unlock(&b->lock);
+		raw_spin_unlock(&b->lock);
 	}
 }
 
@@ -212,7 +213,7 @@ void kvm_async_pf_task_wake(u32 token)
 	}
 
 again:
-	spin_lock(&b->lock);
+	raw_spin_lock(&b->lock);
 	n = _find_apf_task(b, token);
 	if (!n) {
 		/*
@@ -225,17 +226,17 @@ again:
 			 * Allocation failed! Busy wait while other cpu
 			 * handles async PF.
 			 */
-			spin_unlock(&b->lock);
+			raw_spin_unlock(&b->lock);
 			cpu_relax();
 			goto again;
 		}
 		n->token = token;
 		n->cpu = smp_processor_id();
-		init_waitqueue_head(&n->wq);
+		init_swait_queue_head(&n->wq);
 		hlist_add_head(&n->link, &b->list);
 	} else
 		apf_task_wake_one(n);
-	spin_unlock(&b->lock);
+	raw_spin_unlock(&b->lock);
 	return;
 }
 EXPORT_SYMBOL_GPL(kvm_async_pf_task_wake);
@@ -486,7 +487,7 @@ void __init kvm_guest_init(void)
 	paravirt_ops_setup();
 	register_reboot_notifier(&kvm_pv_reboot_nb);
 	for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++)
-		spin_lock_init(&async_pf_sleepers[i].lock);
+		raw_spin_lock_init(&async_pf_sleepers[i].lock);
 	if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF))
 		x86_init.irqs.trap_init = kvm_apf_trap_init;
 
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 697f90db0e37..424aec4a4c71 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -231,7 +231,7 @@ pci_serr_error(unsigned char reason, struct pt_regs *regs)
 #endif
 
 	if (panic_on_unrecovered_nmi)
-		panic("NMI: Not continuing");
+		nmi_panic(regs, "NMI: Not continuing");
 
 	pr_emerg("Dazed and confused, but trying to continue\n");
 
@@ -255,8 +255,16 @@ io_check_error(unsigned char reason, struct pt_regs *regs)
 		 reason, smp_processor_id());
 	show_regs(regs);
 
-	if (panic_on_io_nmi)
-		panic("NMI IOCK error: Not continuing");
+	if (panic_on_io_nmi) {
+		nmi_panic(regs, "NMI IOCK error: Not continuing");
+
+		/*
+		 * If we end up here, it means we have received an NMI while
+		 * processing panic(). Simply return without delaying and
+		 * re-enabling NMIs.
+		 */
+		return;
+	}
 
 	/* Re-enable the IOCK line, wait for a few seconds */
 	reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK;
@@ -297,7 +305,7 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
 
 	pr_emerg("Do you have a strange power saving mode enabled?\n");
 	if (unknown_nmi_panic || panic_on_unrecovered_nmi)
-		panic("NMI: Not continuing");
+		nmi_panic(regs, "NMI: Not continuing");
 
 	pr_emerg("Dazed and confused, but trying to continue\n");
 }
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 9f950917528b..4dd4beae917a 100644
--- a/arch/x86/kernel/process_32.c
+++ b/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>
@@ -210,6 +211,35 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
 }
 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.
@@ -286,6 +316,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_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
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index f660d63f40fe..8384207adde2 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -726,6 +726,7 @@ static int crashing_cpu;
 static nmi_shootdown_cb shootdown_callback;
 
 static atomic_t waiting_for_crash_ipi;
+static int crash_ipi_issued;
 
 static int crash_nmi_callback(unsigned int val, struct pt_regs *regs)
 {
@@ -788,6 +789,9 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback)
 
 	smp_send_nmi_allbutself();
 
+	/* Kick CPUs looping in NMI context. */
+	WRITE_ONCE(crash_ipi_issued, 1);
+
 	msecs = 1000; /* Wait at most a second for the other cpus to stop */
 	while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) {
 		mdelay(1);
@@ -796,6 +800,22 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback)
 
 	/* Leave the nmi callback set */
 }
+
+/* Override the weak function in kernel/panic.c */
+void nmi_panic_self_stop(struct pt_regs *regs)
+{
+	while (1) {
+		/*
+		 * Wait for the crash dumping IPI to be issued, and then
+		 * call its callback directly.
+		 */
+		if (READ_ONCE(crash_ipi_issued))
+			crash_nmi_callback(0, regs); /* Don't return */
+
+		cpu_relax();
+	}
+}
+
 #else /* !CONFIG_SMP */
 void nmi_shootdown_cpus(nmi_shootdown_cb callback)
 {
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 4d30b865be30..20d9e9fb3b74 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1195,7 +1195,7 @@ static void apic_update_lvtt(struct kvm_lapic *apic)
 static void apic_timer_expired(struct kvm_lapic *apic)
 {
 	struct kvm_vcpu *vcpu = apic->vcpu;
-	wait_queue_head_t *q = &vcpu->wq;
+	struct swait_queue_head *q = &vcpu->wq;
 	struct kvm_timer *ktimer = &apic->lapic_timer;
 
 	if (atomic_read(&apic->lapic_timer.pending))
@@ -1204,8 +1204,8 @@ static void apic_timer_expired(struct kvm_lapic *apic)
 	atomic_inc(&apic->lapic_timer.pending);
 	kvm_set_pending_timer(vcpu);
 
-	if (waitqueue_active(q))
-		wake_up_interruptible(q);
+	if (swait_active(q))
+		swake_up(q);
 
 	if (apic_lvtt_tscdeadline(apic))
 		ktimer->expired_tscdeadline = ktimer->tscdeadline;
@@ -1801,6 +1801,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
 	hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
 		     HRTIMER_MODE_ABS);
 	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
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 7429d481a311..aa205d7b7c5c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5804,6 +5804,13 @@ 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;
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index a6d739258137..bd24ba1c4a86 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/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, pgprot_t prot)
 	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);
 
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index 9c0ff045fdd4..dd25dd1671b6 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/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 pfn, pgprot_t prot)
 	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();
 	}
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 3b6ec42718e4..7871083de089 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -714,9 +714,9 @@ static void destination_plugged(struct bau_desc *bau_desc,
 
 		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);
 
@@ -736,9 +736,9 @@ static void destination_timeout(struct bau_desc *bau_desc,
 
 		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);
 
@@ -759,7 +759,7 @@ static void disable_for_period(struct bau_control *bcp, struct ptc_stats *stat)
 	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();
@@ -772,7 +772,7 @@ static void disable_for_period(struct bau_control *bcp, struct ptc_stats *stat)
 			}
 		}
 	}
-	spin_unlock(&hmaster->disable_lock);
+	raw_spin_unlock(&hmaster->disable_lock);
 }
 
 static void count_max_concurr(int stat, struct bau_control *bcp,
@@ -835,7 +835,7 @@ static void record_send_stats(cycles_t time1, cycles_t time2,
  */
 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;
@@ -968,7 +968,7 @@ static int check_enable(struct bau_control *bcp, struct ptc_stats *stat)
 	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) {
@@ -980,10 +980,10 @@ static int check_enable(struct bau_control *bcp, struct ptc_stats *stat)
 				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;
 }
 
@@ -1901,9 +1901,9 @@ static void __init init_per_cpu_tunables(void)
 		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);
 	}
 }
 
diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c
index 2b158a9fa1d7..5e0b122620cb 100644
--- a/arch/x86/platform/uv/uv_time.c
+++ b/arch/x86/platform/uv/uv_time.c
@@ -57,7 +57,7 @@ static DEFINE_PER_CPU(struct clock_event_device, cpu_ced);
 
 /* 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(void)
 				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 expires)
 	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 expires)
 		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, int force)
 	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, int force)
 			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, int force)
 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;
 }
 
 /*
diff --git a/block/blk-core.c b/block/blk-core.c
index 4fab5d610805..52d2fe2fec8f 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -125,6 +125,9 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
 
 	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 *q, gfp_t gfp)
 		if (!gfpflags_allow_blocking(gfp))
 			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_release(struct percpu_ref *ref)
 	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);
 }
 
 struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
@@ -741,7 +744,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
 	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 request_queue *q, unsigned int depth,
 		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 *plug, bool from_schedule)
 	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 *plug, bool from_schedule)
 				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 *plug, bool from_schedule)
 	 */
 	if (q)
 		queue_unplugged(q, depth, from_schedule);
-
-	local_irq_restore(flags);
 }
 
 void blk_finish_plug(struct blk_plug *plug)
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 381cb50a673c..dc8785233d94 100644
--- a/block/blk-ioc.c
+++ b/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_struct *work)
 			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;
 		}
 	}
diff --git a/block/blk-iopoll.c b/block/blk-iopoll.c
index 0736729d6494..3e21e31d0d7e 100644
--- a/block/blk-iopoll.c
+++ b/block/blk-iopoll.c
@@ -35,6 +35,7 @@ void blk_iopoll_sched(struct blk_iopoll *iop)
 	list_add_tail(&iop->list, this_cpu_ptr(&blk_cpu_iopoll));
 	__raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
 	local_irq_restore(flags);
+	preempt_check_resched_rt();
 }
 EXPORT_SYMBOL(blk_iopoll_sched);
 
@@ -132,6 +133,7 @@ static void blk_iopoll_softirq(struct softirq_action *h)
 		__raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
 
 	local_irq_enable();
+	preempt_check_resched_rt();
 }
 
 /**
@@ -201,6 +203,7 @@ static int blk_iopoll_cpu_notify(struct notifier_block *self,
 				 this_cpu_ptr(&blk_cpu_iopoll));
 		__raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
 		local_irq_enable();
+		preempt_check_resched_rt();
 	}
 
 	return NOTIFY_OK;
diff --git a/block/blk-mq-cpu.c b/block/blk-mq-cpu.c
index bb3ed488f7b5..628c6c13c482 100644
--- a/block/blk-mq-cpu.c
+++ b/block/blk-mq-cpu.c
@@ -16,7 +16,7 @@
 #include "blk-mq.h"
 
 static LIST_HEAD(blk_mq_cpu_notify_list);
-static DEFINE_RAW_SPINLOCK(blk_mq_cpu_notify_lock);
+static DEFINE_SPINLOCK(blk_mq_cpu_notify_lock);
 
 static int blk_mq_main_cpu_notify(struct notifier_block *self,
 				  unsigned long action, void *hcpu)
@@ -25,7 +25,10 @@ static int blk_mq_main_cpu_notify(struct notifier_block *self,
 	struct blk_mq_cpu_notifier *notify;
 	int ret = NOTIFY_OK;
 
-	raw_spin_lock(&blk_mq_cpu_notify_lock);
+	if (action != CPU_POST_DEAD)
+		return NOTIFY_OK;
+
+	spin_lock(&blk_mq_cpu_notify_lock);
 
 	list_for_each_entry(notify, &blk_mq_cpu_notify_list, list) {
 		ret = notify->notify(notify->data, action, cpu);
@@ -33,7 +36,7 @@ static int blk_mq_main_cpu_notify(struct notifier_block *self,
 			break;
 	}
 
-	raw_spin_unlock(&blk_mq_cpu_notify_lock);
+	spin_unlock(&blk_mq_cpu_notify_lock);
 	return ret;
 }
 
@@ -41,16 +44,16 @@ void blk_mq_register_cpu_notifier(struct blk_mq_cpu_notifier *notifier)
 {
 	BUG_ON(!notifier->notify);
 
-	raw_spin_lock(&blk_mq_cpu_notify_lock);
+	spin_lock(&blk_mq_cpu_notify_lock);
 	list_add_tail(&notifier->list, &blk_mq_cpu_notify_list);
-	raw_spin_unlock(&blk_mq_cpu_notify_lock);
+	spin_unlock(&blk_mq_cpu_notify_lock);
 }
 
 void blk_mq_unregister_cpu_notifier(struct blk_mq_cpu_notifier *notifier)
 {
-	raw_spin_lock(&blk_mq_cpu_notify_lock);
+	spin_lock(&blk_mq_cpu_notify_lock);
 	list_del(&notifier->list);
-	raw_spin_unlock(&blk_mq_cpu_notify_lock);
+	spin_unlock(&blk_mq_cpu_notify_lock);
 }
 
 void blk_mq_init_cpu_notifier(struct blk_mq_cpu_notifier *notifier,
diff --git a/block/blk-mq.c b/block/blk-mq.c
index c3e461ec40e4..03dfc2c91595 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -92,7 +92,7 @@ EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_start);
 
 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));
 }
 
 /*
@@ -130,7 +130,7 @@ void blk_mq_unfreeze_queue(struct request_queue *q)
 	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);
@@ -149,7 +149,7 @@ void blk_mq_wake_waiters(struct request_queue *q)
 	 * 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)
@@ -196,6 +196,9 @@ static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx,
 	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;
 
@@ -325,6 +328,17 @@ void blk_mq_end_request(struct request *rq, int error)
 }
 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;
@@ -332,6 +346,8 @@ static void __blk_mq_complete_request_remote(void *data)
 	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;
@@ -343,19 +359,23 @@ static void blk_mq_ipi_complete_request(struct request *rq)
 		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)
@@ -864,14 +884,14 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 		return;
 
 	if (!async) {
-		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_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
@@ -1619,7 +1639,7 @@ static int blk_mq_hctx_notify(void *data, unsigned long action,
 {
 	struct blk_mq_hw_ctx *hctx = data;
 
-	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN)
+	if (action == CPU_POST_DEAD)
 		return blk_mq_hctx_cpu_offline(hctx, cpu);
 
 	/*
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 713820b47b31..3cb6feb4fe23 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -74,7 +74,10 @@ struct blk_align_bitmap {
 static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
 					   unsigned int cpu)
 {
-	return per_cpu_ptr(q->queue_ctx, cpu);
+	struct blk_mq_ctx *ctx;
+
+	ctx = per_cpu_ptr(q->queue_ctx, cpu);
+	return ctx;
 }
 
 /*
@@ -85,12 +88,12 @@ static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
  */
 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 {
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index 53b1737e978d..81c3c0a62edf 100644
--- a/block/blk-softirq.c
+++ b/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();
 }
 
 /*
@@ -93,6 +94,7 @@ static int blk_cpu_notify(struct notifier_block *self, unsigned long action,
 				 this_cpu_ptr(&blk_cpu_done));
 		raise_softirq_irqoff(BLOCK_SOFTIRQ);
 		local_irq_enable();
+		preempt_check_resched_rt();
 	}
 
 	return NOTIFY_OK;
@@ -150,6 +152,7 @@ do_local:
 		goto do_local;
 
 	local_irq_restore(flags);
+	preempt_check_resched_rt();
 }
 
 /**
diff --git a/block/bounce.c b/block/bounce.c
index 1cb5dd3a5da1..2f1ec8a67cbe 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -55,11 +55,11 @@ static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom)
 	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 */
diff --git a/crypto/algapi.c b/crypto/algapi.c
index 59bf491fe3d8..f98e79c8cd77 100644
--- a/crypto/algapi.c
+++ b/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);
 
diff --git a/crypto/api.c b/crypto/api.c
index bbc147cb5dec..bc1a848f02ec 100644
--- a/crypto/api.c
+++ b/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 val, void *v)
 {
 	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;
diff --git a/crypto/internal.h b/crypto/internal.h
index 00e42a3ed814..2e85551e235f 100644
--- a/crypto/internal.h
+++ b/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);
@@ -143,7 +143,7 @@ static inline int crypto_is_moribund(struct crypto_alg *alg)
 
 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 */
diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h
index faa97604d878..941497f31cf0 100644
--- a/drivers/acpi/acpica/acglobal.h
+++ b/drivers/acpi/acpica/acglobal.h
@@ -116,7 +116,7 @@ ACPI_GLOBAL(u8, acpi_gbl_global_lock_pending);
  * 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 */
diff --git a/drivers/acpi/acpica/hwregs.c b/drivers/acpi/acpica/hwregs.c
index 3cf77afd142c..dc32e72132f1 100644
--- a/drivers/acpi/acpica/hwregs.c
+++ b/drivers/acpi/acpica/hwregs.c
@@ -269,14 +269,14 @@ acpi_status acpi_hw_clear_acpi_status(void)
 			  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;
diff --git a/drivers/acpi/acpica/hwxface.c b/drivers/acpi/acpica/hwxface.c
index b2e50d8007fe..ff007084dc48 100644
--- a/drivers/acpi/acpica/hwxface.c
+++ b/drivers/acpi/acpica/hwxface.c
@@ -374,7 +374,7 @@ acpi_status acpi_write_bit_register(u32 register_id, u32 value)
 		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
@@ -435,7 +435,7 @@ acpi_status acpi_write_bit_register(u32 register_id, u32 value)
 
 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);
 }
 
diff --git a/drivers/acpi/acpica/utmutex.c b/drivers/acpi/acpica/utmutex.c
index ce406e39b669..41a75eb3ae9d 100644
--- a/drivers/acpi/acpica/utmutex.c
+++ b/drivers/acpi/acpica/utmutex.c
@@ -88,7 +88,7 @@ acpi_status acpi_ut_mutex_initialize(void)
 		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);
 	}
@@ -156,7 +156,7 @@ 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 */
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index 7dbba387d12a..65beb7abb4e7 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -678,9 +678,9 @@ unsigned int ata_sff_data_xfer_noirq(struct ata_device *dev, unsigned char *buf,
 	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_queued_cmd *qc)
 		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_queued_cmd *qc)
 				       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,
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 1648de80e230..4e43cea8fce4 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -520,6 +520,8 @@ static struct zram_meta *zram_meta_alloc(char *pool_name, u64 disksize)
 		goto out_error;
 	}
 
+	zram_meta_init_table_locks(meta, disksize);
+
 	return meta;
 
 out_error:
@@ -568,12 +570,12 @@ static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
 	unsigned long handle;
 	size_t size;
 
-	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]);
 		clear_page(mem);
 		return 0;
 	}
@@ -584,7 +586,7 @@ static int zram_decompress_page(struct zram *zram, char *mem, u32 index)
 	else
 		ret = zcomp_decompress(zram->comp, cmem, size, mem);
 	zs_unmap_object(meta->mem_pool, handle);
-	bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value);
+	zram_unlock_table(&meta->table[index]);
 
 	/* Should NEVER happen. Return bio error if it does. */
 	if (unlikely(ret)) {
@@ -604,14 +606,14 @@ static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
 	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 */
@@ -689,10 +691,10 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 		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;
@@ -752,12 +754,12 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index,
 	 * 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);
@@ -800,9 +802,9 @@ static void zram_bio_discard(struct zram *zram, u32 index,
 	}
 
 	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;
@@ -928,9 +930,9 @@ static void zram_slot_free_notify(struct block_device *bdev,
 	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);
 }
 
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index 8e92339686d7..9e3e953d680e 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -72,6 +72,9 @@ 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 {
@@ -119,4 +122,42 @@ 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
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 491a4dce13fe..cf69b6b42208 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -799,8 +799,6 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
 	} sample;
 	long delta, delta2, delta3;
 
-	preempt_disable();
-
 	sample.jiffies = jiffies;
 	sample.cycles = random_get_entropy();
 	sample.num = num;
@@ -841,7 +839,6 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
 		 */
 		credit_entropy_bits(r, min_t(int, fls(delta>>1), 11));
 	}
-	preempt_enable();
 }
 
 void add_input_randomness(unsigned int type, unsigned int code,
@@ -894,28 +891,27 @@ static __u32 get_reg(struct fast_pool *f, struct pt_regs *regs)
 	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);
diff --git a/drivers/clk/at91/clk-generated.c b/drivers/clk/at91/clk-generated.c
index abc80949e1dd..4ad3298eb372 100644
--- a/drivers/clk/at91/clk-generated.c
+++ b/drivers/clk/at91/clk-generated.c
@@ -15,8 +15,8 @@
 #include <linux/clkdev.h>
 #include <linux/clk/at91_pmc.h>
 #include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/io.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
 
 #include "pmc.h"
 
@@ -28,8 +28,9 @@
 
 struct clk_generated {
 	struct clk_hw hw;
-	struct at91_pmc *pmc;
+	struct regmap *regmap;
 	struct clk_range range;
+	spinlock_t *lock;
 	u32 id;
 	u32 gckdiv;
 	u8 parent_id;
@@ -41,49 +42,52 @@ struct clk_generated {
 static int clk_generated_enable(struct clk_hw *hw)
 {
 	struct clk_generated *gck = to_clk_generated(hw);
-	struct at91_pmc *pmc = gck->pmc;
-	u32 tmp;
+	unsigned long flags;
 
 	pr_debug("GCLK: %s, gckdiv = %d, parent id = %d\n",
 		 __func__, gck->gckdiv, gck->parent_id);
 
-	pmc_lock(pmc);
-	pmc_write(pmc, AT91_PMC_PCR, (gck->id & AT91_PMC_PCR_PID_MASK));
-	tmp = pmc_read(pmc, AT91_PMC_PCR) &
-			~(AT91_PMC_PCR_GCKDIV_MASK | AT91_PMC_PCR_GCKCSS_MASK);
-	pmc_write(pmc, AT91_PMC_PCR, tmp | AT91_PMC_PCR_GCKCSS(gck->parent_id)
-					 | AT91_PMC_PCR_CMD
-					 | AT91_PMC_PCR_GCKDIV(gck->gckdiv)
-					 | AT91_PMC_PCR_GCKEN);
-	pmc_unlock(pmc);
+	spin_lock_irqsave(gck->lock, flags);
+	regmap_write(gck->regmap, AT91_PMC_PCR,
+		     (gck->id & AT91_PMC_PCR_PID_MASK));
+	regmap_update_bits(gck->regmap, AT91_PMC_PCR,
+			   AT91_PMC_PCR_GCKDIV_MASK | AT91_PMC_PCR_GCKCSS_MASK |
+			   AT91_PMC_PCR_CMD | AT91_PMC_PCR_GCKEN,
+			   AT91_PMC_PCR_GCKCSS(gck->parent_id) |
+			   AT91_PMC_PCR_CMD |
+			   AT91_PMC_PCR_GCKDIV(gck->gckdiv) |
+			   AT91_PMC_PCR_GCKEN);
+	spin_unlock_irqrestore(gck->lock, flags);
 	return 0;
 }
 
 static void clk_generated_disable(struct clk_hw *hw)
 {
 	struct clk_generated *gck = to_clk_generated(hw);
-	struct at91_pmc *pmc = gck->pmc;
-	u32 tmp;
-
-	pmc_lock(pmc);
-	pmc_write(pmc, AT91_PMC_PCR, (gck->id & AT91_PMC_PCR_PID_MASK));
-	tmp = pmc_read(pmc, AT91_PMC_PCR) & ~AT91_PMC_PCR_GCKEN;
-	pmc_write(pmc, AT91_PMC_PCR, tmp | AT91_PMC_PCR_CMD);
-	pmc_unlock(pmc);
+	unsigned long flags;
+
+	spin_lock_irqsave(gck->lock, flags);
+	regmap_write(gck->regmap, AT91_PMC_PCR,
+		     (gck->id & AT91_PMC_PCR_PID_MASK));
+	regmap_update_bits(gck->regmap, AT91_PMC_PCR,
+			   AT91_PMC_PCR_CMD | AT91_PMC_PCR_GCKEN,
+			   AT91_PMC_PCR_CMD);
+	spin_unlock_irqrestore(gck->lock, flags);
 }
 
 static int clk_generated_is_enabled(struct clk_hw *hw)
 {
 	struct clk_generated *gck = to_clk_generated(hw);
-	struct at91_pmc *pmc = gck->pmc;
-	int ret;
+	unsigned long flags;
+	unsigned int status;
 
-	pmc_lock(pmc);
-	pmc_write(pmc, AT91_PMC_PCR, (gck->id & AT91_PMC_PCR_PID_MASK));
-	ret = !!(pmc_read(pmc, AT91_PMC_PCR) & AT91_PMC_PCR_GCKEN);
-	pmc_unlock(pmc);
+	spin_lock_irqsave(gck->lock, flags);
+	regmap_write(gck->regmap, AT91_PMC_PCR,
+		     (gck->id & AT91_PMC_PCR_PID_MASK));
+	regmap_read(gck->regmap, AT91_PMC_PCR, &status);
+	spin_unlock_irqrestore(gck->lock, flags);
 
-	return ret;
+	return status & AT91_PMC_PCR_GCKEN ? 1 : 0;
 }
 
 static unsigned long
@@ -214,13 +218,14 @@ static const struct clk_ops generated_ops = {
  */
 static void clk_generated_startup(struct clk_generated *gck)
 {
-	struct at91_pmc *pmc = gck->pmc;
 	u32 tmp;
+	unsigned long flags;
 
-	pmc_lock(pmc);
-	pmc_write(pmc, AT91_PMC_PCR, (gck->id & AT91_PMC_PCR_PID_MASK));
-	tmp = pmc_read(pmc, AT91_PMC_PCR);
-	pmc_unlock(pmc);
+	spin_lock_irqsave(gck->lock, flags);
+	regmap_write(gck->regmap, AT91_PMC_PCR,
+		     (gck->id & AT91_PMC_PCR_PID_MASK));
+	regmap_read(gck->regmap, AT91_PMC_PCR, &tmp);
+	spin_unlock_irqrestore(gck->lock, flags);
 
 	gck->parent_id = (tmp & AT91_PMC_PCR_GCKCSS_MASK)
 					>> AT91_PMC_PCR_GCKCSS_OFFSET;
@@ -229,8 +234,8 @@ static void clk_generated_startup(struct clk_generated *gck)
 }
 
 static struct clk * __init
-at91_clk_register_generated(struct at91_pmc *pmc, const char *name,
-			    const char **parent_names, u8 num_parents,
+at91_clk_register_generated(struct regmap *regmap,  spinlock_t *lock, const char
+			    *name, const char **parent_names, u8 num_parents,
 			    u8 id, const struct clk_range *range)
 {
 	struct clk_generated *gck;
@@ -249,7 +254,8 @@ at91_clk_register_generated(struct at91_pmc *pmc, const char *name,
 
 	gck->id = id;
 	gck->hw.init = &init;
-	gck->pmc = pmc;
+	gck->regmap = regmap;
+	gck->lock = lock;
 	gck->range = *range;
 
 	clk = clk_register(NULL, &gck->hw);
@@ -261,8 +267,7 @@ at91_clk_register_generated(struct at91_pmc *pmc, const char *name,
 	return clk;
 }
 
-void __init of_sama5d2_clk_generated_setup(struct device_node *np,
-					   struct at91_pmc *pmc)
+void __init of_sama5d2_clk_generated_setup(struct device_node *np)
 {
 	int num;
 	u32 id;
@@ -272,6 +277,7 @@ void __init of_sama5d2_clk_generated_setup(struct device_node *np,
 	const char *parent_names[GENERATED_SOURCE_MAX];
 	struct device_node *gcknp;
 	struct clk_range range = CLK_RANGE(0, 0);
+	struct regmap *regmap;
 
 	num_parents = of_clk_get_parent_count(np);
 	if (num_parents <= 0 || num_parents > GENERATED_SOURCE_MAX)
@@ -283,6 +289,10 @@ void __init of_sama5d2_clk_generated_setup(struct device_node *np,
 	if (!num || num > PERIPHERAL_MAX)
 		return;
 
+	regmap = syscon_node_to_regmap(of_get_parent(np));
+	if (IS_ERR(regmap))
+		return;
+
 	for_each_child_of_node(np, gcknp) {
 		if (of_property_read_u32(gcknp, "reg", &id))
 			continue;
@@ -296,11 +306,14 @@ void __init of_sama5d2_clk_generated_setup(struct device_node *np,
 		of_at91_get_clk_range(gcknp, "atmel,clk-output-range",
 				      &range);
 
-		clk = at91_clk_register_generated(pmc, name, parent_names,
-						  num_parents, id, &range);
+		clk = at91_clk_register_generated(regmap, &pmc_pcr_lock, name,
+						  parent_names, num_parents,
+						  id, &range);
 		if (IS_ERR(clk))
 			continue;
 
 		of_clk_add_provider(gcknp, of_clk_src_simple_get, clk);
 	}
 }
+CLK_OF_DECLARE(of_sama5d2_clk_generated_setup, "atmel,sama5d2-clk-generated",
+	       of_sama5d2_clk_generated_setup);
diff --git a/drivers/clk/at91/clk-h32mx.c b/drivers/clk/at91/clk-h32mx.c
index a165230e7eda..8e20c8a76db7 100644
--- a/drivers/clk/at91/clk-h32mx.c
+++ b/drivers/clk/at91/clk-h32mx.c
@@ -15,15 +15,9 @@
 #include <linux/clk-provider.h>
 #include <linux/clkdev.h>
 #include <linux/clk/at91_pmc.h>
-#include <linux/delay.h>
 #include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-#include <linux/io.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/sched.h>
-#include <linux/wait.h>
+#include <linux/regmap.h>
+#include <linux/mfd/syscon.h>
 
 #include "pmc.h"
 
@@ -31,7 +25,7 @@
 
 struct clk_sama5d4_h32mx {
 	struct clk_hw hw;
-	struct at91_pmc *pmc;
+	struct regmap *regmap;
 };
 
 #define to_clk_sama5d4_h32mx(hw) container_of(hw, struct clk_sama5d4_h32mx, hw)
@@ -40,8 +34,10 @@ static unsigned long clk_sama5d4_h32mx_recalc_rate(struct clk_hw *hw,
 						 unsigned long parent_rate)
 {
 	struct clk_sama5d4_h32mx *h32mxclk = to_clk_sama5d4_h32mx(hw);
+	unsigned int mckr;
 
-	if (pmc_read(h32mxclk->pmc, AT91_PMC_MCKR) & AT91_PMC_H32MXDIV)
+	regmap_read(h32mxclk->regmap, AT91_PMC_MCKR, &mckr);
+	if (mckr & AT91_PMC_H32MXDIV)
 		return parent_rate / 2;
 
 	if (parent_rate > H32MX_MAX_FREQ)
@@ -70,18 +66,16 @@ static int clk_sama5d4_h32mx_set_rate(struct clk_hw *hw, unsigned long rate,
 				    unsigned long parent_rate)
 {
 	struct clk_sama5d4_h32mx *h32mxclk = to_clk_sama5d4_h32mx(hw);
-	struct at91_pmc *pmc = h32mxclk->pmc;
-	u32 tmp;
+	u32 mckr = 0;
 
 	if (parent_rate != rate && (parent_rate / 2) != rate)
 		return -EINVAL;
 
-	pmc_lock(pmc);
-	tmp = pmc_read(pmc, AT91_PMC_MCKR) & ~AT91_PMC_H32MXDIV;
 	if ((parent_rate / 2) == rate)
-		tmp |= AT91_PMC_H32MXDIV;
-	pmc_write(pmc, AT91_PMC_MCKR, tmp);
-	pmc_unlock(pmc);
+		mckr = AT91_PMC_H32MXDIV;
+
+	regmap_update_bits(h32mxclk->regmap, AT91_PMC_MCKR,
+			   AT91_PMC_H32MXDIV, mckr);
 
 	return 0;
 }
@@ -92,14 +86,18 @@ static const struct clk_ops h32mx_ops = {
 	.set_rate = clk_sama5d4_h32mx_set_rate,
 };
 
-void __init of_sama5d4_clk_h32mx_setup(struct device_node *np,
-				     struct at91_pmc *pmc)
+static void __init of_sama5d4_clk_h32mx_setup(struct device_node *np)
 {
 	struct clk_sama5d4_h32mx *h32mxclk;
 	struct clk_init_data init;
 	const char *parent_name;
+	struct regmap *regmap;
 	struct clk *clk;
 
+	regmap = syscon_node_to_regmap(of_get_parent(np));
+	if (IS_ERR(regmap))
+		return;
+
 	h32mxclk = kzalloc(sizeof(*h32mxclk), GFP_KERNEL);
 	if (!h32mxclk)
 		return;
@@ -113,7 +111,7 @@ void __init of_sama5d4_clk_h32mx_setup(struct device_node *np,
 	init.flags = CLK_SET_RATE_GATE;
 
 	h32mxclk->hw.init = &init;
-	h32mxclk->pmc = pmc;
+	h32mxclk->regmap = regmap;
 
 	clk = clk_register(NULL, &h32mxclk->hw);
 	if (IS_ERR(clk)) {
@@ -123,3 +121,5 @@ void __init of_sama5d4_clk_h32mx_setup(struct device_node *np,
 
 	of_clk_add_provider(np, of_clk_src_simple_get, clk);
 }
+CLK_OF_DECLARE(of_sama5d4_clk_h32mx_setup, "atmel,sama5d4-clk-h32mx",
+	       of_sama5d4_clk_h32mx_setup);
diff --git a/drivers/clk/at91/clk-main.c b/drivers/clk/at91/clk-main.c
index fd7247deabdc..4bfc94d6c26e 100644
--- a/drivers/clk/at91/clk-main.c
+++ b/drivers/clk/at91/clk-main.c
@@ -13,13 +13,8 @@
 #include <linux/clk/at91_pmc.h>
 #include <linux/delay.h>
 #include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-#include <linux/io.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/sched.h>
-#include <linux/wait.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
 
 #include "pmc.h"
 
@@ -34,18 +29,14 @@
 
 struct clk_main_osc {
 	struct clk_hw hw;
-	struct at91_pmc *pmc;
-	unsigned int irq;
-	wait_queue_head_t wait;
+	struct regmap *regmap;
 };
 
 #define to_clk_main_osc(hw) container_of(hw, struct clk_main_osc, hw)
 
 struct clk_main_rc_osc {
 	struct clk_hw hw;
-	struct at91_pmc *pmc;
-	unsigned int irq;
-	wait_queue_head_t wait;
+	struct regmap *regmap;
 	unsigned long frequency;
 	unsigned long accuracy;
 };
@@ -54,51 +45,47 @@ struct clk_main_rc_osc {
 
 struct clk_rm9200_main {
 	struct clk_hw hw;
-	struct at91_pmc *pmc;
+	struct regmap *regmap;
 };
 
 #define to_clk_rm9200_main(hw) container_of(hw, struct clk_rm9200_main, hw)
 
 struct clk_sam9x5_main {
 	struct clk_hw hw;
-	struct at91_pmc *pmc;
-	unsigned int irq;
-	wait_queue_head_t wait;
+	struct regmap *regmap;
 	u8 parent;
 };
 
 #define to_clk_sam9x5_main(hw) container_of(hw, struct clk_sam9x5_main, hw)
 
-static irqreturn_t clk_main_osc_irq_handler(int irq, void *dev_id)
+static inline bool clk_main_osc_ready(struct regmap *regmap)
 {
-	struct clk_main_osc *osc = dev_id;
+	unsigned int status;
 
-	wake_up(&osc->wait);
-	disable_irq_nosync(osc->irq);
+	regmap_read(regmap, AT91_PMC_SR, &status);
 
-	return IRQ_HANDLED;
+	return status & AT91_PMC_MOSCS;
 }
 
 static int clk_main_osc_prepare(struct clk_hw *hw)
 {
 	struct clk_main_osc *osc = to_clk_main_osc(hw);
-	struct at91_pmc *pmc = osc->pmc;
+	struct regmap *regmap = osc->regmap;
 	u32 tmp;
 
-	tmp = pmc_read(pmc, AT91_CKGR_MOR) & ~MOR_KEY_MASK;
+	regmap_read(regmap, AT91_CKGR_MOR, &tmp);
+	tmp &= ~MOR_KEY_MASK;
+
 	if (tmp & AT91_PMC_OSCBYPASS)
 		return 0;
 
 	if (!(tmp & AT91_PMC_MOSCEN)) {
 		tmp |= AT91_PMC_MOSCEN | AT91_PMC_KEY;
-		pmc_write(pmc, AT91_CKGR_MOR, tmp);
+		regmap_write(regmap, AT91_CKGR_MOR, tmp);
 	}
 
-	while (!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCS)) {
-		enable_irq(osc->irq);
-		wait_event(osc->wait,
-			   pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCS);
-	}
+	while (!clk_main_osc_ready(regmap))
+		cpu_relax();
 
 	return 0;
 }
@@ -106,9 +93,10 @@ static int clk_main_osc_prepare(struct clk_hw *hw)
 static void clk_main_osc_unprepare(struct clk_hw *hw)
 {
 	struct clk_main_osc *osc = to_clk_main_osc(hw);
-	struct at91_pmc *pmc = osc->pmc;
-	u32 tmp = pmc_read(pmc, AT91_CKGR_MOR);
+	struct regmap *regmap = osc->regmap;
+	u32 tmp;
 
+	regmap_read(regmap, AT91_CKGR_MOR, &tmp);
 	if (tmp & AT91_PMC_OSCBYPASS)
 		return;
 
@@ -116,20 +104,22 @@ static void clk_main_osc_unprepare(struct clk_hw *hw)
 		return;
 
 	tmp &= ~(AT91_PMC_KEY | AT91_PMC_MOSCEN);
-	pmc_write(pmc, AT91_CKGR_MOR, tmp | AT91_PMC_KEY);
+	regmap_write(regmap, AT91_CKGR_MOR, tmp | AT91_PMC_KEY);
 }
 
 static int clk_main_osc_is_prepared(struct clk_hw *hw)
 {
 	struct clk_main_osc *osc = to_clk_main_osc(hw);
-	struct at91_pmc *pmc = osc->pmc;
-	u32 tmp = pmc_read(pmc, AT91_CKGR_MOR);
+	struct regmap *regmap = osc->regmap;
+	u32 tmp, status;
 
+	regmap_read(regmap, AT91_CKGR_MOR, &tmp);
 	if (tmp & AT91_PMC_OSCBYPASS)
 		return 1;
 
-	return !!((pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCS) &&
-		  (pmc_read(pmc, AT91_CKGR_MOR) & AT91_PMC_MOSCEN));
+	regmap_read(regmap, AT91_PMC_SR, &status);
+
+	return (status & AT91_PMC_MOSCS) && (tmp & AT91_PMC_MOSCEN);
 }
 
 static const struct clk_ops main_osc_ops = {
@@ -139,18 +129,16 @@ static const struct clk_ops main_osc_ops = {
 };
 
 static struct clk * __init
-at91_clk_register_main_osc(struct at91_pmc *pmc,
-			   unsigned int irq,
+at91_clk_register_main_osc(struct regmap *regmap,
 			   const char *name,
 			   const char *parent_name,
 			   bool bypass)
 {
-	int ret;
 	struct clk_main_osc *osc;
 	struct clk *clk = NULL;
 	struct clk_init_data init;
 
-	if (!pmc || !irq || !name || !parent_name)
+	if (!name || !parent_name)
 		return ERR_PTR(-EINVAL);
 
 	osc = kzalloc(sizeof(*osc), GFP_KERNEL);
@@ -164,85 +152,70 @@ at91_clk_register_main_osc(struct at91_pmc *pmc,
 	init.flags = CLK_IGNORE_UNUSED;
 
 	osc->hw.init = &init;
-	osc->pmc = pmc;
-	osc->irq = irq;
-
-	init_waitqueue_head(&osc->wait);
-	irq_set_status_flags(osc->irq, IRQ_NOAUTOEN);
-	ret = request_irq(osc->irq, clk_main_osc_irq_handler,
-			  IRQF_TRIGGER_HIGH, name, osc);
-	if (ret) {
-		kfree(osc);
-		return ERR_PTR(ret);
-	}
+	osc->regmap = regmap;
 
 	if (bypass)
-		pmc_write(pmc, AT91_CKGR_MOR,
-			  (pmc_read(pmc, AT91_CKGR_MOR) &
-			   ~(MOR_KEY_MASK | AT91_PMC_MOSCEN)) |
-			  AT91_PMC_OSCBYPASS | AT91_PMC_KEY);
+		regmap_update_bits(regmap,
+				   AT91_CKGR_MOR, MOR_KEY_MASK |
+				   AT91_PMC_MOSCEN,
+				   AT91_PMC_OSCBYPASS | AT91_PMC_KEY);
 
 	clk = clk_register(NULL, &osc->hw);
-	if (IS_ERR(clk)) {
-		free_irq(irq, osc);
+	if (IS_ERR(clk))
 		kfree(osc);
-	}
 
 	return clk;
 }
 
-void __init of_at91rm9200_clk_main_osc_setup(struct device_node *np,
-					     struct at91_pmc *pmc)
+static void __init of_at91rm9200_clk_main_osc_setup(struct device_node *np)
 {
 	struct clk *clk;
-	unsigned int irq;
 	const char *name = np->name;
 	const char *parent_name;
+	struct regmap *regmap;
 	bool bypass;
 
 	of_property_read_string(np, "clock-output-names", &name);
 	bypass = of_property_read_bool(np, "atmel,osc-bypass");
 	parent_name = of_clk_get_parent_name(np, 0);
 
-	irq = irq_of_parse_and_map(np, 0);
-	if (!irq)
+	regmap = syscon_node_to_regmap(of_get_parent(np));
+	if (IS_ERR(regmap))
 		return;
 
-	clk = at91_clk_register_main_osc(pmc, irq, name, parent_name, bypass);
+	clk = at91_clk_register_main_osc(regmap, name, parent_name, bypass);
 	if (IS_ERR(clk))
 		return;
 
 	of_clk_add_provider(np, of_clk_src_simple_get, clk);
 }
+CLK_OF_DECLARE(at91rm9200_clk_main_osc, "atmel,at91rm9200-clk-main-osc",
+	       of_at91rm9200_clk_main_osc_setup);
 
-static irqreturn_t clk_main_rc_osc_irq_handler(int irq, void *dev_id)
+static bool clk_main_rc_osc_ready(struct regmap *regmap)
 {
-	struct clk_main_rc_osc *osc = dev_id;
+	unsigned int status;
 
-	wake_up(&osc->wait);
-	disable_irq_nosync(osc->irq);
+	regmap_read(regmap, AT91_PMC_SR, &status);
 
-	return IRQ_HANDLED;
+	return status & AT91_PMC_MOSCRCS;
 }
 
 static int clk_main_rc_osc_prepare(struct clk_hw *hw)
 {
 	struct clk_main_rc_osc *osc = to_clk_main_rc_osc(hw);
-	struct at91_pmc *pmc = osc->pmc;
-	u32 tmp;
+	struct regmap *regmap = osc->regmap;
+	unsigned int mor;
 
-	tmp = pmc_read(pmc, AT91_CKGR_MOR) & ~MOR_KEY_MASK;
+	regmap_read(regmap, AT91_CKGR_MOR, &mor);
 
-	if (!(tmp & AT91_PMC_MOSCRCEN)) {
-		tmp |= AT91_PMC_MOSCRCEN | AT91_PMC_KEY;
-		pmc_write(pmc, AT91_CKGR_MOR, tmp);
-	}
+	if (!(mor & AT91_PMC_MOSCRCEN))
+		regmap_update_bits(regmap, AT91_CKGR_MOR,
+				   MOR_KEY_MASK | AT91_PMC_MOSCRCEN,
+				   AT91_PMC_MOSCRCEN | AT91_PMC_KEY);
 
-	while (!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCRCS)) {
-		enable_irq(osc->irq);
-		wait_event(osc->wait,
-			   pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCRCS);
-	}
+	while (!clk_main_rc_osc_ready(regmap))
+		cpu_relax();
 
 	return 0;
 }
@@ -250,23 +223,28 @@ static int clk_main_rc_osc_prepare(struct clk_hw *hw)
 static void clk_main_rc_osc_unprepare(struct clk_hw *hw)
 {
 	struct clk_main_rc_osc *osc = to_clk_main_rc_osc(hw);
-	struct at91_pmc *pmc = osc->pmc;
-	u32 tmp = pmc_read(pmc, AT91_CKGR_MOR);
+	struct regmap *regmap = osc->regmap;
+	unsigned int mor;
+
+	regmap_read(regmap, AT91_CKGR_MOR, &mor);
 
-	if (!(tmp & AT91_PMC_MOSCRCEN))
+	if (!(mor & AT91_PMC_MOSCRCEN))
 		return;
 
-	tmp &= ~(MOR_KEY_MASK | AT91_PMC_MOSCRCEN);
-	pmc_write(pmc, AT91_CKGR_MOR, tmp | AT91_PMC_KEY);
+	regmap_update_bits(regmap, AT91_CKGR_MOR,
+			   MOR_KEY_MASK | AT91_PMC_MOSCRCEN, AT91_PMC_KEY);
 }
 
 static int clk_main_rc_osc_is_prepared(struct clk_hw *hw)
 {
 	struct clk_main_rc_osc *osc = to_clk_main_rc_osc(hw);
-	struct at91_pmc *pmc = osc->pmc;
+	struct regmap *regmap = osc->regmap;
+	unsigned int mor, status;
 
-	return !!((pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCRCS) &&
-		  (pmc_read(pmc, AT91_CKGR_MOR) & AT91_PMC_MOSCRCEN));
+	regmap_read(regmap, AT91_CKGR_MOR, &mor);
+	regmap_read(regmap, AT91_PMC_SR, &status);
+
+	return (mor & AT91_PMC_MOSCRCEN) && (status & AT91_PMC_MOSCRCS);
 }
 
 static unsigned long clk_main_rc_osc_recalc_rate(struct clk_hw *hw,
@@ -294,17 +272,15 @@ static const struct clk_ops main_rc_osc_ops = {
 };
 
 static struct clk * __init
-at91_clk_register_main_rc_osc(struct at91_pmc *pmc,
-			      unsigned int irq,
+at91_clk_register_main_rc_osc(struct regmap *regmap,
 			      const char *name,
 			      u32 frequency, u32 accuracy)
 {
-	int ret;
 	struct clk_main_rc_osc *osc;
 	struct clk *clk = NULL;
 	struct clk_init_data init;
 
-	if (!pmc || !irq || !name || !frequency)
+	if (!name || !frequency)
 		return ERR_PTR(-EINVAL);
 
 	osc = kzalloc(sizeof(*osc), GFP_KERNEL);
@@ -318,63 +294,53 @@ at91_clk_register_main_rc_osc(struct at91_pmc *pmc,
 	init.flags = CLK_IS_ROOT | CLK_IGNORE_UNUSED;
 
 	osc->hw.init = &init;
-	osc->pmc = pmc;
-	osc->irq = irq;
+	osc->regmap = regmap;
 	osc->frequency = frequency;
 	osc->accuracy = accuracy;
 
-	init_waitqueue_head(&osc->wait);
-	irq_set_status_flags(osc->irq, IRQ_NOAUTOEN);
-	ret = request_irq(osc->irq, clk_main_rc_osc_irq_handler,
-			  IRQF_TRIGGER_HIGH, name, osc);
-	if (ret)
-		return ERR_PTR(ret);
-
 	clk = clk_register(NULL, &osc->hw);
-	if (IS_ERR(clk)) {
-		free_irq(irq, osc);
+	if (IS_ERR(clk))
 		kfree(osc);
-	}
 
 	return clk;
 }
 
-void __init of_at91sam9x5_clk_main_rc_osc_setup(struct device_node *np,
-						struct at91_pmc *pmc)
+static void __init of_at91sam9x5_clk_main_rc_osc_setup(struct device_node *np)
 {
 	struct clk *clk;
-	unsigned int irq;
 	u32 frequency = 0;
 	u32 accuracy = 0;
 	const char *name = np->name;
+	struct regmap *regmap;
 
 	of_property_read_string(np, "clock-output-names", &name);
 	of_property_read_u32(np, "clock-frequency", &frequency);
 	of_property_read_u32(np, "clock-accuracy", &accuracy);
 
-	irq = irq_of_parse_and_map(np, 0);
-	if (!irq)
+	regmap = syscon_node_to_regmap(of_get_parent(np));
+	if (IS_ERR(regmap))
 		return;
 
-	clk = at91_clk_register_main_rc_osc(pmc, irq, name, frequency,
-					    accuracy);
+	clk = at91_clk_register_main_rc_osc(regmap, name, frequency, accuracy);
 	if (IS_ERR(clk))
 		return;
 
 	of_clk_add_provider(np, of_clk_src_simple_get, clk);
 }
+CLK_OF_DECLARE(at91sam9x5_clk_main_rc_osc, "atmel,at91sam9x5-clk-main-rc-osc",
+	       of_at91sam9x5_clk_main_rc_osc_setup);
 
 
-static int clk_main_probe_frequency(struct at91_pmc *pmc)
+static int clk_main_probe_frequency(struct regmap *regmap)
 {
 	unsigned long prep_time, timeout;
-	u32 tmp;
+	unsigned int mcfr;
 
 	timeout = jiffies + usecs_to_jiffies(MAINFRDY_TIMEOUT);
 	do {
 		prep_time = jiffies;
-		tmp = pmc_read(pmc, AT91_CKGR_MCFR);
-		if (tmp & AT91_PMC_MAINRDY)
+		regmap_read(regmap, AT91_CKGR_MCFR, &mcfr);
+		if (mcfr & AT91_PMC_MAINRDY)
 			return 0;
 		usleep_range(MAINF_LOOP_MIN_WAIT, MAINF_LOOP_MAX_WAIT);
 	} while (time_before(prep_time, timeout));
@@ -382,34 +348,37 @@ static int clk_main_probe_frequency(struct at91_pmc *pmc)
 	return -ETIMEDOUT;
 }
 
-static unsigned long clk_main_recalc_rate(struct at91_pmc *pmc,
+static unsigned long clk_main_recalc_rate(struct regmap *regmap,
 					  unsigned long parent_rate)
 {
-	u32 tmp;
+	unsigned int mcfr;
 
 	if (parent_rate)
 		return parent_rate;
 
 	pr_warn("Main crystal frequency not set, using approximate value\n");
-	tmp = pmc_read(pmc, AT91_CKGR_MCFR);
-	if (!(tmp & AT91_PMC_MAINRDY))
+	regmap_read(regmap, AT91_CKGR_MCFR, &mcfr);
+	if (!(mcfr & AT91_PMC_MAINRDY))
 		return 0;
 
-	return ((tmp & AT91_PMC_MAINF) * SLOW_CLOCK_FREQ) / MAINF_DIV;
+	return ((mcfr & AT91_PMC_MAINF) * SLOW_CLOCK_FREQ) / MAINF_DIV;
 }
 
 static int clk_rm9200_main_prepare(struct clk_hw *hw)
 {
 	struct clk_rm9200_main *clkmain = to_clk_rm9200_main(hw);
 
-	return clk_main_probe_frequency(clkmain->pmc);
+	return clk_main_probe_frequency(clkmain->regmap);
 }
 
 static int clk_rm9200_main_is_prepared(struct clk_hw *hw)
 {
 	struct clk_rm9200_main *clkmain = to_clk_rm9200_main(hw);
+	unsigned int status;
+
+	regmap_read(clkmain->regmap, AT91_CKGR_MCFR, &status);
 
-	return !!(pmc_read(clkmain->pmc, AT91_CKGR_MCFR) & AT91_PMC_MAINRDY);
+	return status & AT91_PMC_MAINRDY ? 1 : 0;
 }
 
 static unsigned long clk_rm9200_main_recalc_rate(struct clk_hw *hw,
@@ -417,7 +386,7 @@ static unsigned long clk_rm9200_main_recalc_rate(struct clk_hw *hw,
 {
 	struct clk_rm9200_main *clkmain = to_clk_rm9200_main(hw);
 
-	return clk_main_recalc_rate(clkmain->pmc, parent_rate);
+	return clk_main_recalc_rate(clkmain->regmap, parent_rate);
 }
 
 static const struct clk_ops rm9200_main_ops = {
@@ -427,7 +396,7 @@ static const struct clk_ops rm9200_main_ops = {
 };
 
 static struct clk * __init
-at91_clk_register_rm9200_main(struct at91_pmc *pmc,
+at91_clk_register_rm9200_main(struct regmap *regmap,
 			      const char *name,
 			      const char *parent_name)
 {
@@ -435,7 +404,7 @@ at91_clk_register_rm9200_main(struct at91_pmc *pmc,
 	struct clk *clk = NULL;
 	struct clk_init_data init;
 
-	if (!pmc || !name)
+	if (!name)
 		return ERR_PTR(-EINVAL);
 
 	if (!parent_name)
@@ -452,7 +421,7 @@ at91_clk_register_rm9200_main(struct at91_pmc *pmc,
 	init.flags = 0;
 
 	clkmain->hw.init = &init;
-	clkmain->pmc = pmc;
+	clkmain->regmap = regmap;
 
 	clk = clk_register(NULL, &clkmain->hw);
 	if (IS_ERR(clk))
@@ -461,52 +430,54 @@ at91_clk_register_rm9200_main(struct at91_pmc *pmc,
 	return clk;
 }
 
-void __init of_at91rm9200_clk_main_setup(struct device_node *np,
-					 struct at91_pmc *pmc)
+static void __init of_at91rm9200_clk_main_setup(struct device_node *np)
 {
 	struct clk *clk;
 	const char *parent_name;
 	const char *name = np->name;
+	struct regmap *regmap;
 
 	parent_name = of_clk_get_parent_name(np, 0);
 	of_property_read_string(np, "clock-output-names", &name);
 
-	clk = at91_clk_register_rm9200_main(pmc, name, parent_name);
+	regmap = syscon_node_to_regmap(of_get_parent(np));
+	if (IS_ERR(regmap))
+		return;
+
+	clk = at91_clk_register_rm9200_main(regmap, name, parent_name);
 	if (IS_ERR(clk))
 		return;
 
 	of_clk_add_provider(np, of_clk_src_simple_get, clk);
 }
+CLK_OF_DECLARE(at91rm9200_clk_main, "atmel,at91rm9200-clk-main",
+	       of_at91rm9200_clk_main_setup);
 
-static irqreturn_t clk_sam9x5_main_irq_handler(int irq, void *dev_id)
+static inline bool clk_sam9x5_main_ready(struct regmap *regmap)
 {
-	struct clk_sam9x5_main *clkmain = dev_id;
+	unsigned int status;
 
-	wake_up(&clkmain->wait);
-	disable_irq_nosync(clkmain->irq);
+	regmap_read(regmap, AT91_PMC_SR, &status);
 
-	return IRQ_HANDLED;
+	return status & AT91_PMC_MOSCSELS ? 1 : 0;
 }
 
 static int clk_sam9x5_main_prepare(struct clk_hw *hw)
 {
 	struct clk_sam9x5_main *clkmain = to_clk_sam9x5_main(hw);
-	struct at91_pmc *pmc = clkmain->pmc;
+	struct regmap *regmap = clkmain->regmap;
 
-	while (!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCSELS)) {
-		enable_irq(clkmain->irq);
-		wait_event(clkmain->wait,
-			   pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCSELS);
-	}
+	while (!clk_sam9x5_main_ready(regmap))
+		cpu_relax();
 
-	return clk_main_probe_frequency(pmc);
+	return clk_main_probe_frequency(regmap);
 }
 
 static int clk_sam9x5_main_is_prepared(struct clk_hw *hw)
 {
 	struct clk_sam9x5_main *clkmain = to_clk_sam9x5_main(hw);
 
-	return !!(pmc_read(clkmain->pmc, AT91_PMC_SR) & AT91_PMC_MOSCSELS);
+	return clk_sam9x5_main_ready(clkmain->regmap);
 }
 
 static unsigned long clk_sam9x5_main_recalc_rate(struct clk_hw *hw,
@@ -514,30 +485,28 @@ static unsigned long clk_sam9x5_main_recalc_rate(struct clk_hw *hw,
 {
 	struct clk_sam9x5_main *clkmain = to_clk_sam9x5_main(hw);
 
-	return clk_main_recalc_rate(clkmain->pmc, parent_rate);
+	return clk_main_recalc_rate(clkmain->regmap, parent_rate);
 }
 
 static int clk_sam9x5_main_set_parent(struct clk_hw *hw, u8 index)
 {
 	struct clk_sam9x5_main *clkmain = to_clk_sam9x5_main(hw);
-	struct at91_pmc *pmc = clkmain->pmc;
-	u32 tmp;
+	struct regmap *regmap = clkmain->regmap;
+	unsigned int tmp;
 
 	if (index > 1)
 		return -EINVAL;
 
-	tmp = pmc_read(pmc, AT91_CKGR_MOR) & ~MOR_KEY_MASK;
+	regmap_read(regmap, AT91_CKGR_MOR, &tmp);
+	tmp &= ~MOR_KEY_MASK;
 
 	if (index && !(tmp & AT91_PMC_MOSCSEL))
-		pmc_write(pmc, AT91_CKGR_MOR, tmp | AT91_PMC_MOSCSEL);
+		regmap_write(regmap, AT91_CKGR_MOR, tmp | AT91_PMC_MOSCSEL);
 	else if (!index && (tmp & AT91_PMC_MOSCSEL))
-		pmc_write(pmc, AT91_CKGR_MOR, tmp & ~AT91_PMC_MOSCSEL);
+		regmap_write(regmap, AT91_CKGR_MOR, tmp & ~AT91_PMC_MOSCSEL);
 
-	while (!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCSELS)) {
-		enable_irq(clkmain->irq);
-		wait_event(clkmain->wait,
-			   pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MOSCSELS);
-	}
+	while (!clk_sam9x5_main_ready(regmap))
+		cpu_relax();
 
 	return 0;
 }
@@ -545,8 +514,11 @@ static int clk_sam9x5_main_set_parent(struct clk_hw *hw, u8 index)
 static u8 clk_sam9x5_main_get_parent(struct clk_hw *hw)
 {
 	struct clk_sam9x5_main *clkmain = to_clk_sam9x5_main(hw);
+	unsigned int status;
+
+	regmap_read(clkmain->regmap, AT91_CKGR_MOR, &status);
 
-	return !!(pmc_read(clkmain->pmc, AT91_CKGR_MOR) & AT91_PMC_MOSCEN);
+	return status & AT91_PMC_MOSCEN ? 1 : 0;
 }
 
 static const struct clk_ops sam9x5_main_ops = {
@@ -558,18 +530,17 @@ static const struct clk_ops sam9x5_main_ops = {
 };
 
 static struct clk * __init
-at91_clk_register_sam9x5_main(struct at91_pmc *pmc,
-			      unsigned int irq,
+at91_clk_register_sam9x5_main(struct regmap *regmap,
 			      const char *name,
 			      const char **parent_names,
 			      int num_parents)
 {
-	int ret;
 	struct clk_sam9x5_main *clkmain;
 	struct clk *clk = NULL;
 	struct clk_init_data init;
+	unsigned int status;
 
-	if (!pmc || !irq || !name)
+	if (!name)
 		return ERR_PTR(-EINVAL);
 
 	if (!parent_names || !num_parents)
@@ -586,51 +557,42 @@ at91_clk_register_sam9x5_main(struct at91_pmc *pmc,
 	init.flags = CLK_SET_PARENT_GATE;
 
 	clkmain->hw.init = &init;
-	clkmain->pmc = pmc;
-	clkmain->irq = irq;
-	clkmain->parent = !!(pmc_read(clkmain->pmc, AT91_CKGR_MOR) &
-			     AT91_PMC_MOSCEN);
-	init_waitqueue_head(&clkmain->wait);
-	irq_set_status_flags(clkmain->irq, IRQ_NOAUTOEN);
-	ret = request_irq(clkmain->irq, clk_sam9x5_main_irq_handler,
-			  IRQF_TRIGGER_HIGH, name, clkmain);
-	if (ret)
-		return ERR_PTR(ret);
+	clkmain->regmap = regmap;
+	regmap_read(clkmain->regmap, AT91_CKGR_MOR, &status);
+	clkmain->parent = status & AT91_PMC_MOSCEN ? 1 : 0;
 
 	clk = clk_register(NULL, &clkmain->hw);
-	if (IS_ERR(clk)) {
-		free_irq(clkmain->irq, clkmain);
+	if (IS_ERR(clk))
 		kfree(clkmain);
-	}
 
 	return clk;
 }
 
-void __init of_at91sam9x5_clk_main_setup(struct device_node *np,
-					 struct at91_pmc *pmc)
+static void __init of_at91sam9x5_clk_main_setup(struct device_node *np)
 {
 	struct clk *clk;
 	const char *parent_names[2];
 	int num_parents;
-	unsigned int irq;
 	const char *name = np->name;
+	struct regmap *regmap;
 
 	num_parents = of_clk_get_parent_count(np);
 	if (num_parents <= 0 || num_parents > 2)
 		return;
 
 	of_clk_parent_fill(np, parent_names, num_parents);
+	regmap = syscon_node_to_regmap(of_get_parent(np));
+	if (IS_ERR(regmap))
+		return;
 
 	of_property_read_string(np, "clock-output-names", &name);
 
-	irq = irq_of_parse_and_map(np, 0);
-	if (!irq)
-		return;
-
-	clk = at91_clk_register_sam9x5_main(pmc, irq, name, parent_names,
+	clk = at91_clk_register_sam9x5_main(regmap, name, parent_names,
 					    num_parents);
 	if (IS_ERR(clk))
 		return;
 
 	of_clk_add_provider(np, of_clk_src_simple_get, clk);
 }
+CLK_OF_DECLARE(at91sam9x5_clk_main, "atmel,at91sam9x5-clk-main",
+	       of_at91sam9x5_clk_main_setup);
diff --git a/drivers/clk/at91/clk-master.c b/drivers/clk/at91/clk-master.c
index 620ea323356b..7d4a1864ea7c 100644
--- a/drivers/clk/at91/clk-master.c
+++ b/drivers/clk/at91/clk-master.c
@@ -12,13 +12,8 @@
 #include <linux/clkdev.h>
 #include <linux/clk/at91_pmc.h>
 #include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-#include <linux/io.h>
-#include <linux/wait.h>
-#include <linux/sched.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
 
 #include "pmc.h"
 
@@ -44,32 +39,26 @@ struct clk_master_layout {
 
 struct clk_master {
 	struct clk_hw hw;
-	struct at91_pmc *pmc;
-	unsigned int irq;
-	wait_queue_head_t wait;
+	struct regmap *regmap;
 	const struct clk_master_layout *layout;
 	const struct clk_master_characteristics *characteristics;
 };
 
-static irqreturn_t clk_master_irq_handler(int irq, void *dev_id)
+static inline bool clk_master_ready(struct regmap *regmap)
 {
-	struct clk_master *master = (struct clk_master *)dev_id;
+	unsigned int status;
 
-	wake_up(&master->wait);
-	disable_irq_nosync(master->irq);
+	regmap_read(regmap, AT91_PMC_SR, &status);
 
-	return IRQ_HANDLED;
+	return status & AT91_PMC_MCKRDY ? 1 : 0;
 }
+
 static int clk_master_prepare(struct clk_hw *hw)
 {
 	struct clk_master *master = to_clk_master(hw);
-	struct at91_pmc *pmc = master->pmc;
 
-	while (!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MCKRDY)) {
-		enable_irq(master->irq);
-		wait_event(master->wait,
-			   pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_MCKRDY);
-	}
+	while (!clk_master_ready(master->regmap))
+		cpu_relax();
 
 	return 0;
 }
@@ -78,7 +67,7 @@ static int clk_master_is_prepared(struct clk_hw *hw)
 {
 	struct clk_master *master = to_clk_master(hw);
 
-	return !!(pmc_read(master->pmc, AT91_PMC_SR) & AT91_PMC_MCKRDY);
+	return clk_master_ready(master->regmap);
 }
 
 static unsigned long clk_master_recalc_rate(struct clk_hw *hw,
@@ -88,18 +77,16 @@ static unsigned long clk_master_recalc_rate(struct clk_hw *hw,
 	u8 div;
 	unsigned long rate = parent_rate;
 	struct clk_master *master = to_clk_master(hw);
-	struct at91_pmc *pmc = master->pmc;
 	const struct clk_master_layout *layout = master->layout;
 	const struct clk_master_characteristics *characteristics =
 						master->characteristics;
-	u32 tmp;
+	unsigned int mckr;
 
-	pmc_lock(pmc);
-	tmp = pmc_read(pmc, AT91_PMC_MCKR) & layout->mask;
-	pmc_unlock(pmc);
+	regmap_read(master->regmap, AT91_PMC_MCKR, &mckr);
+	mckr &= layout->mask;
 
-	pres = (tmp >> layout->pres_shift) & MASTER_PRES_MASK;
-	div = (tmp >> MASTER_DIV_SHIFT) & MASTER_DIV_MASK;
+	pres = (mckr >> layout->pres_shift) & MASTER_PRES_MASK;
+	div = (mckr >> MASTER_DIV_SHIFT) & MASTER_DIV_MASK;
 
 	if (characteristics->have_div3_pres && pres == MASTER_PRES_MAX)
 		rate /= 3;
@@ -119,9 +106,11 @@ static unsigned long clk_master_recalc_rate(struct clk_hw *hw,
 static u8 clk_master_get_parent(struct clk_hw *hw)
 {
 	struct clk_master *master = to_clk_master(hw);
-	struct at91_pmc *pmc = master->pmc;
+	unsigned int mckr;
 
-	return pmc_read(pmc, AT91_PMC_MCKR) & AT91_PMC_CSS;
+	regmap_read(master->regmap, AT91_PMC_MCKR, &mckr);
+
+	return mckr & AT91_PMC_CSS;
 }
 
 static const struct clk_ops master_ops = {
@@ -132,18 +121,17 @@ static const struct clk_ops master_ops = {
 };
 
 static struct clk * __init
-at91_clk_register_master(struct at91_pmc *pmc, unsigned int irq,
+at91_clk_register_master(struct regmap *regmap,
 		const char *name, int num_parents,
 		const char **parent_names,
 		const struct clk_master_layout *layout,
 		const struct clk_master_characteristics *characteristics)
 {
-	int ret;
 	struct clk_master *master;
 	struct clk *clk = NULL;
 	struct clk_init_data init;
 
-	if (!pmc || !irq || !name || !num_parents || !parent_names)
+	if (!name || !num_parents || !parent_names)
 		return ERR_PTR(-EINVAL);
 
 	master = kzalloc(sizeof(*master), GFP_KERNEL);
@@ -159,20 +147,10 @@ at91_clk_register_master(struct at91_pmc *pmc, unsigned int irq,
 	master->hw.init = &init;
 	master->layout = layout;
 	master->characteristics = characteristics;
-	master->pmc = pmc;
-	master->irq = irq;
-	init_waitqueue_head(&master->wait);
-	irq_set_status_flags(master->irq, IRQ_NOAUTOEN);
-	ret = request_irq(master->irq, clk_master_irq_handler,
-			  IRQF_TRIGGER_HIGH, "clk-master", master);
-	if (ret) {
-		kfree(master);
-		return ERR_PTR(ret);
-	}
+	master->regmap = regmap;
 
 	clk = clk_register(NULL, &master->hw);
 	if (IS_ERR(clk)) {
-		free_irq(master->irq, master);
 		kfree(master);
 	}
 
@@ -217,15 +195,15 @@ out_free_characteristics:
 }
 
 static void __init
-of_at91_clk_master_setup(struct device_node *np, struct at91_pmc *pmc,
+of_at91_clk_master_setup(struct device_node *np,
 			 const struct clk_master_layout *layout)
 {
 	struct clk *clk;
 	int num_parents;
-	unsigned int irq;
 	const char *parent_names[MASTER_SOURCE_MAX];
 	const char *name = np->name;
 	struct clk_master_characteristics *characteristics;
+	struct regmap *regmap;
 
 	num_parents = of_clk_get_parent_count(np);
 	if (num_parents <= 0 || num_parents > MASTER_SOURCE_MAX)
@@ -239,11 +217,11 @@ of_at91_clk_master_setup(struct device_node *np, struct at91_pmc *pmc,
 	if (!characteristics)
 		return;
 
-	irq = irq_of_parse_and_map(np, 0);
-	if (!irq)
-		goto out_free_characteristics;
+	regmap = syscon_node_to_regmap(of_get_parent(np));
+	if (IS_ERR(regmap))
+		return;
 
-	clk = at91_clk_register_master(pmc, irq, name, num_parents,
+	clk = at91_clk_register_master(regmap, name, num_parents,
 				       parent_names, layout,
 				       characteristics);
 	if (IS_ERR(clk))
@@ -256,14 +234,16 @@ out_free_characteristics:
 	kfree(characteristics);
 }
 
-void __init of_at91rm9200_clk_master_setup(struct device_node *np,
-					   struct at91_pmc *pmc)
+static void __init of_at91rm9200_clk_master_setup(struct device_node *np)
 {
-	of_at91_clk_master_setup(np, pmc, &at91rm9200_master_layout);
+	of_at91_clk_master_setup(np, &at91rm9200_master_layout);
 }
+CLK_OF_DECLARE(at91rm9200_clk_master, "atmel,at91rm9200-clk-master",
+	       of_at91rm9200_clk_master_setup);
 
-void __init of_at91sam9x5_clk_master_setup(struct device_node *np,
-					   struct at91_pmc *pmc)
+static void __init of_at91sam9x5_clk_master_setup(struct device_node *np)
 {
-	of_at91_clk_master_setup(np, pmc, &at91sam9x5_master_layout);
+	of_at91_clk_master_setup(np, &at91sam9x5_master_layout);
 }
+CLK_OF_DECLARE(at91sam9x5_clk_master, "atmel,at91sam9x5-clk-master",
+	       of_at91sam9x5_clk_master_setup);
diff --git a/drivers/clk/at91/clk-peripheral.c b/drivers/clk/at91/clk-peripheral.c
index 58f3b568e9cb..d69cd2a121b1 100644
--- a/drivers/clk/at91/clk-peripheral.c
+++ b/drivers/clk/at91/clk-peripheral.c
@@ -12,11 +12,13 @@
 #include <linux/clkdev.h>
 #include <linux/clk/at91_pmc.h>
 #include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/io.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
 
 #include "pmc.h"
 
+DEFINE_SPINLOCK(pmc_pcr_lock);
+
 #define PERIPHERAL_MAX		64
 
 #define PERIPHERAL_AT91RM9200	0
@@ -33,7 +35,7 @@
 
 struct clk_peripheral {
 	struct clk_hw hw;
-	struct at91_pmc *pmc;
+	struct regmap *regmap;
 	u32 id;
 };
 
@@ -41,8 +43,9 @@ struct clk_peripheral {
 
 struct clk_sam9x5_peripheral {
 	struct clk_hw hw;
-	struct at91_pmc *pmc;
+	struct regmap *regmap;
 	struct clk_range range;
+	spinlock_t *lock;
 	u32 id;
 	u32 div;
 	bool auto_div;
@@ -54,7 +57,6 @@ struct clk_sam9x5_peripheral {
 static int clk_peripheral_enable(struct clk_hw *hw)
 {
 	struct clk_peripheral *periph = to_clk_peripheral(hw);
-	struct at91_pmc *pmc = periph->pmc;
 	int offset = AT91_PMC_PCER;
 	u32 id = periph->id;
 
@@ -62,14 +64,14 @@ static int clk_peripheral_enable(struct clk_hw *hw)
 		return 0;
 	if (id > PERIPHERAL_ID_MAX)
 		offset = AT91_PMC_PCER1;
-	pmc_write(pmc, offset, PERIPHERAL_MASK(id));
+	regmap_write(periph->regmap, offset, PERIPHERAL_MASK(id));
+
 	return 0;
 }
 
 static void clk_peripheral_disable(struct clk_hw *hw)
 {
 	struct clk_peripheral *periph = to_clk_peripheral(hw);
-	struct at91_pmc *pmc = periph->pmc;
 	int offset = AT91_PMC_PCDR;
 	u32 id = periph->id;
 
@@ -77,21 +79,23 @@ static void clk_peripheral_disable(struct clk_hw *hw)
 		return;
 	if (id > PERIPHERAL_ID_MAX)
 		offset = AT91_PMC_PCDR1;
-	pmc_write(pmc, offset, PERIPHERAL_MASK(id));
+	regmap_write(periph->regmap, offset, PERIPHERAL_MASK(id));
 }
 
 static int clk_peripheral_is_enabled(struct clk_hw *hw)
 {
 	struct clk_peripheral *periph = to_clk_peripheral(hw);
-	struct at91_pmc *pmc = periph->pmc;
 	int offset = AT91_PMC_PCSR;
+	unsigned int status;
 	u32 id = periph->id;
 
 	if (id < PERIPHERAL_ID_MIN)
 		return 1;
 	if (id > PERIPHERAL_ID_MAX)
 		offset = AT91_PMC_PCSR1;
-	return !!(pmc_read(pmc, offset) & PERIPHERAL_MASK(id));
+	regmap_read(periph->regmap, offset, &status);
+
+	return status & PERIPHERAL_MASK(id) ? 1 : 0;
 }
 
 static const struct clk_ops peripheral_ops = {
@@ -101,14 +105,14 @@ static const struct clk_ops peripheral_ops = {
 };
 
 static struct clk * __init
-at91_clk_register_peripheral(struct at91_pmc *pmc, const char *name,
+at91_clk_register_peripheral(struct regmap *regmap, const char *name,
 			     const char *parent_name, u32 id)
 {
 	struct clk_peripheral *periph;
 	struct clk *clk = NULL;
 	struct clk_init_data init;
 
-	if (!pmc || !name || !parent_name || id > PERIPHERAL_ID_MAX)
+	if (!name || !parent_name || id > PERIPHERAL_ID_MAX)
 		return ERR_PTR(-EINVAL);
 
 	periph = kzalloc(sizeof(*periph), GFP_KERNEL);
@@ -123,7 +127,7 @@ at91_clk_register_peripheral(struct at91_pmc *pmc, const char *name,
 
 	periph->id = id;
 	periph->hw.init = &init;
-	periph->pmc = pmc;
+	periph->regmap = regmap;
 
 	clk = clk_register(NULL, &periph->hw);
 	if (IS_ERR(clk))
@@ -160,53 +164,58 @@ static void clk_sam9x5_peripheral_autodiv(struct clk_sam9x5_peripheral *periph)
 static int clk_sam9x5_peripheral_enable(struct clk_hw *hw)
 {
 	struct clk_sam9x5_peripheral *periph = to_clk_sam9x5_peripheral(hw);
-	struct at91_pmc *pmc = periph->pmc;
-	u32 tmp;
+	unsigned long flags;
 
 	if (periph->id < PERIPHERAL_ID_MIN)
 		return 0;
 
-	pmc_lock(pmc);
-	pmc_write(pmc, AT91_PMC_PCR, (periph->id & AT91_PMC_PCR_PID_MASK));
-	tmp = pmc_read(pmc, AT91_PMC_PCR) & ~AT91_PMC_PCR_DIV_MASK;
-	pmc_write(pmc, AT91_PMC_PCR, tmp | AT91_PMC_PCR_DIV(periph->div)
-					 | AT91_PMC_PCR_CMD
-					 | AT91_PMC_PCR_EN);
-	pmc_unlock(pmc);
+	spin_lock_irqsave(periph->lock, flags);
+	regmap_write(periph->regmap, AT91_PMC_PCR,
+		     (periph->id & AT91_PMC_PCR_PID_MASK));
+	regmap_update_bits(periph->regmap, AT91_PMC_PCR,
+			   AT91_PMC_PCR_DIV_MASK | AT91_PMC_PCR_CMD |
+			   AT91_PMC_PCR_EN,
+			   AT91_PMC_PCR_DIV(periph->div) |
+			   AT91_PMC_PCR_CMD |
+			   AT91_PMC_PCR_EN);
+	spin_unlock_irqrestore(periph->lock, flags);
+
 	return 0;
 }
 
 static void clk_sam9x5_peripheral_disable(struct clk_hw *hw)
 {
 	struct clk_sam9x5_peripheral *periph = to_clk_sam9x5_peripheral(hw);
-	struct at91_pmc *pmc = periph->pmc;
-	u32 tmp;
+	unsigned long flags;
 
 	if (periph->id < PERIPHERAL_ID_MIN)
 		return;
 
-	pmc_lock(pmc);
-	pmc_write(pmc, AT91_PMC_PCR, (periph->id & AT91_PMC_PCR_PID_MASK));
-	tmp = pmc_read(pmc, AT91_PMC_PCR) & ~AT91_PMC_PCR_EN;
-	pmc_write(pmc, AT91_PMC_PCR, tmp | AT91_PMC_PCR_CMD);
-	pmc_unlock(pmc);
+	spin_lock_irqsave(periph->lock, flags);
+	regmap_write(periph->regmap, AT91_PMC_PCR,
+		     (periph->id & AT91_PMC_PCR_PID_MASK));
+	regmap_update_bits(periph->regmap, AT91_PMC_PCR,
+			   AT91_PMC_PCR_EN | AT91_PMC_PCR_CMD,
+			   AT91_PMC_PCR_CMD);
+	spin_unlock_irqrestore(periph->lock, flags);
 }
 
 static int clk_sam9x5_peripheral_is_enabled(struct clk_hw *hw)
 {
 	struct clk_sam9x5_peripheral *periph = to_clk_sam9x5_peripheral(hw);
-	struct at91_pmc *pmc = periph->pmc;
-	int ret;
+	unsigned long flags;
+	unsigned int status;
 
 	if (periph->id < PERIPHERAL_ID_MIN)
 		return 1;
 
-	pmc_lock(pmc);
-	pmc_write(pmc, AT91_PMC_PCR, (periph->id & AT91_PMC_PCR_PID_MASK));
-	ret = !!(pmc_read(pmc, AT91_PMC_PCR) & AT91_PMC_PCR_EN);
-	pmc_unlock(pmc);
+	spin_lock_irqsave(periph->lock, flags);
+	regmap_write(periph->regmap, AT91_PMC_PCR,
+		     (periph->id & AT91_PMC_PCR_PID_MASK));
+	regmap_read(periph->regmap, AT91_PMC_PCR, &status);
+	spin_unlock_irqrestore(periph->lock, flags);
 
-	return ret;
+	return status & AT91_PMC_PCR_EN ? 1 : 0;
 }
 
 static unsigned long
@@ -214,19 +223,20 @@ clk_sam9x5_peripheral_recalc_rate(struct clk_hw *hw,
 				  unsigned long parent_rate)
 {
 	struct clk_sam9x5_peripheral *periph = to_clk_sam9x5_peripheral(hw);
-	struct at91_pmc *pmc = periph->pmc;
-	u32 tmp;
+	unsigned long flags;
+	unsigned int status;
 
 	if (periph->id < PERIPHERAL_ID_MIN)
 		return parent_rate;
 
-	pmc_lock(pmc);
-	pmc_write(pmc, AT91_PMC_PCR, (periph->id & AT91_PMC_PCR_PID_MASK));
-	tmp = pmc_read(pmc, AT91_PMC_PCR);
-	pmc_unlock(pmc);
+	spin_lock_irqsave(periph->lock, flags);
+	regmap_write(periph->regmap, AT91_PMC_PCR,
+		     (periph->id & AT91_PMC_PCR_PID_MASK));
+	regmap_read(periph->regmap, AT91_PMC_PCR, &status);
+	spin_unlock_irqrestore(periph->lock, flags);
 
-	if (tmp & AT91_PMC_PCR_EN) {
-		periph->div = PERIPHERAL_RSHIFT(tmp);
+	if (status & AT91_PMC_PCR_EN) {
+		periph->div = PERIPHERAL_RSHIFT(status);
 		periph->auto_div = false;
 	} else {
 		clk_sam9x5_peripheral_autodiv(periph);
@@ -318,15 +328,15 @@ static const struct clk_ops sam9x5_peripheral_ops = {
 };
 
 static struct clk * __init
-at91_clk_register_sam9x5_peripheral(struct at91_pmc *pmc, const char *name,
-				    const char *parent_name, u32 id,
-				    const struct clk_range *range)
+at91_clk_register_sam9x5_peripheral(struct regmap *regmap, spinlock_t *lock,
+				    const char *name, const char *parent_name,
+				    u32 id, const struct clk_range *range)
 {
 	struct clk_sam9x5_peripheral *periph;
 	struct clk *clk = NULL;
 	struct clk_init_data init;
 
-	if (!pmc || !name || !parent_name)
+	if (!name || !parent_name)
 		return ERR_PTR(-EINVAL);
 
 	periph = kzalloc(sizeof(*periph), GFP_KERNEL);
@@ -342,7 +352,8 @@ at91_clk_register_sam9x5_peripheral(struct at91_pmc *pmc, const char *name,
 	periph->id = id;
 	periph->hw.init = &init;
 	periph->div = 0;
-	periph->pmc = pmc;
+	periph->regmap = regmap;
+	periph->lock = lock;
 	periph->auto_div = true;
 	periph->range = *range;
 
@@ -356,7 +367,7 @@ at91_clk_register_sam9x5_peripheral(struct at91_pmc *pmc, const char *name,
 }
 
 static void __init
-of_at91_clk_periph_setup(struct device_node *np, struct at91_pmc *pmc, u8 type)
+of_at91_clk_periph_setup(struct device_node *np, u8 type)
 {
 	int num;
 	u32 id;
@@ -364,6 +375,7 @@ of_at91_clk_periph_setup(struct device_node *np, struct at91_pmc *pmc, u8 type)
 	const char *parent_name;
 	const char *name;
 	struct device_node *periphclknp;
+	struct regmap *regmap;
 
 	parent_name = of_clk_get_parent_name(np, 0);
 	if (!parent_name)
@@ -373,6 +385,10 @@ of_at91_clk_periph_setup(struct device_node *np, struct at91_pmc *pmc, u8 type)
 	if (!num || num > PERIPHERAL_MAX)
 		return;
 
+	regmap = syscon_node_to_regmap(of_get_parent(np));
+	if (IS_ERR(regmap))
+		return;
+
 	for_each_child_of_node(np, periphclknp) {
 		if (of_property_read_u32(periphclknp, "reg", &id))
 			continue;
@@ -384,7 +400,7 @@ of_at91_clk_periph_setup(struct device_node *np, struct at91_pmc *pmc, u8 type)
 			name = periphclknp->name;
 
 		if (type == PERIPHERAL_AT91RM9200) {
-			clk = at91_clk_register_peripheral(pmc, name,
+			clk = at91_clk_register_peripheral(regmap, name,
 							   parent_name, id);
 		} else {
 			struct clk_range range = CLK_RANGE(0, 0);
@@ -393,7 +409,9 @@ of_at91_clk_periph_setup(struct device_node *np, struct at91_pmc *pmc, u8 type)
 					      "atmel,clk-output-range",
 					      &range);
 
-			clk = at91_clk_register_sam9x5_peripheral(pmc, name,
+			clk = at91_clk_register_sam9x5_peripheral(regmap,
+								  &pmc_pcr_lock,
+								  name,
 								  parent_name,
 								  id, &range);
 		}
@@ -405,14 +423,16 @@ of_at91_clk_periph_setup(struct device_node *np, struct at91_pmc *pmc, u8 type)
 	}
 }
 
-void __init of_at91rm9200_clk_periph_setup(struct device_node *np,
-					   struct at91_pmc *pmc)
+static void __init of_at91rm9200_clk_periph_setup(struct device_node *np)
 {
-	of_at91_clk_periph_setup(np, pmc, PERIPHERAL_AT91RM9200);
+	of_at91_clk_periph_setup(np, PERIPHERAL_AT91RM9200);
 }
+CLK_OF_DECLARE(at91rm9200_clk_periph, "atmel,at91rm9200-clk-peripheral",
+	       of_at91rm9200_clk_periph_setup);
 
-void __init of_at91sam9x5_clk_periph_setup(struct device_node *np,
-					   struct at91_pmc *pmc)
+static void __init of_at91sam9x5_clk_periph_setup(struct device_node *np)
 {
-	of_at91_clk_periph_setup(np, pmc, PERIPHERAL_AT91SAM9X5);
+	of_at91_clk_periph_setup(np, PERIPHERAL_AT91SAM9X5);
 }
+CLK_OF_DECLARE(at91sam9x5_clk_periph, "atmel,at91sam9x5-clk-peripheral",
+	       of_at91sam9x5_clk_periph_setup);
diff --git a/drivers/clk/at91/clk-pll.c b/drivers/clk/at91/clk-pll.c
index 18b60f4895a6..fb2e0b56d4b7 100644
--- a/drivers/clk/at91/clk-pll.c
+++ b/drivers/clk/at91/clk-pll.c
@@ -12,14 +12,8 @@
 #include <linux/clkdev.h>
 #include <linux/clk/at91_pmc.h>
 #include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-#include <linux/io.h>
-#include <linux/kernel.h>
-#include <linux/wait.h>
-#include <linux/sched.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
 
 #include "pmc.h"
 
@@ -58,9 +52,7 @@ struct clk_pll_layout {
 
 struct clk_pll {
 	struct clk_hw hw;
-	struct at91_pmc *pmc;
-	unsigned int irq;
-	wait_queue_head_t wait;
+	struct regmap *regmap;
 	u8 id;
 	u8 div;
 	u8 range;
@@ -69,20 +61,19 @@ struct clk_pll {
 	const struct clk_pll_characteristics *characteristics;
 };
 
-static irqreturn_t clk_pll_irq_handler(int irq, void *dev_id)
+static inline bool clk_pll_ready(struct regmap *regmap, int id)
 {
-	struct clk_pll *pll = (struct clk_pll *)dev_id;
+	unsigned int status;
 
-	wake_up(&pll->wait);
-	disable_irq_nosync(pll->irq);
+	regmap_read(regmap, AT91_PMC_SR, &status);
 
-	return IRQ_HANDLED;
+	return status & PLL_STATUS_MASK(id) ? 1 : 0;
 }
 
 static int clk_pll_prepare(struct clk_hw *hw)
 {
 	struct clk_pll *pll = to_clk_pll(hw);
-	struct at91_pmc *pmc = pll->pmc;
+	struct regmap *regmap = pll->regmap;
 	const struct clk_pll_layout *layout = pll->layout;
 	const struct clk_pll_characteristics *characteristics =
 							pll->characteristics;
@@ -90,39 +81,34 @@ static int clk_pll_prepare(struct clk_hw *hw)
 	u32 mask = PLL_STATUS_MASK(id);
 	int offset = PLL_REG(id);
 	u8 out = 0;
-	u32 pllr, icpr;
+	unsigned int pllr;
+	unsigned int status;
 	u8 div;
 	u16 mul;
 
-	pllr = pmc_read(pmc, offset);
+	regmap_read(regmap, offset, &pllr);
 	div = PLL_DIV(pllr);
 	mul = PLL_MUL(pllr, layout);
 
-	if ((pmc_read(pmc, AT91_PMC_SR) & mask) &&
+	regmap_read(regmap, AT91_PMC_SR, &status);
+	if ((status & mask) &&
 	    (div == pll->div && mul == pll->mul))
 		return 0;
 
 	if (characteristics->out)
 		out = characteristics->out[pll->range];
-	if (characteristics->icpll) {
-		icpr = pmc_read(pmc, AT91_PMC_PLLICPR) & ~PLL_ICPR_MASK(id);
-		icpr |= (characteristics->icpll[pll->range] <<
-			PLL_ICPR_SHIFT(id));
-		pmc_write(pmc, AT91_PMC_PLLICPR, icpr);
-	}
 
-	pllr &= ~layout->pllr_mask;
-	pllr |= layout->pllr_mask &
-	       (pll->div | (PLL_MAX_COUNT << PLL_COUNT_SHIFT) |
-		(out << PLL_OUT_SHIFT) |
-		((pll->mul & layout->mul_mask) << layout->mul_shift));
-	pmc_write(pmc, offset, pllr);
-
-	while (!(pmc_read(pmc, AT91_PMC_SR) & mask)) {
-		enable_irq(pll->irq);
-		wait_event(pll->wait,
-			   pmc_read(pmc, AT91_PMC_SR) & mask);
-	}
+	if (characteristics->icpll)
+		regmap_update_bits(regmap, AT91_PMC_PLLICPR, PLL_ICPR_MASK(id),
+			characteristics->icpll[pll->range] << PLL_ICPR_SHIFT(id));
+
+	regmap_update_bits(regmap, offset, layout->pllr_mask,
+			pll->div | (PLL_MAX_COUNT << PLL_COUNT_SHIFT) |
+			(out << PLL_OUT_SHIFT) |
+			((pll->mul & layout->mul_mask) << layout->mul_shift));
+
+	while (!clk_pll_ready(regmap, pll->id))
+		cpu_relax();
 
 	return 0;
 }
@@ -130,32 +116,35 @@ static int clk_pll_prepare(struct clk_hw *hw)
 static int clk_pll_is_prepared(struct clk_hw *hw)
 {
 	struct clk_pll *pll = to_clk_pll(hw);
-	struct at91_pmc *pmc = pll->pmc;
 
-	return !!(pmc_read(pmc, AT91_PMC_SR) &
-		  PLL_STATUS_MASK(pll->id));
+	return clk_pll_ready(pll->regmap, pll->id);
 }
 
 static void clk_pll_unprepare(struct clk_hw *hw)
 {
 	struct clk_pll *pll = to_clk_pll(hw);
-	struct at91_pmc *pmc = pll->pmc;
-	const struct clk_pll_layout *layout = pll->layout;
-	int offset = PLL_REG(pll->id);
-	u32 tmp = pmc_read(pmc, offset) & ~(layout->pllr_mask);
+	unsigned int mask = pll->layout->pllr_mask;
 
-	pmc_write(pmc, offset, tmp);
+	regmap_update_bits(pll->regmap, PLL_REG(pll->id), mask, ~mask);
 }
 
 static unsigned long clk_pll_recalc_rate(struct clk_hw *hw,
 					 unsigned long parent_rate)
 {
 	struct clk_pll *pll = to_clk_pll(hw);
+	unsigned int pllr;
+	u16 mul;
+	u8 div;
 
-	if (!pll->div || !pll->mul)
+	regmap_read(pll->regmap, PLL_REG(pll->id), &pllr);
+
+	div = PLL_DIV(pllr);
+	mul = PLL_MUL(pllr, pll->layout);
+
+	if (!div || !mul)
 		return 0;
 
-	return (parent_rate / pll->div) * (pll->mul + 1);
+	return (parent_rate / div) * (mul + 1);
 }
 
 static long clk_pll_get_best_div_mul(struct clk_pll *pll, unsigned long rate,
@@ -308,7 +297,7 @@ static const struct clk_ops pll_ops = {
 };
 
 static struct clk * __init
-at91_clk_register_pll(struct at91_pmc *pmc, unsigned int irq, const char *name,
+at91_clk_register_pll(struct regmap *regmap, const char *name,
 		      const char *parent_name, u8 id,
 		      const struct clk_pll_layout *layout,
 		      const struct clk_pll_characteristics *characteristics)
@@ -316,9 +305,8 @@ at91_clk_register_pll(struct at91_pmc *pmc, unsigned int irq, const char *name,
 	struct clk_pll *pll;
 	struct clk *clk = NULL;
 	struct clk_init_data init;
-	int ret;
 	int offset = PLL_REG(id);
-	u32 tmp;
+	unsigned int pllr;
 
 	if (id > PLL_MAX_ID)
 		return ERR_PTR(-EINVAL);
@@ -337,23 +325,13 @@ at91_clk_register_pll(struct at91_pmc *pmc, unsigned int irq, const char *name,
 	pll->hw.init = &init;
 	pll->layout = layout;
 	pll->characteristics = characteristics;
-	pll->pmc = pmc;
-	pll->irq = irq;
-	tmp = pmc_read(pmc, offset) & layout->pllr_mask;
-	pll->div = PLL_DIV(tmp);
-	pll->mul = PLL_MUL(tmp, layout);
-	init_waitqueue_head(&pll->wait);
-	irq_set_status_flags(pll->irq, IRQ_NOAUTOEN);
-	ret = request_irq(pll->irq, clk_pll_irq_handler, IRQF_TRIGGER_HIGH,
-			  id ? "clk-pllb" : "clk-plla", pll);
-	if (ret) {
-		kfree(pll);
-		return ERR_PTR(ret);
-	}
+	pll->regmap = regmap;
+	regmap_read(regmap, offset, &pllr);
+	pll->div = PLL_DIV(pllr);
+	pll->mul = PLL_MUL(pllr, layout);
 
 	clk = clk_register(NULL, &pll->hw);
 	if (IS_ERR(clk)) {
-		free_irq(pll->irq, pll);
 		kfree(pll);
 	}
 
@@ -483,12 +461,12 @@ out_free_characteristics:
 }
 
 static void __init
-of_at91_clk_pll_setup(struct device_node *np, struct at91_pmc *pmc,
+of_at91_clk_pll_setup(struct device_node *np,
 		      const struct clk_pll_layout *layout)
 {
 	u32 id;
-	unsigned int irq;
 	struct clk *clk;
+	struct regmap *regmap;
 	const char *parent_name;
 	const char *name = np->name;
 	struct clk_pll_characteristics *characteristics;
@@ -500,15 +478,15 @@ of_at91_clk_pll_setup(struct device_node *np, struct at91_pmc *pmc,
 
 	of_property_read_string(np, "clock-output-names", &name);
 
-	characteristics = of_at91_clk_pll_get_characteristics(np);
-	if (!characteristics)
+	regmap = syscon_node_to_regmap(of_get_parent(np));
+	if (IS_ERR(regmap))
 		return;
 
-	irq = irq_of_parse_and_map(np, 0);
-	if (!irq)
+	characteristics = of_at91_clk_pll_get_characteristics(np);
+	if (!characteristics)
 		return;
 
-	clk = at91_clk_register_pll(pmc, irq, name, parent_name, id, layout,
+	clk = at91_clk_register_pll(regmap, name, parent_name, id, layout,
 				    characteristics);
 	if (IS_ERR(clk))
 		goto out_free_characteristics;
@@ -520,26 +498,30 @@ out_free_characteristics:
 	kfree(characteristics);
 }
 
-void __init of_at91rm9200_clk_pll_setup(struct device_node *np,
-					       struct at91_pmc *pmc)
+static void __init of_at91rm9200_clk_pll_setup(struct device_node *np)
 {
-	of_at91_clk_pll_setup(np, pmc, &at91rm9200_pll_layout);
+	of_at91_clk_pll_setup(np, &at91rm9200_pll_layout);
 }
+CLK_OF_DECLARE(at91rm9200_clk_pll, "atmel,at91rm9200-clk-pll",
+	       of_at91rm9200_clk_pll_setup);
 
-void __init of_at91sam9g45_clk_pll_setup(struct device_node *np,
-						struct at91_pmc *pmc)
+static void __init of_at91sam9g45_clk_pll_setup(struct device_node *np)
 {
-	of_at91_clk_pll_setup(np, pmc, &at91sam9g45_pll_layout);
+	of_at91_clk_pll_setup(np, &at91sam9g45_pll_layout);
 }
+CLK_OF_DECLARE(at91sam9g45_clk_pll, "atmel,at91sam9g45-clk-pll",
+	       of_at91sam9g45_clk_pll_setup);
 
-void __init of_at91sam9g20_clk_pllb_setup(struct device_node *np,
-						 struct at91_pmc *pmc)
+static void __init of_at91sam9g20_clk_pllb_setup(struct device_node *np)
 {
-	of_at91_clk_pll_setup(np, pmc, &at91sam9g20_pllb_layout);
+	of_at91_clk_pll_setup(np, &at91sam9g20_pllb_layout);
 }
+CLK_OF_DECLARE(at91sam9g20_clk_pllb, "atmel,at91sam9g20-clk-pllb",
+	       of_at91sam9g20_clk_pllb_setup);
 
-void __init of_sama5d3_clk_pll_setup(struct device_node *np,
-					    struct at91_pmc *pmc)
+static void __init of_sama5d3_clk_pll_setup(struct device_node *np)
 {
-	of_at91_clk_pll_setup(np, pmc, &sama5d3_pll_layout);
+	of_at91_clk_pll_setup(np, &sama5d3_pll_layout);
 }
+CLK_OF_DECLARE(sama5d3_clk_pll, "atmel,sama5d3-clk-pll",
+	       of_sama5d3_clk_pll_setup);
diff --git a/drivers/clk/at91/clk-plldiv.c b/drivers/clk/at91/clk-plldiv.c
index ea226562bb40..2bed26481027 100644
--- a/drivers/clk/at91/clk-plldiv.c
+++ b/drivers/clk/at91/clk-plldiv.c
@@ -12,8 +12,8 @@
 #include <linux/clkdev.h>
 #include <linux/clk/at91_pmc.h>
 #include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/io.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
 
 #include "pmc.h"
 
@@ -21,16 +21,18 @@
 
 struct clk_plldiv {
 	struct clk_hw hw;
-	struct at91_pmc *pmc;
+	struct regmap *regmap;
 };
 
 static unsigned long clk_plldiv_recalc_rate(struct clk_hw *hw,
 					    unsigned long parent_rate)
 {
 	struct clk_plldiv *plldiv = to_clk_plldiv(hw);
-	struct at91_pmc *pmc = plldiv->pmc;
+	unsigned int mckr;
 
-	if (pmc_read(pmc, AT91_PMC_MCKR) & AT91_PMC_PLLADIV2)
+	regmap_read(plldiv->regmap, AT91_PMC_MCKR, &mckr);
+
+	if (mckr & AT91_PMC_PLLADIV2)
 		return parent_rate / 2;
 
 	return parent_rate;
@@ -57,18 +59,12 @@ static int clk_plldiv_set_rate(struct clk_hw *hw, unsigned long rate,
 			       unsigned long parent_rate)
 {
 	struct clk_plldiv *plldiv = to_clk_plldiv(hw);
-	struct at91_pmc *pmc = plldiv->pmc;
-	u32 tmp;
 
-	if (parent_rate != rate && (parent_rate / 2) != rate)
+	if ((parent_rate != rate) && (parent_rate / 2 != rate))
 		return -EINVAL;
 
-	pmc_lock(pmc);
-	tmp = pmc_read(pmc, AT91_PMC_MCKR) & ~AT91_PMC_PLLADIV2;
-	if ((parent_rate / 2) == rate)
-		tmp |= AT91_PMC_PLLADIV2;
-	pmc_write(pmc, AT91_PMC_MCKR, tmp);
-	pmc_unlock(pmc);
+	regmap_update_bits(plldiv->regmap, AT91_PMC_MCKR, AT91_PMC_PLLADIV2,
+			   parent_rate != rate ? AT91_PMC_PLLADIV2 : 0);
 
 	return 0;
 }
@@ -80,7 +76,7 @@ static const struct clk_ops plldiv_ops = {
 };
 
 static struct clk * __init
-at91_clk_register_plldiv(struct at91_pmc *pmc, const char *name,
+at91_clk_register_plldiv(struct regmap *regmap, const char *name,
 			 const char *parent_name)
 {
 	struct clk_plldiv *plldiv;
@@ -98,7 +94,7 @@ at91_clk_register_plldiv(struct at91_pmc *pmc, const char *name,
 	init.flags = CLK_SET_RATE_GATE;
 
 	plldiv->hw.init = &init;
-	plldiv->pmc = pmc;
+	plldiv->regmap = regmap;
 
 	clk = clk_register(NULL, &plldiv->hw);
 
@@ -109,27 +105,27 @@ at91_clk_register_plldiv(struct at91_pmc *pmc, const char *name,
 }
 
 static void __init
-of_at91_clk_plldiv_setup(struct device_node *np, struct at91_pmc *pmc)
+of_at91sam9x5_clk_plldiv_setup(struct device_node *np)
 {
 	struct clk *clk;
 	const char *parent_name;
 	const char *name = np->name;
+	struct regmap *regmap;
 
 	parent_name = of_clk_get_parent_name(np, 0);
 
 	of_property_read_string(np, "clock-output-names", &name);
 
-	clk = at91_clk_register_plldiv(pmc, name, parent_name);
+	regmap = syscon_node_to_regmap(of_get_parent(np));
+	if (IS_ERR(regmap))
+		return;
 
+	clk = at91_clk_register_plldiv(regmap, name, parent_name);
 	if (IS_ERR(clk))
 		return;
 
 	of_clk_add_provider(np, of_clk_src_simple_get, clk);
 	return;
 }
-
-void __init of_at91sam9x5_clk_plldiv_setup(struct device_node *np,
-					   struct at91_pmc *pmc)
-{
-	of_at91_clk_plldiv_setup(np, pmc);
-}
+CLK_OF_DECLARE(at91sam9x5_clk_plldiv, "atmel,at91sam9x5-clk-plldiv",
+	       of_at91sam9x5_clk_plldiv_setup);
diff --git a/drivers/clk/at91/clk-programmable.c b/drivers/clk/at91/clk-programmable.c
index 14b270b85fec..bc0be629671b 100644
--- a/drivers/clk/at91/clk-programmable.c
+++ b/drivers/clk/at91/clk-programmable.c
@@ -12,10 +12,8 @@
 #include <linux/clkdev.h>
 #include <linux/clk/at91_pmc.h>
 #include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/io.h>
-#include <linux/wait.h>
-#include <linux/sched.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
 
 #include "pmc.h"
 
@@ -24,6 +22,7 @@
 
 #define PROG_STATUS_MASK(id)	(1 << ((id) + 8))
 #define PROG_PRES_MASK		0x7
+#define PROG_PRES(layout, pckr)	((pckr >> layout->pres_shift) & PROG_PRES_MASK)
 #define PROG_MAX_RM9200_CSS	3
 
 struct clk_programmable_layout {
@@ -34,7 +33,7 @@ struct clk_programmable_layout {
 
 struct clk_programmable {
 	struct clk_hw hw;
-	struct at91_pmc *pmc;
+	struct regmap *regmap;
 	u8 id;
 	const struct clk_programmable_layout *layout;
 };
@@ -44,14 +43,12 @@ struct clk_programmable {
 static unsigned long clk_programmable_recalc_rate(struct clk_hw *hw,
 						  unsigned long parent_rate)
 {
-	u32 pres;
 	struct clk_programmable *prog = to_clk_programmable(hw);
-	struct at91_pmc *pmc = prog->pmc;
-	const struct clk_programmable_layout *layout = prog->layout;
+	unsigned int pckr;
+
+	regmap_read(prog->regmap, AT91_PMC_PCKR(prog->id), &pckr);
 
-	pres = (pmc_read(pmc, AT91_PMC_PCKR(prog->id)) >> layout->pres_shift) &
-	       PROG_PRES_MASK;
-	return parent_rate >> pres;
+	return parent_rate >> PROG_PRES(prog->layout, pckr);
 }
 
 static int clk_programmable_determine_rate(struct clk_hw *hw,
@@ -101,36 +98,36 @@ static int clk_programmable_set_parent(struct clk_hw *hw, u8 index)
 {
 	struct clk_programmable *prog = to_clk_programmable(hw);
 	const struct clk_programmable_layout *layout = prog->layout;
-	struct at91_pmc *pmc = prog->pmc;
-	u32 tmp = pmc_read(pmc, AT91_PMC_PCKR(prog->id)) & ~layout->css_mask;
+	unsigned int mask = layout->css_mask;
+	unsigned int pckr = 0;
 
 	if (layout->have_slck_mck)
-		tmp &= AT91_PMC_CSSMCK_MCK;
+		mask |= AT91_PMC_CSSMCK_MCK;
 
 	if (index > layout->css_mask) {
-		if (index > PROG_MAX_RM9200_CSS && layout->have_slck_mck) {
-			tmp |= AT91_PMC_CSSMCK_MCK;
-			return 0;
-		} else {
+		if (index > PROG_MAX_RM9200_CSS && !layout->have_slck_mck)
 			return -EINVAL;
-		}
+
+		pckr |= AT91_PMC_CSSMCK_MCK;
 	}
 
-	pmc_write(pmc, AT91_PMC_PCKR(prog->id), tmp | index);
+	regmap_update_bits(prog->regmap, AT91_PMC_PCKR(prog->id), mask, pckr);
+
 	return 0;
 }
 
 static u8 clk_programmable_get_parent(struct clk_hw *hw)
 {
-	u32 tmp;
-	u8 ret;
 	struct clk_programmable *prog = to_clk_programmable(hw);
-	struct at91_pmc *pmc = prog->pmc;
 	const struct clk_programmable_layout *layout = prog->layout;
+	unsigned int pckr;
+	u8 ret;
+
+	regmap_read(prog->regmap, AT91_PMC_PCKR(prog->id), &pckr);
+
+	ret = pckr & layout->css_mask;
 
-	tmp = pmc_read(pmc, AT91_PMC_PCKR(prog->id));
-	ret = tmp & layout->css_mask;
-	if (layout->have_slck_mck && (tmp & AT91_PMC_CSSMCK_MCK) && !ret)
+	if (layout->have_slck_mck && (pckr & AT91_PMC_CSSMCK_MCK) && !ret)
 		ret = PROG_MAX_RM9200_CSS + 1;
 
 	return ret;
@@ -140,26 +137,27 @@ static int clk_programmable_set_rate(struct clk_hw *hw, unsigned long rate,
 				     unsigned long parent_rate)
 {
 	struct clk_programmable *prog = to_clk_programmable(hw);
-	struct at91_pmc *pmc = prog->pmc;
 	const struct clk_programmable_layout *layout = prog->layout;
 	unsigned long div = parent_rate / rate;
+	unsigned int pckr;
 	int shift = 0;
-	u32 tmp = pmc_read(pmc, AT91_PMC_PCKR(prog->id)) &
-		  ~(PROG_PRES_MASK << layout->pres_shift);
+
+	regmap_read(prog->regmap, AT91_PMC_PCKR(prog->id), &pckr);
 
 	if (!div)
 		return -EINVAL;
 
 	shift = fls(div) - 1;
 
-	if (div != (1<<shift))
+	if (div != (1 << shift))
 		return -EINVAL;
 
 	if (shift >= PROG_PRES_MASK)
 		return -EINVAL;
 
-	pmc_write(pmc, AT91_PMC_PCKR(prog->id),
-		  tmp | (shift << layout->pres_shift));
+	regmap_update_bits(prog->regmap, AT91_PMC_PCKR(prog->id),
+			   PROG_PRES_MASK << layout->pres_shift,
+			   shift << layout->pres_shift);
 
 	return 0;
 }
@@ -173,7 +171,7 @@ static const struct clk_ops programmable_ops = {
 };
 
 static struct clk * __init
-at91_clk_register_programmable(struct at91_pmc *pmc,
+at91_clk_register_programmable(struct regmap *regmap,
 			       const char *name, const char **parent_names,
 			       u8 num_parents, u8 id,
 			       const struct clk_programmable_layout *layout)
@@ -198,7 +196,7 @@ at91_clk_register_programmable(struct at91_pmc *pmc,
 	prog->id = id;
 	prog->layout = layout;
 	prog->hw.init = &init;
-	prog->pmc = pmc;
+	prog->regmap = regmap;
 
 	clk = clk_register(NULL, &prog->hw);
 	if (IS_ERR(clk))
@@ -226,7 +224,7 @@ static const struct clk_programmable_layout at91sam9x5_programmable_layout = {
 };
 
 static void __init
-of_at91_clk_prog_setup(struct device_node *np, struct at91_pmc *pmc,
+of_at91_clk_prog_setup(struct device_node *np,
 		       const struct clk_programmable_layout *layout)
 {
 	int num;
@@ -236,6 +234,7 @@ of_at91_clk_prog_setup(struct device_node *np, struct at91_pmc *pmc,
 	const char *parent_names[PROG_SOURCE_MAX];
 	const char *name;
 	struct device_node *progclknp;
+	struct regmap *regmap;
 
 	num_parents = of_clk_get_parent_count(np);
 	if (num_parents <= 0 || num_parents > PROG_SOURCE_MAX)
@@ -247,6 +246,10 @@ of_at91_clk_prog_setup(struct device_node *np, struct at91_pmc *pmc,
 	if (!num || num > (PROG_ID_MAX + 1))
 		return;
 
+	regmap = syscon_node_to_regmap(of_get_parent(np));
+	if (IS_ERR(regmap))
+		return;
+
 	for_each_child_of_node(np, progclknp) {
 		if (of_property_read_u32(progclknp, "reg", &id))
 			continue;
@@ -254,7 +257,7 @@ of_at91_clk_prog_setup(struct device_node *np, struct at91_pmc *pmc,
 		if (of_property_read_string(np, "clock-output-names", &name))
 			name = progclknp->name;
 
-		clk = at91_clk_register_programmable(pmc, name,
+		clk = at91_clk_register_programmable(regmap, name,
 						     parent_names, num_parents,
 						     id, layout);
 		if (IS_ERR(clk))
@@ -265,20 +268,23 @@ of_at91_clk_prog_setup(struct device_node *np, struct at91_pmc *pmc,
 }
 
 
-void __init of_at91rm9200_clk_prog_setup(struct device_node *np,
-					 struct at91_pmc *pmc)
+static void __init of_at91rm9200_clk_prog_setup(struct device_node *np)
 {
-	of_at91_clk_prog_setup(np, pmc, &at91rm9200_programmable_layout);
+	of_at91_clk_prog_setup(np, &at91rm9200_programmable_layout);
 }
+CLK_OF_DECLARE(at91rm9200_clk_prog, "atmel,at91rm9200-clk-programmable",
+	       of_at91rm9200_clk_prog_setup);
 
-void __init of_at91sam9g45_clk_prog_setup(struct device_node *np,
-					  struct at91_pmc *pmc)
+static void __init of_at91sam9g45_clk_prog_setup(struct device_node *np)
 {
-	of_at91_clk_prog_setup(np, pmc, &at91sam9g45_programmable_layout);
+	of_at91_clk_prog_setup(np, &at91sam9g45_programmable_layout);
 }
+CLK_OF_DECLARE(at91sam9g45_clk_prog, "atmel,at91sam9g45-clk-programmable",
+	       of_at91sam9g45_clk_prog_setup);
 
-void __init of_at91sam9x5_clk_prog_setup(struct device_node *np,
-					 struct at91_pmc *pmc)
+static void __init of_at91sam9x5_clk_prog_setup(struct device_node *np)
 {
-	of_at91_clk_prog_setup(np, pmc, &at91sam9x5_programmable_layout);
+	of_at91_clk_prog_setup(np, &at91sam9x5_programmable_layout);
 }
+CLK_OF_DECLARE(at91sam9x5_clk_prog, "atmel,at91sam9x5-clk-programmable",
+	       of_at91sam9x5_clk_prog_setup);
diff --git a/drivers/clk/at91/clk-slow.c b/drivers/clk/at91/clk-slow.c
index d0d5076a9b94..221c09684ba3 100644
--- a/drivers/clk/at91/clk-slow.c
+++ b/drivers/clk/at91/clk-slow.c
@@ -13,17 +13,11 @@
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/clkdev.h>
-#include <linux/slab.h>
 #include <linux/clk/at91_pmc.h>
 #include <linux/delay.h>
 #include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-#include <linux/io.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/sched.h>
-#include <linux/wait.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
 
 #include "pmc.h"
 #include "sckc.h"
@@ -59,7 +53,7 @@ struct clk_slow_rc_osc {
 
 struct clk_sam9260_slow {
 	struct clk_hw hw;
-	struct at91_pmc *pmc;
+	struct regmap *regmap;
 };
 
 #define to_clk_sam9260_slow(hw) container_of(hw, struct clk_sam9260_slow, hw)
@@ -393,8 +387,11 @@ void __init of_at91sam9x5_clk_slow_setup(struct device_node *np,
 static u8 clk_sam9260_slow_get_parent(struct clk_hw *hw)
 {
 	struct clk_sam9260_slow *slowck = to_clk_sam9260_slow(hw);
+	unsigned int status;
 
-	return !!(pmc_read(slowck->pmc, AT91_PMC_SR) & AT91_PMC_OSCSEL);
+	regmap_read(slowck->regmap, AT91_PMC_SR, &status);
+
+	return status & AT91_PMC_OSCSEL ? 1 : 0;
 }
 
 static const struct clk_ops sam9260_slow_ops = {
@@ -402,7 +399,7 @@ static const struct clk_ops sam9260_slow_ops = {
 };
 
 static struct clk * __init
-at91_clk_register_sam9260_slow(struct at91_pmc *pmc,
+at91_clk_register_sam9260_slow(struct regmap *regmap,
 			       const char *name,
 			       const char **parent_names,
 			       int num_parents)
@@ -411,7 +408,7 @@ at91_clk_register_sam9260_slow(struct at91_pmc *pmc,
 	struct clk *clk = NULL;
 	struct clk_init_data init;
 
-	if (!pmc || !name)
+	if (!name)
 		return ERR_PTR(-EINVAL);
 
 	if (!parent_names || !num_parents)
@@ -428,7 +425,7 @@ at91_clk_register_sam9260_slow(struct at91_pmc *pmc,
 	init.flags = 0;
 
 	slowck->hw.init = &init;
-	slowck->pmc = pmc;
+	slowck->regmap = regmap;
 
 	clk = clk_register(NULL, &slowck->hw);
 	if (IS_ERR(clk))
@@ -439,29 +436,34 @@ at91_clk_register_sam9260_slow(struct at91_pmc *pmc,
 	return clk;
 }
 
-void __init of_at91sam9260_clk_slow_setup(struct device_node *np,
-					  struct at91_pmc *pmc)
+static void __init of_at91sam9260_clk_slow_setup(struct device_node *np)
 {
 	struct clk *clk;
 	const char *parent_names[2];
 	int num_parents;
 	const char *name = np->name;
+	struct regmap *regmap;
 
 	num_parents = of_clk_get_parent_count(np);
 	if (num_parents != 2)
 		return;
 
 	of_clk_parent_fill(np, parent_names, num_parents);
+	regmap = syscon_node_to_regmap(of_get_parent(np));
+	if (IS_ERR(regmap))
+		return;
 
 	of_property_read_string(np, "clock-output-names", &name);
 
-	clk = at91_clk_register_sam9260_slow(pmc, name, parent_names,
+	clk = at91_clk_register_sam9260_slow(regmap, name, parent_names,
 					     num_parents);
 	if (IS_ERR(clk))
 		return;
 
 	of_clk_add_provider(np, of_clk_src_simple_get, clk);
 }
+CLK_OF_DECLARE(at91sam9260_clk_slow, "atmel,at91sam9260-clk-slow",
+	       of_at91sam9260_clk_slow_setup);
 
 /*
  * FIXME: All slow clk users are not properly claiming it (get + prepare +
diff --git a/drivers/clk/at91/clk-smd.c b/drivers/clk/at91/clk-smd.c
index a7f8501cfa05..e6948a52005a 100644
--- a/drivers/clk/at91/clk-smd.c
+++ b/drivers/clk/at91/clk-smd.c
@@ -12,8 +12,8 @@
 #include <linux/clkdev.h>
 #include <linux/clk/at91_pmc.h>
 #include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/io.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
 
 #include "pmc.h"
 
@@ -24,7 +24,7 @@
 
 struct at91sam9x5_clk_smd {
 	struct clk_hw hw;
-	struct at91_pmc *pmc;
+	struct regmap *regmap;
 };
 
 #define to_at91sam9x5_clk_smd(hw) \
@@ -33,13 +33,13 @@ struct at91sam9x5_clk_smd {
 static unsigned long at91sam9x5_clk_smd_recalc_rate(struct clk_hw *hw,
 						    unsigned long parent_rate)
 {
-	u32 tmp;
-	u8 smddiv;
 	struct at91sam9x5_clk_smd *smd = to_at91sam9x5_clk_smd(hw);
-	struct at91_pmc *pmc = smd->pmc;
+	unsigned int smdr;
+	u8 smddiv;
+
+	regmap_read(smd->regmap, AT91_PMC_SMD, &smdr);
+	smddiv = (smdr & AT91_PMC_SMD_DIV) >> SMD_DIV_SHIFT;
 
-	tmp = pmc_read(pmc, AT91_PMC_SMD);
-	smddiv = (tmp & AT91_PMC_SMD_DIV) >> SMD_DIV_SHIFT;
 	return parent_rate / (smddiv + 1);
 }
 
@@ -67,40 +67,38 @@ static long at91sam9x5_clk_smd_round_rate(struct clk_hw *hw, unsigned long rate,
 
 static int at91sam9x5_clk_smd_set_parent(struct clk_hw *hw, u8 index)
 {
-	u32 tmp;
 	struct at91sam9x5_clk_smd *smd = to_at91sam9x5_clk_smd(hw);
-	struct at91_pmc *pmc = smd->pmc;
 
 	if (index > 1)
 		return -EINVAL;
-	tmp = pmc_read(pmc, AT91_PMC_SMD) & ~AT91_PMC_SMDS;
-	if (index)
-		tmp |= AT91_PMC_SMDS;
-	pmc_write(pmc, AT91_PMC_SMD, tmp);
+
+	regmap_update_bits(smd->regmap, AT91_PMC_SMD, AT91_PMC_SMDS,
+			   index ? AT91_PMC_SMDS : 0);
+
 	return 0;
 }
 
 static u8 at91sam9x5_clk_smd_get_parent(struct clk_hw *hw)
 {
 	struct at91sam9x5_clk_smd *smd = to_at91sam9x5_clk_smd(hw);
-	struct at91_pmc *pmc = smd->pmc;
+	unsigned int smdr;
 
-	return pmc_read(pmc, AT91_PMC_SMD) & AT91_PMC_SMDS;
+	regmap_read(smd->regmap, AT91_PMC_SMD, &smdr);
+
+	return smdr & AT91_PMC_SMDS;
 }
 
 static int at91sam9x5_clk_smd_set_rate(struct clk_hw *hw, unsigned long rate,
 				       unsigned long parent_rate)
 {
-	u32 tmp;
 	struct at91sam9x5_clk_smd *smd = to_at91sam9x5_clk_smd(hw);
-	struct at91_pmc *pmc = smd->pmc;
 	unsigned long div = parent_rate / rate;
 
 	if (parent_rate % rate || div < 1 || div > (SMD_MAX_DIV + 1))
 		return -EINVAL;
-	tmp = pmc_read(pmc, AT91_PMC_SMD) & ~AT91_PMC_SMD_DIV;
-	tmp |= (div - 1) << SMD_DIV_SHIFT;
-	pmc_write(pmc, AT91_PMC_SMD, tmp);
+
+	regmap_update_bits(smd->regmap, AT91_PMC_SMD, AT91_PMC_SMD_DIV,
+			   (div - 1) << SMD_DIV_SHIFT);
 
 	return 0;
 }
@@ -114,7 +112,7 @@ static const struct clk_ops at91sam9x5_smd_ops = {
 };
 
 static struct clk * __init
-at91sam9x5_clk_register_smd(struct at91_pmc *pmc, const char *name,
+at91sam9x5_clk_register_smd(struct regmap *regmap, const char *name,
 			    const char **parent_names, u8 num_parents)
 {
 	struct at91sam9x5_clk_smd *smd;
@@ -132,7 +130,7 @@ at91sam9x5_clk_register_smd(struct at91_pmc *pmc, const char *name,
 	init.flags = CLK_SET_RATE_GATE | CLK_SET_PARENT_GATE;
 
 	smd->hw.init = &init;
-	smd->pmc = pmc;
+	smd->regmap = regmap;
 
 	clk = clk_register(NULL, &smd->hw);
 	if (IS_ERR(clk))
@@ -141,13 +139,13 @@ at91sam9x5_clk_register_smd(struct at91_pmc *pmc, const char *name,
 	return clk;
 }
 
-void __init of_at91sam9x5_clk_smd_setup(struct device_node *np,
-					struct at91_pmc *pmc)
+static void __init of_at91sam9x5_clk_smd_setup(struct device_node *np)
 {
 	struct clk *clk;
 	int num_parents;
 	const char *parent_names[SMD_SOURCE_MAX];
 	const char *name = np->name;
+	struct regmap *regmap;
 
 	num_parents = of_clk_get_parent_count(np);
 	if (num_parents <= 0 || num_parents > SMD_SOURCE_MAX)
@@ -157,10 +155,16 @@ void __init of_at91sam9x5_clk_smd_setup(struct device_node *np,
 
 	of_property_read_string(np, "clock-output-names", &name);
 
-	clk = at91sam9x5_clk_register_smd(pmc, name, parent_names,
+	regmap = syscon_node_to_regmap(of_get_parent(np));
+	if (IS_ERR(regmap))
+		return;
+
+	clk = at91sam9x5_clk_register_smd(regmap, name, parent_names,
 					  num_parents);
 	if (IS_ERR(clk))
 		return;
 
 	of_clk_add_provider(np, of_clk_src_simple_get, clk);
 }
+CLK_OF_DECLARE(at91sam9x5_clk_smd, "atmel,at91sam9x5-clk-smd",
+	       of_at91sam9x5_clk_smd_setup);
diff --git a/drivers/clk/at91/clk-system.c b/drivers/clk/at91/clk-system.c
index 3f5314344286..8f35d8172909 100644
--- a/drivers/clk/at91/clk-system.c
+++ b/drivers/clk/at91/clk-system.c
@@ -12,13 +12,8 @@
 #include <linux/clkdev.h>
 #include <linux/clk/at91_pmc.h>
 #include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/io.h>
-#include <linux/irq.h>
-#include <linux/of_irq.h>
-#include <linux/interrupt.h>
-#include <linux/wait.h>
-#include <linux/sched.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
 
 #include "pmc.h"
 
@@ -29,9 +24,7 @@
 #define to_clk_system(hw) container_of(hw, struct clk_system, hw)
 struct clk_system {
 	struct clk_hw hw;
-	struct at91_pmc *pmc;
-	unsigned int irq;
-	wait_queue_head_t wait;
+	struct regmap *regmap;
 	u8 id;
 };
 
@@ -39,58 +32,54 @@ static inline int is_pck(int id)
 {
 	return (id >= 8) && (id <= 15);
 }
-static irqreturn_t clk_system_irq_handler(int irq, void *dev_id)
+
+static inline bool clk_system_ready(struct regmap *regmap, int id)
 {
-	struct clk_system *sys = (struct clk_system *)dev_id;
+	unsigned int status;
 
-	wake_up(&sys->wait);
-	disable_irq_nosync(sys->irq);
+	regmap_read(regmap, AT91_PMC_SR, &status);
 
-	return IRQ_HANDLED;
+	return status & (1 << id) ? 1 : 0;
 }
 
 static int clk_system_prepare(struct clk_hw *hw)
 {
 	struct clk_system *sys = to_clk_system(hw);
-	struct at91_pmc *pmc = sys->pmc;
-	u32 mask = 1 << sys->id;
 
-	pmc_write(pmc, AT91_PMC_SCER, mask);
+	regmap_write(sys->regmap, AT91_PMC_SCER, 1 << sys->id);
 
 	if (!is_pck(sys->id))
 		return 0;
 
-	while (!(pmc_read(pmc, AT91_PMC_SR) & mask)) {
-		if (sys->irq) {
-			enable_irq(sys->irq);
-			wait_event(sys->wait,
-				   pmc_read(pmc, AT91_PMC_SR) & mask);
-		} else
-			cpu_relax();
-	}
+	while (!clk_system_ready(sys->regmap, sys->id))
+		cpu_relax();
+
 	return 0;
 }
 
 static void clk_system_unprepare(struct clk_hw *hw)
 {
 	struct clk_system *sys = to_clk_system(hw);
-	struct at91_pmc *pmc = sys->pmc;
 
-	pmc_write(pmc, AT91_PMC_SCDR, 1 << sys->id);
+	regmap_write(sys->regmap, AT91_PMC_SCDR, 1 << sys->id);
 }
 
 static int clk_system_is_prepared(struct clk_hw *hw)
 {
 	struct clk_system *sys = to_clk_system(hw);
-	struct at91_pmc *pmc = sys->pmc;
+	unsigned int status;
+
+	regmap_read(sys->regmap, AT91_PMC_SCSR, &status);
 
-	if (!(pmc_read(pmc, AT91_PMC_SCSR) & (1 << sys->id)))
+	if (!(status & (1 << sys->id)))
 		return 0;
 
 	if (!is_pck(sys->id))
 		return 1;
 
-	return !!(pmc_read(pmc, AT91_PMC_SR) & (1 << sys->id));
+	regmap_read(sys->regmap, AT91_PMC_SR, &status);
+
+	return status & (1 << sys->id) ? 1 : 0;
 }
 
 static const struct clk_ops system_ops = {
@@ -100,13 +89,12 @@ static const struct clk_ops system_ops = {
 };
 
 static struct clk * __init
-at91_clk_register_system(struct at91_pmc *pmc, const char *name,
-			 const char *parent_name, u8 id, int irq)
+at91_clk_register_system(struct regmap *regmap, const char *name,
+			 const char *parent_name, u8 id)
 {
 	struct clk_system *sys;
 	struct clk *clk = NULL;
 	struct clk_init_data init;
-	int ret;
 
 	if (!parent_name || id > SYSTEM_MAX_ID)
 		return ERR_PTR(-EINVAL);
@@ -123,44 +111,33 @@ at91_clk_register_system(struct at91_pmc *pmc, const char *name,
 
 	sys->id = id;
 	sys->hw.init = &init;
-	sys->pmc = pmc;
-	sys->irq = irq;
-	if (irq) {
-		init_waitqueue_head(&sys->wait);
-		irq_set_status_flags(sys->irq, IRQ_NOAUTOEN);
-		ret = request_irq(sys->irq, clk_system_irq_handler,
-				IRQF_TRIGGER_HIGH, name, sys);
-		if (ret) {
-			kfree(sys);
-			return ERR_PTR(ret);
-		}
-	}
+	sys->regmap = regmap;
 
 	clk = clk_register(NULL, &sys->hw);
-	if (IS_ERR(clk)) {
-		if (irq)
-			free_irq(sys->irq, sys);
+	if (IS_ERR(clk))
 		kfree(sys);
-	}
 
 	return clk;
 }
 
-static void __init
-of_at91_clk_sys_setup(struct device_node *np, struct at91_pmc *pmc)
+static void __init of_at91rm9200_clk_sys_setup(struct device_node *np)
 {
 	int num;
-	int irq = 0;
 	u32 id;
 	struct clk *clk;
 	const char *name;
 	struct device_node *sysclknp;
 	const char *parent_name;
+	struct regmap *regmap;
 
 	num = of_get_child_count(np);
 	if (num > (SYSTEM_MAX_ID + 1))
 		return;
 
+	regmap = syscon_node_to_regmap(of_get_parent(np));
+	if (IS_ERR(regmap))
+		return;
+
 	for_each_child_of_node(np, sysclknp) {
 		if (of_property_read_u32(sysclknp, "reg", &id))
 			continue;
@@ -168,21 +145,14 @@ of_at91_clk_sys_setup(struct device_node *np, struct at91_pmc *pmc)
 		if (of_property_read_string(np, "clock-output-names", &name))
 			name = sysclknp->name;
 
-		if (is_pck(id))
-			irq = irq_of_parse_and_map(sysclknp, 0);
-
 		parent_name = of_clk_get_parent_name(sysclknp, 0);
 
-		clk = at91_clk_register_system(pmc, name, parent_name, id, irq);
+		clk = at91_clk_register_system(regmap, name, parent_name, id);
 		if (IS_ERR(clk))
 			continue;
 
 		of_clk_add_provider(sysclknp, of_clk_src_simple_get, clk);
 	}
 }
-
-void __init of_at91rm9200_clk_sys_setup(struct device_node *np,
-					struct at91_pmc *pmc)
-{
-	of_at91_clk_sys_setup(np, pmc);
-}
+CLK_OF_DECLARE(at91rm9200_clk_sys, "atmel,at91rm9200-clk-system",
+	       of_at91rm9200_clk_sys_setup);
diff --git a/drivers/clk/at91/clk-usb.c b/drivers/clk/at91/clk-usb.c
index 8ab8502778a2..650ca45892c0 100644
--- a/drivers/clk/at91/clk-usb.c
+++ b/drivers/clk/at91/clk-usb.c
@@ -12,8 +12,8 @@
 #include <linux/clkdev.h>
 #include <linux/clk/at91_pmc.h>
 #include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/io.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
 
 #include "pmc.h"
 
@@ -27,7 +27,7 @@
 
 struct at91sam9x5_clk_usb {
 	struct clk_hw hw;
-	struct at91_pmc *pmc;
+	struct regmap *regmap;
 };
 
 #define to_at91sam9x5_clk_usb(hw) \
@@ -35,7 +35,7 @@ struct at91sam9x5_clk_usb {
 
 struct at91rm9200_clk_usb {
 	struct clk_hw hw;
-	struct at91_pmc *pmc;
+	struct regmap *regmap;
 	u32 divisors[4];
 };
 
@@ -45,13 +45,12 @@ struct at91rm9200_clk_usb {
 static unsigned long at91sam9x5_clk_usb_recalc_rate(struct clk_hw *hw,
 						    unsigned long parent_rate)
 {
-	u32 tmp;
-	u8 usbdiv;
 	struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw);
-	struct at91_pmc *pmc = usb->pmc;
+	unsigned int usbr;
+	u8 usbdiv;
 
-	tmp = pmc_read(pmc, AT91_PMC_USB);
-	usbdiv = (tmp & AT91_PMC_OHCIUSBDIV) >> SAM9X5_USB_DIV_SHIFT;
+	regmap_read(usb->regmap, AT91_PMC_USB, &usbr);
+	usbdiv = (usbr & AT91_PMC_OHCIUSBDIV) >> SAM9X5_USB_DIV_SHIFT;
 
 	return DIV_ROUND_CLOSEST(parent_rate, (usbdiv + 1));
 }
@@ -109,33 +108,31 @@ static int at91sam9x5_clk_usb_determine_rate(struct clk_hw *hw,
 
 static int at91sam9x5_clk_usb_set_parent(struct clk_hw *hw, u8 index)
 {
-	u32 tmp;
 	struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw);
-	struct at91_pmc *pmc = usb->pmc;
 
 	if (index > 1)
 		return -EINVAL;
-	tmp = pmc_read(pmc, AT91_PMC_USB) & ~AT91_PMC_USBS;
-	if (index)
-		tmp |= AT91_PMC_USBS;
-	pmc_write(pmc, AT91_PMC_USB, tmp);
+
+	regmap_update_bits(usb->regmap, AT91_PMC_USB, AT91_PMC_USBS,
+			   index ? AT91_PMC_USBS : 0);
+
 	return 0;
 }
 
 static u8 at91sam9x5_clk_usb_get_parent(struct clk_hw *hw)
 {
 	struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw);
-	struct at91_pmc *pmc = usb->pmc;
+	unsigned int usbr;
 
-	return pmc_read(pmc, AT91_PMC_USB) & AT91_PMC_USBS;
+	regmap_read(usb->regmap, AT91_PMC_USB, &usbr);
+
+	return usbr & AT91_PMC_USBS;
 }
 
 static int at91sam9x5_clk_usb_set_rate(struct clk_hw *hw, unsigned long rate,
 				       unsigned long parent_rate)
 {
-	u32 tmp;
 	struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw);
-	struct at91_pmc *pmc = usb->pmc;
 	unsigned long div;
 
 	if (!rate)
@@ -145,9 +142,8 @@ static int at91sam9x5_clk_usb_set_rate(struct clk_hw *hw, unsigned long rate,
 	if (div > SAM9X5_USB_MAX_DIV + 1 || !div)
 		return -EINVAL;
 
-	tmp = pmc_read(pmc, AT91_PMC_USB) & ~AT91_PMC_OHCIUSBDIV;
-	tmp |= (div - 1) << SAM9X5_USB_DIV_SHIFT;
-	pmc_write(pmc, AT91_PMC_USB, tmp);
+	regmap_update_bits(usb->regmap, AT91_PMC_USB, AT91_PMC_OHCIUSBDIV,
+			   (div - 1) << SAM9X5_USB_DIV_SHIFT);
 
 	return 0;
 }
@@ -163,28 +159,28 @@ static const struct clk_ops at91sam9x5_usb_ops = {
 static int at91sam9n12_clk_usb_enable(struct clk_hw *hw)
 {
 	struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw);
-	struct at91_pmc *pmc = usb->pmc;
 
-	pmc_write(pmc, AT91_PMC_USB,
-		  pmc_read(pmc, AT91_PMC_USB) | AT91_PMC_USBS);
+	regmap_update_bits(usb->regmap, AT91_PMC_USB, AT91_PMC_USBS,
+			   AT91_PMC_USBS);
+
 	return 0;
 }
 
 static void at91sam9n12_clk_usb_disable(struct clk_hw *hw)
 {
 	struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw);
-	struct at91_pmc *pmc = usb->pmc;
 
-	pmc_write(pmc, AT91_PMC_USB,
-		  pmc_read(pmc, AT91_PMC_USB) & ~AT91_PMC_USBS);
+	regmap_update_bits(usb->regmap, AT91_PMC_USB, AT91_PMC_USBS, 0);
 }
 
 static int at91sam9n12_clk_usb_is_enabled(struct clk_hw *hw)
 {
 	struct at91sam9x5_clk_usb *usb = to_at91sam9x5_clk_usb(hw);
-	struct at91_pmc *pmc = usb->pmc;
+	unsigned int usbr;
 
-	return !!(pmc_read(pmc, AT91_PMC_USB) & AT91_PMC_USBS);
+	regmap_read(usb->regmap, AT91_PMC_USB, &usbr);
+
+	return usbr & AT91_PMC_USBS;
 }
 
 static const struct clk_ops at91sam9n12_usb_ops = {
@@ -197,7 +193,7 @@ static const struct clk_ops at91sam9n12_usb_ops = {
 };
 
 static struct clk * __init
-at91sam9x5_clk_register_usb(struct at91_pmc *pmc, const char *name,
+at91sam9x5_clk_register_usb(struct regmap *regmap, const char *name,
 			    const char **parent_names, u8 num_parents)
 {
 	struct at91sam9x5_clk_usb *usb;
@@ -216,7 +212,7 @@ at91sam9x5_clk_register_usb(struct at91_pmc *pmc, const char *name,
 		     CLK_SET_RATE_PARENT;
 
 	usb->hw.init = &init;
-	usb->pmc = pmc;
+	usb->regmap = regmap;
 
 	clk = clk_register(NULL, &usb->hw);
 	if (IS_ERR(clk))
@@ -226,7 +222,7 @@ at91sam9x5_clk_register_usb(struct at91_pmc *pmc, const char *name,
 }
 
 static struct clk * __init
-at91sam9n12_clk_register_usb(struct at91_pmc *pmc, const char *name,
+at91sam9n12_clk_register_usb(struct regmap *regmap, const char *name,
 			     const char *parent_name)
 {
 	struct at91sam9x5_clk_usb *usb;
@@ -244,7 +240,7 @@ at91sam9n12_clk_register_usb(struct at91_pmc *pmc, const char *name,
 	init.flags = CLK_SET_RATE_GATE | CLK_SET_RATE_PARENT;
 
 	usb->hw.init = &init;
-	usb->pmc = pmc;
+	usb->regmap = regmap;
 
 	clk = clk_register(NULL, &usb->hw);
 	if (IS_ERR(clk))
@@ -257,12 +253,12 @@ static unsigned long at91rm9200_clk_usb_recalc_rate(struct clk_hw *hw,
 						    unsigned long parent_rate)
 {
 	struct at91rm9200_clk_usb *usb = to_at91rm9200_clk_usb(hw);
-	struct at91_pmc *pmc = usb->pmc;
-	u32 tmp;
+	unsigned int pllbr;
 	u8 usbdiv;
 
-	tmp = pmc_read(pmc, AT91_CKGR_PLLBR);
-	usbdiv = (tmp & AT91_PMC_USBDIV) >> RM9200_USB_DIV_SHIFT;
+	regmap_read(usb->regmap, AT91_CKGR_PLLBR, &pllbr);
+
+	usbdiv = (pllbr & AT91_PMC_USBDIV) >> RM9200_USB_DIV_SHIFT;
 	if (usb->divisors[usbdiv])
 		return parent_rate / usb->divisors[usbdiv];
 
@@ -310,10 +306,8 @@ static long at91rm9200_clk_usb_round_rate(struct clk_hw *hw, unsigned long rate,
 static int at91rm9200_clk_usb_set_rate(struct clk_hw *hw, unsigned long rate,
 				       unsigned long parent_rate)
 {
-	u32 tmp;
 	int i;
 	struct at91rm9200_clk_usb *usb = to_at91rm9200_clk_usb(hw);
-	struct at91_pmc *pmc = usb->pmc;
 	unsigned long div;
 
 	if (!rate)
@@ -323,10 +317,10 @@ static int at91rm9200_clk_usb_set_rate(struct clk_hw *hw, unsigned long rate,
 
 	for (i = 0; i < RM9200_USB_DIV_TAB_SIZE; i++) {
 		if (usb->divisors[i] == div) {
-			tmp = pmc_read(pmc, AT91_CKGR_PLLBR) &
-			      ~AT91_PMC_USBDIV;
-			tmp |= i << RM9200_USB_DIV_SHIFT;
-			pmc_write(pmc, AT91_CKGR_PLLBR, tmp);
+			regmap_update_bits(usb->regmap, AT91_CKGR_PLLBR,
+					   AT91_PMC_USBDIV,
+					   i << RM9200_USB_DIV_SHIFT);
+
 			return 0;
 		}
 	}
@@ -341,7 +335,7 @@ static const struct clk_ops at91rm9200_usb_ops = {
 };
 
 static struct clk * __init
-at91rm9200_clk_register_usb(struct at91_pmc *pmc, const char *name,
+at91rm9200_clk_register_usb(struct regmap *regmap, const char *name,
 			    const char *parent_name, const u32 *divisors)
 {
 	struct at91rm9200_clk_usb *usb;
@@ -359,7 +353,7 @@ at91rm9200_clk_register_usb(struct at91_pmc *pmc, const char *name,
 	init.flags = CLK_SET_RATE_PARENT;
 
 	usb->hw.init = &init;
-	usb->pmc = pmc;
+	usb->regmap = regmap;
 	memcpy(usb->divisors, divisors, sizeof(usb->divisors));
 
 	clk = clk_register(NULL, &usb->hw);
@@ -369,13 +363,13 @@ at91rm9200_clk_register_usb(struct at91_pmc *pmc, const char *name,
 	return clk;
 }
 
-void __init of_at91sam9x5_clk_usb_setup(struct device_node *np,
-					struct at91_pmc *pmc)
+static void __init of_at91sam9x5_clk_usb_setup(struct device_node *np)
 {
 	struct clk *clk;
 	int num_parents;
 	const char *parent_names[USB_SOURCE_MAX];
 	const char *name = np->name;
+	struct regmap *regmap;
 
 	num_parents = of_clk_get_parent_count(np);
 	if (num_parents <= 0 || num_parents > USB_SOURCE_MAX)
@@ -385,19 +379,26 @@ void __init of_at91sam9x5_clk_usb_setup(struct device_node *np,
 
 	of_property_read_string(np, "clock-output-names", &name);
 
-	clk = at91sam9x5_clk_register_usb(pmc, name, parent_names, num_parents);
+	regmap = syscon_node_to_regmap(of_get_parent(np));
+	if (IS_ERR(regmap))
+		return;
+
+	clk = at91sam9x5_clk_register_usb(regmap, name, parent_names,
+					  num_parents);
 	if (IS_ERR(clk))
 		return;
 
 	of_clk_add_provider(np, of_clk_src_simple_get, clk);
 }
+CLK_OF_DECLARE(at91sam9x5_clk_usb, "atmel,at91sam9x5-clk-usb",
+	       of_at91sam9x5_clk_usb_setup);
 
-void __init of_at91sam9n12_clk_usb_setup(struct device_node *np,
-					 struct at91_pmc *pmc)
+static void __init of_at91sam9n12_clk_usb_setup(struct device_node *np)
 {
 	struct clk *clk;
 	const char *parent_name;
 	const char *name = np->name;
+	struct regmap *regmap;
 
 	parent_name = of_clk_get_parent_name(np, 0);
 	if (!parent_name)
@@ -405,20 +406,26 @@ void __init of_at91sam9n12_clk_usb_setup(struct device_node *np,
 
 	of_property_read_string(np, "clock-output-names", &name);
 
-	clk = at91sam9n12_clk_register_usb(pmc, name, parent_name);
+	regmap = syscon_node_to_regmap(of_get_parent(np));
+	if (IS_ERR(regmap))
+		return;
+
+	clk = at91sam9n12_clk_register_usb(regmap, name, parent_name);
 	if (IS_ERR(clk))
 		return;
 
 	of_clk_add_provider(np, of_clk_src_simple_get, clk);
 }
+CLK_OF_DECLARE(at91sam9n12_clk_usb, "atmel,at91sam9n12-clk-usb",
+	       of_at91sam9n12_clk_usb_setup);
 
-void __init of_at91rm9200_clk_usb_setup(struct device_node *np,
-					struct at91_pmc *pmc)
+static void __init of_at91rm9200_clk_usb_setup(struct device_node *np)
 {
 	struct clk *clk;
 	const char *parent_name;
 	const char *name = np->name;
 	u32 divisors[4] = {0, 0, 0, 0};
+	struct regmap *regmap;
 
 	parent_name = of_clk_get_parent_name(np, 0);
 	if (!parent_name)
@@ -430,9 +437,15 @@ void __init of_at91rm9200_clk_usb_setup(struct device_node *np,
 
 	of_property_read_string(np, "clock-output-names", &name);
 
-	clk = at91rm9200_clk_register_usb(pmc, name, parent_name, divisors);
+	regmap = syscon_node_to_regmap(of_get_parent(np));
+	if (IS_ERR(regmap))
+		return;
+
+	clk = at91rm9200_clk_register_usb(regmap, name, parent_name, divisors);
 	if (IS_ERR(clk))
 		return;
 
 	of_clk_add_provider(np, of_clk_src_simple_get, clk);
 }
+CLK_OF_DECLARE(at91rm9200_clk_usb, "atmel,at91rm9200-clk-usb",
+	       of_at91rm9200_clk_usb_setup);
diff --git a/drivers/clk/at91/clk-utmi.c b/drivers/clk/at91/clk-utmi.c
index ca561e90a60f..61fcf399e58c 100644
--- a/drivers/clk/at91/clk-utmi.c
+++ b/drivers/clk/at91/clk-utmi.c
@@ -11,14 +11,9 @@
 #include <linux/clk-provider.h>
 #include <linux/clkdev.h>
 #include <linux/clk/at91_pmc.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
 #include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-#include <linux/io.h>
-#include <linux/sched.h>
-#include <linux/wait.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
 
 #include "pmc.h"
 
@@ -26,37 +21,30 @@
 
 struct clk_utmi {
 	struct clk_hw hw;
-	struct at91_pmc *pmc;
-	unsigned int irq;
-	wait_queue_head_t wait;
+	struct regmap *regmap;
 };
 
 #define to_clk_utmi(hw) container_of(hw, struct clk_utmi, hw)
 
-static irqreturn_t clk_utmi_irq_handler(int irq, void *dev_id)
+static inline bool clk_utmi_ready(struct regmap *regmap)
 {
-	struct clk_utmi *utmi = (struct clk_utmi *)dev_id;
+	unsigned int status;
 
-	wake_up(&utmi->wait);
-	disable_irq_nosync(utmi->irq);
+	regmap_read(regmap, AT91_PMC_SR, &status);
 
-	return IRQ_HANDLED;
+	return status & AT91_PMC_LOCKU;
 }
 
 static int clk_utmi_prepare(struct clk_hw *hw)
 {
 	struct clk_utmi *utmi = to_clk_utmi(hw);
-	struct at91_pmc *pmc = utmi->pmc;
-	u32 tmp = pmc_read(pmc, AT91_CKGR_UCKR) | AT91_PMC_UPLLEN |
-		  AT91_PMC_UPLLCOUNT | AT91_PMC_BIASEN;
+	unsigned int uckr = AT91_PMC_UPLLEN | AT91_PMC_UPLLCOUNT |
+			    AT91_PMC_BIASEN;
 
-	pmc_write(pmc, AT91_CKGR_UCKR, tmp);
+	regmap_update_bits(utmi->regmap, AT91_CKGR_UCKR, uckr, uckr);
 
-	while (!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_LOCKU)) {
-		enable_irq(utmi->irq);
-		wait_event(utmi->wait,
-			   pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_LOCKU);
-	}
+	while (!clk_utmi_ready(utmi->regmap))
+		cpu_relax();
 
 	return 0;
 }
@@ -64,18 +52,15 @@ static int clk_utmi_prepare(struct clk_hw *hw)
 static int clk_utmi_is_prepared(struct clk_hw *hw)
 {
 	struct clk_utmi *utmi = to_clk_utmi(hw);
-	struct at91_pmc *pmc = utmi->pmc;
 
-	return !!(pmc_read(pmc, AT91_PMC_SR) & AT91_PMC_LOCKU);
+	return clk_utmi_ready(utmi->regmap);
 }
 
 static void clk_utmi_unprepare(struct clk_hw *hw)
 {
 	struct clk_utmi *utmi = to_clk_utmi(hw);
-	struct at91_pmc *pmc = utmi->pmc;
-	u32 tmp = pmc_read(pmc, AT91_CKGR_UCKR) & ~AT91_PMC_UPLLEN;
 
-	pmc_write(pmc, AT91_CKGR_UCKR, tmp);
+	regmap_update_bits(utmi->regmap, AT91_CKGR_UCKR, AT91_PMC_UPLLEN, 0);
 }
 
 static unsigned long clk_utmi_recalc_rate(struct clk_hw *hw,
@@ -93,10 +78,9 @@ static const struct clk_ops utmi_ops = {
 };
 
 static struct clk * __init
-at91_clk_register_utmi(struct at91_pmc *pmc, unsigned int irq,
+at91_clk_register_utmi(struct regmap *regmap,
 		       const char *name, const char *parent_name)
 {
-	int ret;
 	struct clk_utmi *utmi;
 	struct clk *clk = NULL;
 	struct clk_init_data init;
@@ -112,52 +96,36 @@ at91_clk_register_utmi(struct at91_pmc *pmc, unsigned int irq,
 	init.flags = CLK_SET_RATE_GATE;
 
 	utmi->hw.init = &init;
-	utmi->pmc = pmc;
-	utmi->irq = irq;
-	init_waitqueue_head(&utmi->wait);
-	irq_set_status_flags(utmi->irq, IRQ_NOAUTOEN);
-	ret = request_irq(utmi->irq, clk_utmi_irq_handler,
-			  IRQF_TRIGGER_HIGH, "clk-utmi", utmi);
-	if (ret) {
-		kfree(utmi);
-		return ERR_PTR(ret);
-	}
+	utmi->regmap = regmap;
 
 	clk = clk_register(NULL, &utmi->hw);
-	if (IS_ERR(clk)) {
-		free_irq(utmi->irq, utmi);
+	if (IS_ERR(clk))
 		kfree(utmi);
-	}
 
 	return clk;
 }
 
-static void __init
-of_at91_clk_utmi_setup(struct device_node *np, struct at91_pmc *pmc)
+static void __init of_at91sam9x5_clk_utmi_setup(struct device_node *np)
 {
-	unsigned int irq;
 	struct clk *clk;
 	const char *parent_name;
 	const char *name = np->name;
+	struct regmap *regmap;
 
 	parent_name = of_clk_get_parent_name(np, 0);
 
 	of_property_read_string(np, "clock-output-names", &name);
 
-	irq = irq_of_parse_and_map(np, 0);
-	if (!irq)
+	regmap = syscon_node_to_regmap(of_get_parent(np));
+	if (IS_ERR(regmap))
 		return;
 
-	clk = at91_clk_register_utmi(pmc, irq, name, parent_name);
+	clk = at91_clk_register_utmi(regmap, name, parent_name);
 	if (IS_ERR(clk))
 		return;
 
 	of_clk_add_provider(np, of_clk_src_simple_get, clk);
 	return;
 }
-
-void __init of_at91sam9x5_clk_utmi_setup(struct device_node *np,
-					 struct at91_pmc *pmc)
-{
-	of_at91_clk_utmi_setup(np, pmc);
-}
+CLK_OF_DECLARE(at91sam9x5_clk_utmi, "atmel,at91sam9x5-clk-utmi",
+	       of_at91sam9x5_clk_utmi_setup);
diff --git a/drivers/clk/at91/pmc.c b/drivers/clk/at91/pmc.c
index 8476b570779b..526df5ba042d 100644
--- a/drivers/clk/at91/pmc.c
+++ b/drivers/clk/at91/pmc.c
@@ -12,36 +12,13 @@
 #include <linux/clkdev.h>
 #include <linux/clk/at91_pmc.h>
 #include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/io.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/irqchip/chained_irq.h>
-#include <linux/irqdomain.h>
-#include <linux/of_irq.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
 
 #include <asm/proc-fns.h>
 
 #include "pmc.h"
 
-void __iomem *at91_pmc_base;
-EXPORT_SYMBOL_GPL(at91_pmc_base);
-
-void at91rm9200_idle(void)
-{
-	/*
-	 * Disable the processor clock.  The processor will be automatically
-	 * re-enabled by an interrupt or by a reset.
-	 */
-	at91_pmc_write(AT91_PMC_SCDR, AT91_PMC_PCK);
-}
-
-void at91sam9_idle(void)
-{
-	at91_pmc_write(AT91_PMC_SCDR, AT91_PMC_PCK);
-	cpu_do_idle();
-}
-
 int of_at91_get_clk_range(struct device_node *np, const char *propname,
 			  struct clk_range *range)
 {
@@ -64,402 +41,3 @@ int of_at91_get_clk_range(struct device_node *np, const char *propname,
 	return 0;
 }
 EXPORT_SYMBOL_GPL(of_at91_get_clk_range);
-
-static void pmc_irq_mask(struct irq_data *d)
-{
-	struct at91_pmc *pmc = irq_data_get_irq_chip_data(d);
-
-	pmc_write(pmc, AT91_PMC_IDR, 1 << d->hwirq);
-}
-
-static void pmc_irq_unmask(struct irq_data *d)
-{
-	struct at91_pmc *pmc = irq_data_get_irq_chip_data(d);
-
-	pmc_write(pmc, AT91_PMC_IER, 1 << d->hwirq);
-}
-
-static int pmc_irq_set_type(struct irq_data *d, unsigned type)
-{
-	if (type != IRQ_TYPE_LEVEL_HIGH) {
-		pr_warn("PMC: type not supported (support only IRQ_TYPE_LEVEL_HIGH type)\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-static void pmc_irq_suspend(struct irq_data *d)
-{
-	struct at91_pmc *pmc = irq_data_get_irq_chip_data(d);
-
-	pmc->imr = pmc_read(pmc, AT91_PMC_IMR);
-	pmc_write(pmc, AT91_PMC_IDR, pmc->imr);
-}
-
-static void pmc_irq_resume(struct irq_data *d)
-{
-	struct at91_pmc *pmc = irq_data_get_irq_chip_data(d);
-
-	pmc_write(pmc, AT91_PMC_IER, pmc->imr);
-}
-
-static struct irq_chip pmc_irq = {
-	.name = "PMC",
-	.irq_disable = pmc_irq_mask,
-	.irq_mask = pmc_irq_mask,
-	.irq_unmask = pmc_irq_unmask,
-	.irq_set_type = pmc_irq_set_type,
-	.irq_suspend = pmc_irq_suspend,
-	.irq_resume = pmc_irq_resume,
-};
-
-static struct lock_class_key pmc_lock_class;
-
-static int pmc_irq_map(struct irq_domain *h, unsigned int virq,
-		       irq_hw_number_t hw)
-{
-	struct at91_pmc	*pmc = h->host_data;
-
-	irq_set_lockdep_class(virq, &pmc_lock_class);
-
-	irq_set_chip_and_handler(virq, &pmc_irq,
-				 handle_level_irq);
-	irq_set_chip_data(virq, pmc);
-
-	return 0;
-}
-
-static int pmc_irq_domain_xlate(struct irq_domain *d,
-				struct device_node *ctrlr,
-				const u32 *intspec, unsigned int intsize,
-				irq_hw_number_t *out_hwirq,
-				unsigned int *out_type)
-{
-	struct at91_pmc *pmc = d->host_data;
-	const struct at91_pmc_caps *caps = pmc->caps;
-
-	if (WARN_ON(intsize < 1))
-		return -EINVAL;
-
-	*out_hwirq = intspec[0];
-
-	if (!(caps->available_irqs & (1 << *out_hwirq)))
-		return -EINVAL;
-
-	*out_type = IRQ_TYPE_LEVEL_HIGH;
-
-	return 0;
-}
-
-static const struct irq_domain_ops pmc_irq_ops = {
-	.map	= pmc_irq_map,
-	.xlate	= pmc_irq_domain_xlate,
-};
-
-static irqreturn_t pmc_irq_handler(int irq, void *data)
-{
-	struct at91_pmc *pmc = (struct at91_pmc *)data;
-	unsigned long sr;
-	int n;
-
-	sr = pmc_read(pmc, AT91_PMC_SR) & pmc_read(pmc, AT91_PMC_IMR);
-	if (!sr)
-		return IRQ_NONE;
-
-	for_each_set_bit(n, &sr, BITS_PER_LONG)
-		generic_handle_irq(irq_find_mapping(pmc->irqdomain, n));
-
-	return IRQ_HANDLED;
-}
-
-static const struct at91_pmc_caps at91rm9200_caps = {
-	.available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_LOCKB |
-			  AT91_PMC_MCKRDY | AT91_PMC_PCK0RDY |
-			  AT91_PMC_PCK1RDY | AT91_PMC_PCK2RDY |
-			  AT91_PMC_PCK3RDY,
-};
-
-static const struct at91_pmc_caps at91sam9260_caps = {
-	.available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_LOCKB |
-			  AT91_PMC_MCKRDY | AT91_PMC_PCK0RDY |
-			  AT91_PMC_PCK1RDY,
-};
-
-static const struct at91_pmc_caps at91sam9g45_caps = {
-	.available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_MCKRDY |
-			  AT91_PMC_LOCKU | AT91_PMC_PCK0RDY |
-			  AT91_PMC_PCK1RDY,
-};
-
-static const struct at91_pmc_caps at91sam9n12_caps = {
-	.available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_LOCKB |
-			  AT91_PMC_MCKRDY | AT91_PMC_PCK0RDY |
-			  AT91_PMC_PCK1RDY | AT91_PMC_MOSCSELS |
-			  AT91_PMC_MOSCRCS | AT91_PMC_CFDEV,
-};
-
-static const struct at91_pmc_caps at91sam9x5_caps = {
-	.available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_MCKRDY |
-			  AT91_PMC_LOCKU | AT91_PMC_PCK0RDY |
-			  AT91_PMC_PCK1RDY | AT91_PMC_MOSCSELS |
-			  AT91_PMC_MOSCRCS | AT91_PMC_CFDEV,
-};
-
-static const struct at91_pmc_caps sama5d2_caps = {
-	.available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_MCKRDY |
-			  AT91_PMC_LOCKU | AT91_PMC_PCK0RDY |
-			  AT91_PMC_PCK1RDY | AT91_PMC_PCK2RDY |
-			  AT91_PMC_MOSCSELS | AT91_PMC_MOSCRCS |
-			  AT91_PMC_CFDEV | AT91_PMC_GCKRDY,
-};
-
-static const struct at91_pmc_caps sama5d3_caps = {
-	.available_irqs = AT91_PMC_MOSCS | AT91_PMC_LOCKA | AT91_PMC_MCKRDY |
-			  AT91_PMC_LOCKU | AT91_PMC_PCK0RDY |
-			  AT91_PMC_PCK1RDY | AT91_PMC_PCK2RDY |
-			  AT91_PMC_MOSCSELS | AT91_PMC_MOSCRCS |
-			  AT91_PMC_CFDEV,
-};
-
-static struct at91_pmc *__init at91_pmc_init(struct device_node *np,
-					     void __iomem *regbase, int virq,
-					     const struct at91_pmc_caps *caps)
-{
-	struct at91_pmc *pmc;
-
-	if (!regbase || !virq ||  !caps)
-		return NULL;
-
-	at91_pmc_base = regbase;
-
-	pmc = kzalloc(sizeof(*pmc), GFP_KERNEL);
-	if (!pmc)
-		return NULL;
-
-	spin_lock_init(&pmc->lock);
-	pmc->regbase = regbase;
-	pmc->virq = virq;
-	pmc->caps = caps;
-
-	pmc->irqdomain = irq_domain_add_linear(np, 32, &pmc_irq_ops, pmc);
-
-	if (!pmc->irqdomain)
-		goto out_free_pmc;
-
-	pmc_write(pmc, AT91_PMC_IDR, 0xffffffff);
-	if (request_irq(pmc->virq, pmc_irq_handler,
-			IRQF_SHARED | IRQF_COND_SUSPEND, "pmc", pmc))
-		goto out_remove_irqdomain;
-
-	return pmc;
-
-out_remove_irqdomain:
-	irq_domain_remove(pmc->irqdomain);
-out_free_pmc:
-	kfree(pmc);
-
-	return NULL;
-}
-
-static const struct of_device_id pmc_clk_ids[] __initconst = {
-	/* Slow oscillator */
-	{
-		.compatible = "atmel,at91sam9260-clk-slow",
-		.data = of_at91sam9260_clk_slow_setup,
-	},
-	/* Main clock */
-	{
-		.compatible = "atmel,at91rm9200-clk-main-osc",
-		.data = of_at91rm9200_clk_main_osc_setup,
-	},
-	{
-		.compatible = "atmel,at91sam9x5-clk-main-rc-osc",
-		.data = of_at91sam9x5_clk_main_rc_osc_setup,
-	},
-	{
-		.compatible = "atmel,at91rm9200-clk-main",
-		.data = of_at91rm9200_clk_main_setup,
-	},
-	{
-		.compatible = "atmel,at91sam9x5-clk-main",
-		.data = of_at91sam9x5_clk_main_setup,
-	},
-	/* PLL clocks */
-	{
-		.compatible = "atmel,at91rm9200-clk-pll",
-		.data = of_at91rm9200_clk_pll_setup,
-	},
-	{
-		.compatible = "atmel,at91sam9g45-clk-pll",
-		.data = of_at91sam9g45_clk_pll_setup,
-	},
-	{
-		.compatible = "atmel,at91sam9g20-clk-pllb",
-		.data = of_at91sam9g20_clk_pllb_setup,
-	},
-	{
-		.compatible = "atmel,sama5d3-clk-pll",
-		.data = of_sama5d3_clk_pll_setup,
-	},
-	{
-		.compatible = "atmel,at91sam9x5-clk-plldiv",
-		.data = of_at91sam9x5_clk_plldiv_setup,
-	},
-	/* Master clock */
-	{
-		.compatible = "atmel,at91rm9200-clk-master",
-		.data = of_at91rm9200_clk_master_setup,
-	},
-	{
-		.compatible = "atmel,at91sam9x5-clk-master",
-		.data = of_at91sam9x5_clk_master_setup,
-	},
-	/* System clocks */
-	{
-		.compatible = "atmel,at91rm9200-clk-system",
-		.data = of_at91rm9200_clk_sys_setup,
-	},
-	/* Peripheral clocks */
-	{
-		.compatible = "atmel,at91rm9200-clk-peripheral",
-		.data = of_at91rm9200_clk_periph_setup,
-	},
-	{
-		.compatible = "atmel,at91sam9x5-clk-peripheral",
-		.data = of_at91sam9x5_clk_periph_setup,
-	},
-	/* Programmable clocks */
-	{
-		.compatible = "atmel,at91rm9200-clk-programmable",
-		.data = of_at91rm9200_clk_prog_setup,
-	},
-	{
-		.compatible = "atmel,at91sam9g45-clk-programmable",
-		.data = of_at91sam9g45_clk_prog_setup,
-	},
-	{
-		.compatible = "atmel,at91sam9x5-clk-programmable",
-		.data = of_at91sam9x5_clk_prog_setup,
-	},
-	/* UTMI clock */
-#if defined(CONFIG_HAVE_AT91_UTMI)
-	{
-		.compatible = "atmel,at91sam9x5-clk-utmi",
-		.data = of_at91sam9x5_clk_utmi_setup,
-	},
-#endif
-	/* USB clock */
-#if defined(CONFIG_HAVE_AT91_USB_CLK)
-	{
-		.compatible = "atmel,at91rm9200-clk-usb",
-		.data = of_at91rm9200_clk_usb_setup,
-	},
-	{
-		.compatible = "atmel,at91sam9x5-clk-usb",
-		.data = of_at91sam9x5_clk_usb_setup,
-	},
-	{
-		.compatible = "atmel,at91sam9n12-clk-usb",
-		.data = of_at91sam9n12_clk_usb_setup,
-	},
-#endif
-	/* SMD clock */
-#if defined(CONFIG_HAVE_AT91_SMD)
-	{
-		.compatible = "atmel,at91sam9x5-clk-smd",
-		.data = of_at91sam9x5_clk_smd_setup,
-	},
-#endif
-#if defined(CONFIG_HAVE_AT91_H32MX)
-	{
-		.compatible = "atmel,sama5d4-clk-h32mx",
-		.data = of_sama5d4_clk_h32mx_setup,
-	},
-#endif
-#if defined(CONFIG_HAVE_AT91_GENERATED_CLK)
-	{
-		.compatible = "atmel,sama5d2-clk-generated",
-		.data = of_sama5d2_clk_generated_setup,
-	},
-#endif
-	{ /*sentinel*/ }
-};
-
-static void __init of_at91_pmc_setup(struct device_node *np,
-				     const struct at91_pmc_caps *caps)
-{
-	struct at91_pmc *pmc;
-	struct device_node *childnp;
-	void (*clk_setup)(struct device_node *, struct at91_pmc *);
-	const struct of_device_id *clk_id;
-	void __iomem *regbase = of_iomap(np, 0);
-	int virq;
-
-	if (!regbase)
-		return;
-
-	virq = irq_of_parse_and_map(np, 0);
-	if (!virq)
-		return;
-
-	pmc = at91_pmc_init(np, regbase, virq, caps);
-	if (!pmc)
-		return;
-	for_each_child_of_node(np, childnp) {
-		clk_id = of_match_node(pmc_clk_ids, childnp);
-		if (!clk_id)
-			continue;
-		clk_setup = clk_id->data;
-		clk_setup(childnp, pmc);
-	}
-}
-
-static void __init of_at91rm9200_pmc_setup(struct device_node *np)
-{
-	of_at91_pmc_setup(np, &at91rm9200_caps);
-}
-CLK_OF_DECLARE(at91rm9200_clk_pmc, "atmel,at91rm9200-pmc",
-	       of_at91rm9200_pmc_setup);
-
-static void __init of_at91sam9260_pmc_setup(struct device_node *np)
-{
-	of_at91_pmc_setup(np, &at91sam9260_caps);
-}
-CLK_OF_DECLARE(at91sam9260_clk_pmc, "atmel,at91sam9260-pmc",
-	       of_at91sam9260_pmc_setup);
-
-static void __init of_at91sam9g45_pmc_setup(struct device_node *np)
-{
-	of_at91_pmc_setup(np, &at91sam9g45_caps);
-}
-CLK_OF_DECLARE(at91sam9g45_clk_pmc, "atmel,at91sam9g45-pmc",
-	       of_at91sam9g45_pmc_setup);
-
-static void __init of_at91sam9n12_pmc_setup(struct device_node *np)
-{
-	of_at91_pmc_setup(np, &at91sam9n12_caps);
-}
-CLK_OF_DECLARE(at91sam9n12_clk_pmc, "atmel,at91sam9n12-pmc",
-	       of_at91sam9n12_pmc_setup);
-
-static void __init of_at91sam9x5_pmc_setup(struct device_node *np)
-{
-	of_at91_pmc_setup(np, &at91sam9x5_caps);
-}
-CLK_OF_DECLARE(at91sam9x5_clk_pmc, "atmel,at91sam9x5-pmc",
-	       of_at91sam9x5_pmc_setup);
-
-static void __init of_sama5d2_pmc_setup(struct device_node *np)
-{
-	of_at91_pmc_setup(np, &sama5d2_caps);
-}
-CLK_OF_DECLARE(sama5d2_clk_pmc, "atmel,sama5d2-pmc",
-	       of_sama5d2_pmc_setup);
-
-static void __init of_sama5d3_pmc_setup(struct device_node *np)
-{
-	of_at91_pmc_setup(np, &sama5d3_caps);
-}
-CLK_OF_DECLARE(sama5d3_clk_pmc, "atmel,sama5d3-pmc",
-	       of_sama5d3_pmc_setup);
diff --git a/drivers/clk/at91/pmc.h b/drivers/clk/at91/pmc.h
index f65739272779..5771fff0ee3f 100644
--- a/drivers/clk/at91/pmc.h
+++ b/drivers/clk/at91/pmc.h
@@ -14,8 +14,11 @@
 
 #include <linux/io.h>
 #include <linux/irqdomain.h>
+#include <linux/regmap.h>
 #include <linux/spinlock.h>
 
+extern spinlock_t pmc_pcr_lock;
+
 struct clk_range {
 	unsigned long min;
 	unsigned long max;
@@ -23,102 +26,7 @@ struct clk_range {
 
 #define CLK_RANGE(MIN, MAX) {.min = MIN, .max = MAX,}
 
-struct at91_pmc_caps {
-	u32 available_irqs;
-};
-
-struct at91_pmc {
-	void __iomem *regbase;
-	int virq;
-	spinlock_t lock;
-	const struct at91_pmc_caps *caps;
-	struct irq_domain *irqdomain;
-	u32 imr;
-};
-
-static inline void pmc_lock(struct at91_pmc *pmc)
-{
-	spin_lock(&pmc->lock);
-}
-
-static inline void pmc_unlock(struct at91_pmc *pmc)
-{
-	spin_unlock(&pmc->lock);
-}
-
-static inline u32 pmc_read(struct at91_pmc *pmc, int offset)
-{
-	return readl(pmc->regbase + offset);
-}
-
-static inline void pmc_write(struct at91_pmc *pmc, int offset, u32 value)
-{
-	writel(value, pmc->regbase + offset);
-}
-
 int of_at91_get_clk_range(struct device_node *np, const char *propname,
 			  struct clk_range *range);
 
-void of_at91sam9260_clk_slow_setup(struct device_node *np,
-				   struct at91_pmc *pmc);
-
-void of_at91rm9200_clk_main_osc_setup(struct device_node *np,
-				      struct at91_pmc *pmc);
-void of_at91sam9x5_clk_main_rc_osc_setup(struct device_node *np,
-					 struct at91_pmc *pmc);
-void of_at91rm9200_clk_main_setup(struct device_node *np,
-				  struct at91_pmc *pmc);
-void of_at91sam9x5_clk_main_setup(struct device_node *np,
-				  struct at91_pmc *pmc);
-
-void of_at91rm9200_clk_pll_setup(struct device_node *np,
-				 struct at91_pmc *pmc);
-void of_at91sam9g45_clk_pll_setup(struct device_node *np,
-				  struct at91_pmc *pmc);
-void of_at91sam9g20_clk_pllb_setup(struct device_node *np,
-				   struct at91_pmc *pmc);
-void of_sama5d3_clk_pll_setup(struct device_node *np,
-			      struct at91_pmc *pmc);
-void of_at91sam9x5_clk_plldiv_setup(struct device_node *np,
-				    struct at91_pmc *pmc);
-
-void of_at91rm9200_clk_master_setup(struct device_node *np,
-				    struct at91_pmc *pmc);
-void of_at91sam9x5_clk_master_setup(struct device_node *np,
-				    struct at91_pmc *pmc);
-
-void of_at91rm9200_clk_sys_setup(struct device_node *np,
-				 struct at91_pmc *pmc);
-
-void of_at91rm9200_clk_periph_setup(struct device_node *np,
-				    struct at91_pmc *pmc);
-void of_at91sam9x5_clk_periph_setup(struct device_node *np,
-				    struct at91_pmc *pmc);
-
-void of_at91rm9200_clk_prog_setup(struct device_node *np,
-				  struct at91_pmc *pmc);
-void of_at91sam9g45_clk_prog_setup(struct device_node *np,
-				   struct at91_pmc *pmc);
-void of_at91sam9x5_clk_prog_setup(struct device_node *np,
-				  struct at91_pmc *pmc);
-
-void of_at91sam9x5_clk_utmi_setup(struct device_node *np,
-				  struct at91_pmc *pmc);
-
-void of_at91rm9200_clk_usb_setup(struct device_node *np,
-				 struct at91_pmc *pmc);
-void of_at91sam9x5_clk_usb_setup(struct device_node *np,
-				 struct at91_pmc *pmc);
-void of_at91sam9n12_clk_usb_setup(struct device_node *np,
-				  struct at91_pmc *pmc);
-
-void of_at91sam9x5_clk_smd_setup(struct device_node *np,
-				 struct at91_pmc *pmc);
-
-void of_sama5d4_clk_h32mx_setup(struct device_node *np,
-				struct at91_pmc *pmc);
-
-void of_sama5d2_clk_generated_setup(struct device_node *np,
-				    struct at91_pmc *pmc);
-
 #endif /* __PMC_H_ */
diff --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c
index 4da2af9694a2..5b6f57f500b8 100644
--- a/drivers/clocksource/tcb_clksrc.c
+++ b/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_clkevt(struct clock_event_device *clkevt)
 	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_event_device *d)
 
 	__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_event_device *d)
 	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_event_device *d)
 	/* 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 *handle)
 	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 atmel_tc *tc, int clk32k_divisor_idx)
 	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 atmel_tc *tc, int clk32k_divisor_idx)
 		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;
 
diff --git a/drivers/clocksource/timer-atmel-pit.c b/drivers/clocksource/timer-atmel-pit.c
index d911c5dca8f1..7a40f7e88468 100644
--- a/drivers/clocksource/timer-atmel-pit.c
+++ b/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 clock_event_device *dev)
 
 	/* 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));
@@ -181,7 +196,6 @@ static void __init at91sam926x_pit_common_init(struct pit_data *data)
 {
 	unsigned long	pit_rate;
 	unsigned	bits;
-	int		ret;
 
 	/*
 	 * Use our actual MCK to figure out how many MCK/16 ticks per
@@ -206,13 +220,6 @@ static void __init at91sam926x_pit_common_init(struct pit_data *data)
 	data->clksrc.flags = CLOCK_SOURCE_IS_CONTINUOUS;
 	clocksource_register_hz(&data->clksrc, pit_rate);
 
-	/* Set up irq handler */
-	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"));
-
 	/* Set up and register clockevents */
 	data->clkevt.name = "pit";
 	data->clkevt.features = CLOCK_EVT_FEAT_PERIODIC;
diff --git a/drivers/clocksource/timer-atmel-st.c b/drivers/clocksource/timer-atmel-st.c
index 29d21d68df5a..103d0fd70cc4 100644
--- a/drivers/clocksource/timer-atmel-st.c
+++ b/drivers/clocksource/timer-atmel-st.c
@@ -115,18 +115,29 @@ static void clkdev32k_disable_and_flush_irq(void)
 	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 clock_event_device *dev)
 
 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 void __init atmel_st_timer_init(struct device_node *node)
 {
 	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))
@@ -210,17 +229,10 @@ static void __init atmel_st_timer_init(struct device_node *node)
 	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)
 		panic(pr_fmt("Unable to get IRQ from DT\n"));
 
-	/* 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)
-		panic(pr_fmt("Unable to setup IRQ\n"));
-
 	sclk = of_clk_get(node, 0);
 	if (IS_ERR(sclk))
 		panic(pr_fmt("Unable to get slow clock\n"));
diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86
index c59bdcb83217..8f23161d80be 100644
--- a/drivers/cpufreq/Kconfig.x86
+++ b/drivers/cpufreq/Kconfig.x86
@@ -123,7 +123,7 @@ 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.
diff --git a/drivers/cpuidle/coupled.c b/drivers/cpuidle/coupled.c
index 344058f8501a..d5657d50ac40 100644
--- a/drivers/cpuidle/coupled.c
+++ b/drivers/cpuidle/coupled.c
@@ -119,7 +119,6 @@ struct cpuidle_coupled {
 
 #define CPUIDLE_COUPLED_NOT_IDLE	(-1)
 
-static DEFINE_MUTEX(cpuidle_coupled_lock);
 static DEFINE_PER_CPU(struct call_single_data, cpuidle_coupled_poke_cb);
 
 /*
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 6ed7d63a0688..9da7482ad256 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1264,7 +1264,9 @@ i915_gem_ringbuffer_submission(struct i915_execbuffer_params *params,
 	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);
 	i915_gem_execbuffer_retire_commands(params);
diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
index c0a96f1ee18e..deb1e207fa3c 100644
--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -39,7 +39,7 @@ static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task)
 	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 */
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 0f42a2782afc..80a1db09a379 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -812,6 +812,7 @@ static int i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
 	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(struct drm_device *dev, unsigned int pipe,
 		*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);
 
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 909d1d71d130..8688709b4ffa 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -11400,7 +11400,7 @@ void intel_check_page_flip(struct drm_device *dev, int pipe)
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 	struct intel_unpin_work *work;
 
-	WARN_ON(!in_interrupt());
+	WARN_ON_NONRT(!in_interrupt());
 
 	if (crtc == NULL)
 		return;
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 2cc6aa072f4c..b79d33f14868 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -38,6 +38,7 @@
 #include "intel_drv.h"
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
+#include <linux/locallock.h>
 
 static bool
 format_is_yuv(uint32_t format)
@@ -64,6 +65,8 @@ static int usecs_to_scanlines(const struct drm_display_mode *adjusted_mode,
 			    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
@@ -96,7 +99,7 @@ void intel_pipe_update_start(struct intel_crtc *crtc)
 	min = vblank_start - 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;
@@ -126,11 +129,11 @@ void intel_pipe_update_start(struct intel_crtc *crtc)
 			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);
@@ -164,7 +167,7 @@ void intel_pipe_update_end(struct intel_crtc *crtc)
 
 	trace_i915_pipe_update_end(crtc, end_vbl_count, scanline_end);
 
-	local_irq_enable();
+	local_unlock_irq(pipe_update_lock);
 
 	if (crtc->debug.start_vbl_count &&
 	    crtc->debug.start_vbl_count != end_vbl_count) {
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 3645b223aa37..642854b2ed2c 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -1862,6 +1862,7 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
 	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)
@@ -1954,6 +1955,7 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
 		*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;
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 509ed9731630..b2498b270f2c 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -820,7 +820,7 @@ static void vmbus_isr(void)
 			tasklet_schedule(&msg_dpc);
 	}
 
-	add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0);
+	add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0, 0);
 }
 
 
diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c
index 08d26ba61ed3..46b89dd42b10 100644
--- a/drivers/i2c/busses/i2c-omap.c
+++ b/drivers/i2c/busses/i2c-omap.c
@@ -995,15 +995,12 @@ omap_i2c_isr(int irq, void *dev_id)
 	u16 mask;
 	u16 stat;
 
-	spin_lock(&omap->lock);
-	mask = omap_i2c_read_reg(omap, OMAP_I2C_IE_REG);
 	stat = omap_i2c_read_reg(omap, OMAP_I2C_STAT_REG);
+	mask = omap_i2c_read_reg(omap, OMAP_I2C_IE_REG);
 
 	if (stat & mask)
 		ret = IRQ_WAKE_THREAD;
 
-	spin_unlock(&omap->lock);
-
 	return ret;
 }
 
diff --git a/drivers/ide/alim15x3.c b/drivers/ide/alim15x3.c
index 36f76e28a0bf..394f142f90c7 100644
--- a/drivers/ide/alim15x3.c
+++ b/drivers/ide/alim15x3.c
@@ -234,7 +234,7 @@ static int init_chipset_ali15x3(struct pci_dev *dev)
 
 	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;
 }
 
diff --git a/drivers/ide/hpt366.c b/drivers/ide/hpt366.c
index 696b6c1ec940..0d0a96629b73 100644
--- a/drivers/ide/hpt366.c
+++ b/drivers/ide/hpt366.c
@@ -1241,7 +1241,7 @@ static int init_dma_hpt366(ide_hwif_t *hwif,
 
 	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);
@@ -1252,7 +1252,7 @@ static int init_dma_hpt366(ide_hwif_t *hwif,
 	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);
diff --git a/drivers/ide/ide-io-std.c b/drivers/ide/ide-io-std.c
index 19763977568c..4169433faab5 100644
--- a/drivers/ide/ide-io-std.c
+++ b/drivers/ide/ide-io-std.c
@@ -175,7 +175,7 @@ void ide_input_data(ide_drive_t *drive, struct ide_cmd *cmd, void *buf,
 		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, struct ide_cmd *cmd, void *buf,
 			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, struct ide_cmd *cmd, void *buf,
 		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, struct ide_cmd *cmd, void *buf,
 			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;
diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c
index 669ea1e45795..e12e43e62245 100644
--- a/drivers/ide/ide-io.c
+++ b/drivers/ide/ide-io.c
@@ -659,7 +659,7 @@ void ide_timer_expiry (unsigned long data)
 		/* 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)) {
diff --git a/drivers/ide/ide-iops.c b/drivers/ide/ide-iops.c
index 376f2dc410c5..f014dd1b73dc 100644
--- a/drivers/ide/ide-iops.c
+++ b/drivers/ide/ide-iops.c
@@ -129,12 +129,12 @@ int __ide_wait_stat(ide_drive_t *drive, u8 good, u8 bad,
 				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.
diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c
index 0b63facd1d87..4ceba37afc0c 100644
--- a/drivers/ide/ide-probe.c
+++ b/drivers/ide/ide-probe.c
@@ -196,10 +196,10 @@ static void do_identify(ide_drive_t *drive, u8 cmd, u16 *id)
 	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
diff --git a/drivers/ide/ide-taskfile.c b/drivers/ide/ide-taskfile.c
index a716693417a3..be0568c722d6 100644
--- a/drivers/ide/ide-taskfile.c
+++ b/drivers/ide/ide-taskfile.c
@@ -250,7 +250,7 @@ void ide_pio_bytes(ide_drive_t *drive, struct ide_cmd *cmd,
 
 		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, struct ide_cmd *cmd,
 		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(ide_drive_t *drive,
 	}
 
 	if ((drive->dev_flags & IDE_DFLAG_UNMASK) == 0)
-		local_irq_disable();
+		local_irq_disable_nort();
 
 	ide_set_handler(drive, &task_pio_intr, WAIT_WORSTCASE);
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 87799de90a1d..66cdd37f8605 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -857,7 +857,7 @@ void ipoib_mcast_restart_task(struct work_struct *work)
 
 	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);
 
@@ -939,7 +939,7 @@ void ipoib_mcast_restart_task(struct work_struct *work)
 
 	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
diff --git a/drivers/input/gameport/gameport.c b/drivers/input/gameport/gameport.c
index 4a2a9e370be7..e970d9afd179 100644
--- a/drivers/input/gameport/gameport.c
+++ b/drivers/input/gameport/gameport.c
@@ -91,13 +91,13 @@ static int gameport_measure_speed(struct gameport *gameport)
 	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(struct gameport *gameport)
 	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(struct gameport *gameport)
 	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;
 	}
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 5975d76ce755..c8fc4c6a0a7b 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -2022,10 +2022,10 @@ static int __attach_device(struct iommu_dev_data *dev_data,
 	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);
@@ -2188,10 +2188,10 @@ static void __detach_device(struct iommu_dev_data *dev_data)
 	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;
diff --git a/drivers/leds/trigger/Kconfig b/drivers/leds/trigger/Kconfig
index 5bda6a9b56bb..d6286584c807 100644
--- a/drivers/leds/trigger/Kconfig
+++ b/drivers/leds/trigger/Kconfig
@@ -61,7 +61,7 @@ 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
diff --git a/drivers/md/bcache/Kconfig b/drivers/md/bcache/Kconfig
index 4d200883c505..98b64ed5cb81 100644
--- a/drivers/md/bcache/Kconfig
+++ b/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.
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 3384a3eef917..170a3c2d8872 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2127,7 +2127,7 @@ static void dm_request_fn(struct request_queue *q)
 		/* Establish tio->ti before queuing work (map_tio_request) */
 		tio->ti = ti;
 		queue_kthread_work(&md->kworker, &tio->work);
-		BUG_ON(!irqs_disabled());
+		BUG_ON_NONRT(!irqs_disabled());
 	}
 
 	goto out;
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 10ce885445f6..76f71791361c 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1920,8 +1920,9 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
 	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++;
@@ -1977,7 +1978,8 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
 			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)
@@ -6414,6 +6416,7 @@ static int raid5_alloc_percpu(struct r5conf *conf)
 			       __func__, cpu);
 			break;
 		}
+		spin_lock_init(&per_cpu_ptr(conf->percpu, cpu)->lock);
 	}
 	put_online_cpus();
 
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 517d4b68a1be..efe91887ecd7 100644
--- a/drivers/md/raid5.h
+++ b/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
diff --git a/drivers/media/platform/vsp1/vsp1_video.c b/drivers/media/platform/vsp1/vsp1_video.c
index 5ce88e1f5d71..b4f8cd74ecb8 100644
--- a/drivers/media/platform/vsp1/vsp1_video.c
+++ b/drivers/media/platform/vsp1/vsp1_video.c
@@ -520,7 +520,7 @@ static bool vsp1_pipeline_stopped(struct vsp1_pipeline *pipe)
 	bool stopped;
 
 	spin_lock_irqsave(&pipe->irqlock, flags);
-	stopped = pipe->state == VSP1_PIPELINE_STOPPED,
+	stopped = pipe->state == VSP1_PIPELINE_STOPPED;
 	spin_unlock_irqrestore(&pipe->irqlock, flags);
 
 	return stopped;
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index 4bf7d50b1bc7..6f7e99ad6e29 100644
--- a/drivers/misc/Kconfig
+++ b/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
@@ -113,6 +122,35 @@ config IBM_ASM
 	  for information on the specific driver level and support statement
 	  for your IBM server.
 
+config HWLAT_DETECTOR
+	tristate "Testing module to detect hardware-induced latencies"
+	depends on DEBUG_FS
+	depends on RING_BUFFER
+	default m
+	---help---
+	  A simple hardware latency detector. Use this module to detect
+	  large latencies introduced by the behavior of the underlying
+	  system firmware external to Linux. We do this using periodic
+	  use of stop_machine to grab all available CPUs and measure
+	  for unexplainable gaps in the CPU timestamp counter(s). By
+	  default, the module is not enabled until the "enable" file
+	  within the "hwlat_detector" debugfs directory is toggled.
+
+	  This module is often used to detect SMI (System Management
+	  Interrupts) on x86 systems, though is not x86 specific. To
+	  this end, we default to using a sample window of 1 second,
+	  during which we will sample for 0.5 seconds. If an SMI or
+	  similar event occurs during that time, it is recorded
+	  into an 8K samples global ring buffer until retreived.
+
+	  WARNING: This software should never be enabled (it can be built
+	  but should not be turned on after it is loaded) in a production
+	  environment where high latencies are a concern since the
+	  sampling mechanism actually introduces latencies for
+	  regular tasks while the CPU(s) are being held.
+
+	  If unsure, say N
+
 config PHANTOM
 	tristate "Sensable PHANToM (PCI)"
 	depends on PCI
diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile
index 537d7f3b78da..ec4aecba0656 100644
--- a/drivers/misc/Makefile
+++ b/drivers/misc/Makefile
@@ -39,6 +39,7 @@ obj-$(CONFIG_C2PORT)		+= c2port/
 obj-$(CONFIG_HMC6352)		+= hmc6352.o
 obj-y				+= eeprom/
 obj-y				+= cb710/
+obj-$(CONFIG_HWLAT_DETECTOR)	+= hwlat_detector.o
 obj-$(CONFIG_SPEAR13XX_PCIE_GADGET)	+= spear13xx_pcie_gadget.o
 obj-$(CONFIG_VMWARE_BALLOON)	+= vmw_balloon.o
 obj-$(CONFIG_ARM_CHARLCD)	+= arm-charlcd.o
diff --git a/drivers/misc/hwlat_detector.c b/drivers/misc/hwlat_detector.c
new file mode 100644
index 000000000000..52f5ad5fd9c0
--- /dev/null
+++ b/drivers/misc/hwlat_detector.c
@@ -0,0 +1,1240 @@
+/*
+ * hwlat_detector.c - A simple Hardware Latency detector.
+ *
+ * Use this module to detect large system latencies induced by the behavior of
+ * certain underlying system hardware or firmware, independent of Linux itself.
+ * The code was developed originally to detect the presence of SMIs on Intel
+ * and AMD systems, although there is no dependency upon x86 herein.
+ *
+ * The classical example usage of this module is in detecting the presence of
+ * SMIs or System Management Interrupts on Intel and AMD systems. An SMI is a
+ * somewhat special form of hardware interrupt spawned from earlier CPU debug
+ * modes in which the (BIOS/EFI/etc.) firmware arranges for the South Bridge
+ * LPC (or other device) to generate a special interrupt under certain
+ * circumstances, for example, upon expiration of a special SMI timer device,
+ * due to certain external thermal readings, on certain I/O address accesses,
+ * and other situations. An SMI hits a special CPU pin, triggers a special
+ * SMI mode (complete with special memory map), and the OS is unaware.
+ *
+ * Although certain hardware-inducing latencies are necessary (for example,
+ * a modern system often requires an SMI handler for correct thermal control
+ * and remote management) they can wreak havoc upon any OS-level performance
+ * guarantees toward low-latency, especially when the OS is not even made
+ * aware of the presence of these interrupts. For this reason, we need a
+ * somewhat brute force mechanism to detect these interrupts. In this case,
+ * we do it by hogging all of the CPU(s) for configurable timer intervals,
+ * sampling the built-in CPU timer, looking for discontiguous readings.
+ *
+ * WARNING: This implementation necessarily introduces latencies. Therefore,
+ *          you should NEVER use this module in a production environment
+ *          requiring any kind of low-latency performance guarantee(s).
+ *
+ * Copyright (C) 2008-2009 Jon Masters, Red Hat, Inc. <jcm@redhat.com>
+ *
+ * Includes useful feedback from Clark Williams <clark@redhat.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/ring_buffer.h>
+#include <linux/time.h>
+#include <linux/hrtimer.h>
+#include <linux/kthread.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/uaccess.h>
+#include <linux/version.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/trace_clock.h>
+
+#define BUF_SIZE_DEFAULT	262144UL		/* 8K*(sizeof(entry)) */
+#define BUF_FLAGS		(RB_FL_OVERWRITE)	/* no block on full */
+#define U64STR_SIZE		22			/* 20 digits max */
+
+#define VERSION			"1.0.0"
+#define BANNER			"hwlat_detector: "
+#define DRVNAME			"hwlat_detector"
+#define DEFAULT_SAMPLE_WINDOW	1000000			/* 1s */
+#define DEFAULT_SAMPLE_WIDTH	500000			/* 0.5s */
+#define DEFAULT_LAT_THRESHOLD	10			/* 10us */
+
+/* Module metadata */
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Jon Masters <jcm@redhat.com>");
+MODULE_DESCRIPTION("A simple hardware latency detector");
+MODULE_VERSION(VERSION);
+
+/* Module parameters */
+
+static int debug;
+static int enabled;
+static int threshold;
+
+module_param(debug, int, 0);			/* enable debug */
+module_param(enabled, int, 0);			/* enable detector */
+module_param(threshold, int, 0);		/* latency threshold */
+
+/* Buffering and sampling */
+
+static struct ring_buffer *ring_buffer;		/* sample buffer */
+static DEFINE_MUTEX(ring_buffer_mutex);		/* lock changes */
+static unsigned long buf_size = BUF_SIZE_DEFAULT;
+static struct task_struct *kthread;		/* sampling thread */
+
+/* DebugFS filesystem entries */
+
+static struct dentry *debug_dir;		/* debugfs directory */
+static struct dentry *debug_max;		/* maximum TSC delta */
+static struct dentry *debug_count;		/* total detect count */
+static struct dentry *debug_sample_width;	/* sample width us */
+static struct dentry *debug_sample_window;	/* sample window us */
+static struct dentry *debug_sample;		/* raw samples us */
+static struct dentry *debug_threshold;		/* threshold us */
+static struct dentry *debug_enable;		/* enable/disable */
+
+/* Individual samples and global state */
+
+struct sample;					/* latency sample */
+struct data;					/* Global state */
+
+/* Sampling functions */
+static int __buffer_add_sample(struct sample *sample);
+static struct sample *buffer_get_sample(struct sample *sample);
+
+/* Threading and state */
+static int kthread_fn(void *unused);
+static int start_kthread(void);
+static int stop_kthread(void);
+static void __reset_stats(void);
+static int init_stats(void);
+
+/* Debugfs interface */
+static ssize_t simple_data_read(struct file *filp, char __user *ubuf,
+				size_t cnt, loff_t *ppos, const u64 *entry);
+static ssize_t simple_data_write(struct file *filp, const char __user *ubuf,
+				 size_t cnt, loff_t *ppos, u64 *entry);
+static int debug_sample_fopen(struct inode *inode, struct file *filp);
+static ssize_t debug_sample_fread(struct file *filp, char __user *ubuf,
+				  size_t cnt, loff_t *ppos);
+static int debug_sample_release(struct inode *inode, struct file *filp);
+static int debug_enable_fopen(struct inode *inode, struct file *filp);
+static ssize_t debug_enable_fread(struct file *filp, char __user *ubuf,
+				  size_t cnt, loff_t *ppos);
+static ssize_t debug_enable_fwrite(struct file *file,
+				   const char __user *user_buffer,
+				   size_t user_size, loff_t *offset);
+
+/* Initialization functions */
+static int init_debugfs(void);
+static void free_debugfs(void);
+static int detector_init(void);
+static void detector_exit(void);
+
+/* Individual latency samples are stored here when detected and packed into
+ * the ring_buffer circular buffer, where they are overwritten when
+ * more than buf_size/sizeof(sample) samples are received. */
+struct sample {
+	u64		seqnum;		/* unique sequence */
+	u64		duration;	/* ktime delta */
+	u64		outer_duration;	/* ktime delta (outer loop) */
+	struct timespec	timestamp;	/* wall time */
+	unsigned long   lost;
+};
+
+/* keep the global state somewhere. */
+static struct data {
+
+	struct mutex lock;		/* protect changes */
+
+	u64	count;			/* total since reset */
+	u64	max_sample;		/* max hardware latency */
+	u64	threshold;		/* sample threshold level */
+
+	u64	sample_window;		/* total sampling window (on+off) */
+	u64	sample_width;		/* active sampling portion of window */
+
+	atomic_t sample_open;		/* whether the sample file is open */
+
+	wait_queue_head_t wq;		/* waitqeue for new sample values */
+
+} data;
+
+/**
+ * __buffer_add_sample - add a new latency sample recording to the ring buffer
+ * @sample: The new latency sample value
+ *
+ * This receives a new latency sample and records it in a global ring buffer.
+ * No additional locking is used in this case.
+ */
+static int __buffer_add_sample(struct sample *sample)
+{
+	return ring_buffer_write(ring_buffer,
+				 sizeof(struct sample), sample);
+}
+
+/**
+ * buffer_get_sample - remove a hardware latency sample from the ring buffer
+ * @sample: Pre-allocated storage for the sample
+ *
+ * This retrieves a hardware latency sample from the global circular buffer
+ */
+static struct sample *buffer_get_sample(struct sample *sample)
+{
+	struct ring_buffer_event *e = NULL;
+	struct sample *s = NULL;
+	unsigned int cpu = 0;
+
+	if (!sample)
+		return NULL;
+
+	mutex_lock(&ring_buffer_mutex);
+	for_each_online_cpu(cpu) {
+		e = ring_buffer_consume(ring_buffer, cpu, NULL, &sample->lost);
+		if (e)
+			break;
+	}
+
+	if (e) {
+		s = ring_buffer_event_data(e);
+		memcpy(sample, s, sizeof(struct sample));
+	} else
+		sample = NULL;
+	mutex_unlock(&ring_buffer_mutex);
+
+	return sample;
+}
+
+#ifndef CONFIG_TRACING
+#define time_type	ktime_t
+#define time_get()	ktime_get()
+#define time_to_us(x)	ktime_to_us(x)
+#define time_sub(a, b)	ktime_sub(a, b)
+#define init_time(a, b)	(a).tv64 = b
+#define time_u64(a)	((a).tv64)
+#else
+#define time_type	u64
+#define time_get()	trace_clock_local()
+#define time_to_us(x)	div_u64(x, 1000)
+#define time_sub(a, b)	((a) - (b))
+#define init_time(a, b)	(a = b)
+#define time_u64(a)	a
+#endif
+/**
+ * get_sample - sample the CPU TSC and look for likely hardware latencies
+ *
+ * Used to repeatedly capture the CPU TSC (or similar), looking for potential
+ * hardware-induced latency. Called with interrupts disabled and with
+ * data.lock held.
+ */
+static int get_sample(void)
+{
+	time_type start, t1, t2, last_t2;
+	s64 diff, total = 0;
+	u64 sample = 0;
+	u64 outer_sample = 0;
+	int ret = -1;
+
+	init_time(last_t2, 0);
+	start = time_get(); /* start timestamp */
+
+	do {
+
+		t1 = time_get();	/* we'll look for a discontinuity */
+		t2 = time_get();
+
+		if (time_u64(last_t2)) {
+			/* Check the delta from outer loop (t2 to next t1) */
+			diff = time_to_us(time_sub(t1, last_t2));
+			/* This shouldn't happen */
+			if (diff < 0) {
+				pr_err(BANNER "time running backwards\n");
+				goto out;
+			}
+			if (diff > outer_sample)
+				outer_sample = diff;
+		}
+		last_t2 = t2;
+
+		total = time_to_us(time_sub(t2, start)); /* sample width */
+
+		/* This checks the inner loop (t1 to t2) */
+		diff = time_to_us(time_sub(t2, t1));     /* current diff */
+
+		/* This shouldn't happen */
+		if (diff < 0) {
+			pr_err(BANNER "time running backwards\n");
+			goto out;
+		}
+
+		if (diff > sample)
+			sample = diff; /* only want highest value */
+
+	} while (total <= data.sample_width);
+
+	ret = 0;
+
+	/* If we exceed the threshold value, we have found a hardware latency */
+	if (sample > data.threshold || outer_sample > data.threshold) {
+		struct sample s;
+
+		ret = 1;
+
+		data.count++;
+		s.seqnum = data.count;
+		s.duration = sample;
+		s.outer_duration = outer_sample;
+		s.timestamp = CURRENT_TIME;
+		__buffer_add_sample(&s);
+
+		/* Keep a running maximum ever recorded hardware latency */
+		if (sample > data.max_sample)
+			data.max_sample = sample;
+	}
+
+out:
+	return ret;
+}
+
+/*
+ * kthread_fn - The CPU time sampling/hardware latency detection kernel thread
+ * @unused: A required part of the kthread API.
+ *
+ * Used to periodically sample the CPU TSC via a call to get_sample. We
+ * disable interrupts, which does (intentionally) introduce latency since we
+ * need to ensure nothing else might be running (and thus pre-empting).
+ * Obviously this should never be used in production environments.
+ *
+ * Currently this runs on which ever CPU it was scheduled on, but most
+ * real-worald hardware latency situations occur across several CPUs,
+ * but we might later generalize this if we find there are any actualy
+ * systems with alternate SMI delivery or other hardware latencies.
+ */
+static int kthread_fn(void *unused)
+{
+	int ret;
+	u64 interval;
+
+	while (!kthread_should_stop()) {
+
+		mutex_lock(&data.lock);
+
+		local_irq_disable();
+		ret = get_sample();
+		local_irq_enable();
+
+		if (ret > 0)
+			wake_up(&data.wq); /* wake up reader(s) */
+
+		interval = data.sample_window - data.sample_width;
+		do_div(interval, USEC_PER_MSEC); /* modifies interval value */
+
+		mutex_unlock(&data.lock);
+
+		if (msleep_interruptible(interval))
+			break;
+	}
+
+	return 0;
+}
+
+/**
+ * start_kthread - Kick off the hardware latency sampling/detector kthread
+ *
+ * This starts a kernel thread that will sit and sample the CPU timestamp
+ * counter (TSC or similar) and look for potential hardware latencies.
+ */
+static int start_kthread(void)
+{
+	kthread = kthread_run(kthread_fn, NULL,
+					DRVNAME);
+	if (IS_ERR(kthread)) {
+		pr_err(BANNER "could not start sampling thread\n");
+		enabled = 0;
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+/**
+ * stop_kthread - Inform the hardware latency samping/detector kthread to stop
+ *
+ * This kicks the running hardware latency sampling/detector kernel thread and
+ * tells it to stop sampling now. Use this on unload and at system shutdown.
+ */
+static int stop_kthread(void)
+{
+	int ret;
+
+	ret = kthread_stop(kthread);
+
+	return ret;
+}
+
+/**
+ * __reset_stats - Reset statistics for the hardware latency detector
+ *
+ * We use data to store various statistics and global state. We call this
+ * function in order to reset those when "enable" is toggled on or off, and
+ * also at initialization. Should be called with data.lock held.
+ */
+static void __reset_stats(void)
+{
+	data.count = 0;
+	data.max_sample = 0;
+	ring_buffer_reset(ring_buffer); /* flush out old sample entries */
+}
+
+/**
+ * init_stats - Setup global state statistics for the hardware latency detector
+ *
+ * We use data to store various statistics and global state. We also use
+ * a global ring buffer (ring_buffer) to keep raw samples of detected hardware
+ * induced system latencies. This function initializes these structures and
+ * allocates the global ring buffer also.
+ */
+static int init_stats(void)
+{
+	int ret = -ENOMEM;
+
+	mutex_init(&data.lock);
+	init_waitqueue_head(&data.wq);
+	atomic_set(&data.sample_open, 0);
+
+	ring_buffer = ring_buffer_alloc(buf_size, BUF_FLAGS);
+
+	if (WARN(!ring_buffer, KERN_ERR BANNER
+			       "failed to allocate ring buffer!\n"))
+		goto out;
+
+	__reset_stats();
+	data.threshold = threshold ?: DEFAULT_LAT_THRESHOLD; /* threshold us */
+	data.sample_window = DEFAULT_SAMPLE_WINDOW; /* window us */
+	data.sample_width = DEFAULT_SAMPLE_WIDTH;   /* width us */
+
+	ret = 0;
+
+out:
+	return ret;
+
+}
+
+/*
+ * simple_data_read - Wrapper read function for global state debugfs entries
+ * @filp: The active open file structure for the debugfs "file"
+ * @ubuf: The userspace provided buffer to read value into
+ * @cnt: The maximum number of bytes to read
+ * @ppos: The current "file" position
+ * @entry: The entry to read from
+ *
+ * This function provides a generic read implementation for the global state
+ * "data" structure debugfs filesystem entries. It would be nice to use
+ * simple_attr_read directly, but we need to make sure that the data.lock
+ * is held during the actual read.
+ */
+static ssize_t simple_data_read(struct file *filp, char __user *ubuf,
+				size_t cnt, loff_t *ppos, const u64 *entry)
+{
+	char buf[U64STR_SIZE];
+	u64 val = 0;
+	int len = 0;
+
+	memset(buf, 0, sizeof(buf));
+
+	if (!entry)
+		return -EFAULT;
+
+	mutex_lock(&data.lock);
+	val = *entry;
+	mutex_unlock(&data.lock);
+
+	len = snprintf(buf, sizeof(buf), "%llu\n", (unsigned long long)val);
+
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, len);
+
+}
+
+/*
+ * simple_data_write - Wrapper write function for global state debugfs entries
+ * @filp: The active open file structure for the debugfs "file"
+ * @ubuf: The userspace provided buffer to write value from
+ * @cnt: The maximum number of bytes to write
+ * @ppos: The current "file" position
+ * @entry: The entry to write to
+ *
+ * This function provides a generic write implementation for the global state
+ * "data" structure debugfs filesystem entries. It would be nice to use
+ * simple_attr_write directly, but we need to make sure that the data.lock
+ * is held during the actual write.
+ */
+static ssize_t simple_data_write(struct file *filp, const char __user *ubuf,
+				 size_t cnt, loff_t *ppos, u64 *entry)
+{
+	char buf[U64STR_SIZE];
+	int csize = min(cnt, sizeof(buf));
+	u64 val = 0;
+	int err = 0;
+
+	memset(buf, '\0', sizeof(buf));
+	if (copy_from_user(buf, ubuf, csize))
+		return -EFAULT;
+
+	buf[U64STR_SIZE-1] = '\0';			/* just in case */
+	err = kstrtoull(buf, 10, &val);
+	if (err)
+		return -EINVAL;
+
+	mutex_lock(&data.lock);
+	*entry = val;
+	mutex_unlock(&data.lock);
+
+	return csize;
+}
+
+/**
+ * debug_count_fopen - Open function for "count" debugfs entry
+ * @inode: The in-kernel inode representation of the debugfs "file"
+ * @filp: The active open file structure for the debugfs "file"
+ *
+ * This function provides an open implementation for the "count" debugfs
+ * interface to the hardware latency detector.
+ */
+static int debug_count_fopen(struct inode *inode, struct file *filp)
+{
+	return 0;
+}
+
+/**
+ * debug_count_fread - Read function for "count" debugfs entry
+ * @filp: The active open file structure for the debugfs "file"
+ * @ubuf: The userspace provided buffer to read value into
+ * @cnt: The maximum number of bytes to read
+ * @ppos: The current "file" position
+ *
+ * This function provides a read implementation for the "count" debugfs
+ * interface to the hardware latency detector. Can be used to read the
+ * number of latency readings exceeding the configured threshold since
+ * the detector was last reset (e.g. by writing a zero into "count").
+ */
+static ssize_t debug_count_fread(struct file *filp, char __user *ubuf,
+				     size_t cnt, loff_t *ppos)
+{
+	return simple_data_read(filp, ubuf, cnt, ppos, &data.count);
+}
+
+/**
+ * debug_count_fwrite - Write function for "count" debugfs entry
+ * @filp: The active open file structure for the debugfs "file"
+ * @ubuf: The user buffer that contains the value to write
+ * @cnt: The maximum number of bytes to write to "file"
+ * @ppos: The current position in the debugfs "file"
+ *
+ * This function provides a write implementation for the "count" debugfs
+ * interface to the hardware latency detector. Can be used to write a
+ * desired value, especially to zero the total count.
+ */
+static ssize_t  debug_count_fwrite(struct file *filp,
+				       const char __user *ubuf,
+				       size_t cnt,
+				       loff_t *ppos)
+{
+	return simple_data_write(filp, ubuf, cnt, ppos, &data.count);
+}
+
+/**
+ * debug_enable_fopen - Dummy open function for "enable" debugfs interface
+ * @inode: The in-kernel inode representation of the debugfs "file"
+ * @filp: The active open file structure for the debugfs "file"
+ *
+ * This function provides an open implementation for the "enable" debugfs
+ * interface to the hardware latency detector.
+ */
+static int debug_enable_fopen(struct inode *inode, struct file *filp)
+{
+	return 0;
+}
+
+/**
+ * debug_enable_fread - Read function for "enable" debugfs interface
+ * @filp: The active open file structure for the debugfs "file"
+ * @ubuf: The userspace provided buffer to read value into
+ * @cnt: The maximum number of bytes to read
+ * @ppos: The current "file" position
+ *
+ * This function provides a read implementation for the "enable" debugfs
+ * interface to the hardware latency detector. Can be used to determine
+ * whether the detector is currently enabled ("0\n" or "1\n" returned).
+ */
+static ssize_t debug_enable_fread(struct file *filp, char __user *ubuf,
+				      size_t cnt, loff_t *ppos)
+{
+	char buf[4];
+
+	if ((cnt < sizeof(buf)) || (*ppos))
+		return 0;
+
+	buf[0] = enabled ? '1' : '0';
+	buf[1] = '\n';
+	buf[2] = '\0';
+	if (copy_to_user(ubuf, buf, strlen(buf)))
+		return -EFAULT;
+	return *ppos = strlen(buf);
+}
+
+/**
+ * debug_enable_fwrite - Write function for "enable" debugfs interface
+ * @filp: The active open file structure for the debugfs "file"
+ * @ubuf: The user buffer that contains the value to write
+ * @cnt: The maximum number of bytes to write to "file"
+ * @ppos: The current position in the debugfs "file"
+ *
+ * This function provides a write implementation for the "enable" debugfs
+ * interface to the hardware latency detector. Can be used to enable or
+ * disable the detector, which will have the side-effect of possibly
+ * also resetting the global stats and kicking off the measuring
+ * kthread (on an enable) or the converse (upon a disable).
+ */
+static ssize_t  debug_enable_fwrite(struct file *filp,
+					const char __user *ubuf,
+					size_t cnt,
+					loff_t *ppos)
+{
+	char buf[4];
+	int csize = min(cnt, sizeof(buf));
+	long val = 0;
+	int err = 0;
+
+	memset(buf, '\0', sizeof(buf));
+	if (copy_from_user(buf, ubuf, csize))
+		return -EFAULT;
+
+	buf[sizeof(buf)-1] = '\0';			/* just in case */
+	err = kstrtoul(buf, 10, &val);
+	if (err)
+		return -EINVAL;
+
+	if (val) {
+		if (enabled)
+			goto unlock;
+		enabled = 1;
+		__reset_stats();
+		if (start_kthread())
+			return -EFAULT;
+	} else {
+		if (!enabled)
+			goto unlock;
+		enabled = 0;
+		err = stop_kthread();
+		if (err) {
+			pr_err(BANNER "cannot stop kthread\n");
+			return -EFAULT;
+		}
+		wake_up(&data.wq);		/* reader(s) should return */
+	}
+unlock:
+	return csize;
+}
+
+/**
+ * debug_max_fopen - Open function for "max" debugfs entry
+ * @inode: The in-kernel inode representation of the debugfs "file"
+ * @filp: The active open file structure for the debugfs "file"
+ *
+ * This function provides an open implementation for the "max" debugfs
+ * interface to the hardware latency detector.
+ */
+static int debug_max_fopen(struct inode *inode, struct file *filp)
+{
+	return 0;
+}
+
+/**
+ * debug_max_fread - Read function for "max" debugfs entry
+ * @filp: The active open file structure for the debugfs "file"
+ * @ubuf: The userspace provided buffer to read value into
+ * @cnt: The maximum number of bytes to read
+ * @ppos: The current "file" position
+ *
+ * This function provides a read implementation for the "max" debugfs
+ * interface to the hardware latency detector. Can be used to determine
+ * the maximum latency value observed since it was last reset.
+ */
+static ssize_t debug_max_fread(struct file *filp, char __user *ubuf,
+				   size_t cnt, loff_t *ppos)
+{
+	return simple_data_read(filp, ubuf, cnt, ppos, &data.max_sample);
+}
+
+/**
+ * debug_max_fwrite - Write function for "max" debugfs entry
+ * @filp: The active open file structure for the debugfs "file"
+ * @ubuf: The user buffer that contains the value to write
+ * @cnt: The maximum number of bytes to write to "file"
+ * @ppos: The current position in the debugfs "file"
+ *
+ * This function provides a write implementation for the "max" debugfs
+ * interface to the hardware latency detector. Can be used to reset the
+ * maximum or set it to some other desired value - if, then, subsequent
+ * measurements exceed this value, the maximum will be updated.
+ */
+static ssize_t  debug_max_fwrite(struct file *filp,
+				     const char __user *ubuf,
+				     size_t cnt,
+				     loff_t *ppos)
+{
+	return simple_data_write(filp, ubuf, cnt, ppos, &data.max_sample);
+}
+
+
+/**
+ * debug_sample_fopen - An open function for "sample" debugfs interface
+ * @inode: The in-kernel inode representation of this debugfs "file"
+ * @filp: The active open file structure for the debugfs "file"
+ *
+ * This function handles opening the "sample" file within the hardware
+ * latency detector debugfs directory interface. This file is used to read
+ * raw samples from the global ring_buffer and allows the user to see a
+ * running latency history. Can be opened blocking or non-blocking,
+ * affecting whether it behaves as a buffer read pipe, or does not.
+ * Implements simple locking to prevent multiple simultaneous use.
+ */
+static int debug_sample_fopen(struct inode *inode, struct file *filp)
+{
+	if (!atomic_add_unless(&data.sample_open, 1, 1))
+		return -EBUSY;
+	else
+		return 0;
+}
+
+/**
+ * debug_sample_fread - A read function for "sample" debugfs interface
+ * @filp: The active open file structure for the debugfs "file"
+ * @ubuf: The user buffer that will contain the samples read
+ * @cnt: The maximum bytes to read from the debugfs "file"
+ * @ppos: The current position in the debugfs "file"
+ *
+ * This function handles reading from the "sample" file within the hardware
+ * latency detector debugfs directory interface. This file is used to read
+ * raw samples from the global ring_buffer and allows the user to see a
+ * running latency history. By default this will block pending a new
+ * value written into the sample buffer, unless there are already a
+ * number of value(s) waiting in the buffer, or the sample file was
+ * previously opened in a non-blocking mode of operation.
+ */
+static ssize_t debug_sample_fread(struct file *filp, char __user *ubuf,
+					size_t cnt, loff_t *ppos)
+{
+	int len = 0;
+	char buf[64];
+	struct sample *sample = NULL;
+
+	if (!enabled)
+		return 0;
+
+	sample = kzalloc(sizeof(struct sample), GFP_KERNEL);
+	if (!sample)
+		return -ENOMEM;
+
+	while (!buffer_get_sample(sample)) {
+
+		DEFINE_WAIT(wait);
+
+		if (filp->f_flags & O_NONBLOCK) {
+			len = -EAGAIN;
+			goto out;
+		}
+
+		prepare_to_wait(&data.wq, &wait, TASK_INTERRUPTIBLE);
+		schedule();
+		finish_wait(&data.wq, &wait);
+
+		if (signal_pending(current)) {
+			len = -EINTR;
+			goto out;
+		}
+
+		if (!enabled) {			/* enable was toggled */
+			len = 0;
+			goto out;
+		}
+	}
+
+	len = snprintf(buf, sizeof(buf), "%010lu.%010lu\t%llu\t%llu\n",
+		       sample->timestamp.tv_sec,
+		       sample->timestamp.tv_nsec,
+		       sample->duration,
+		       sample->outer_duration);
+
+
+	/* handling partial reads is more trouble than it's worth */
+	if (len > cnt)
+		goto out;
+
+	if (copy_to_user(ubuf, buf, len))
+		len = -EFAULT;
+
+out:
+	kfree(sample);
+	return len;
+}
+
+/**
+ * debug_sample_release - Release function for "sample" debugfs interface
+ * @inode: The in-kernel inode represenation of the debugfs "file"
+ * @filp: The active open file structure for the debugfs "file"
+ *
+ * This function completes the close of the debugfs interface "sample" file.
+ * Frees the sample_open "lock" so that other users may open the interface.
+ */
+static int debug_sample_release(struct inode *inode, struct file *filp)
+{
+	atomic_dec(&data.sample_open);
+
+	return 0;
+}
+
+/**
+ * debug_threshold_fopen - Open function for "threshold" debugfs entry
+ * @inode: The in-kernel inode representation of the debugfs "file"
+ * @filp: The active open file structure for the debugfs "file"
+ *
+ * This function provides an open implementation for the "threshold" debugfs
+ * interface to the hardware latency detector.
+ */
+static int debug_threshold_fopen(struct inode *inode, struct file *filp)
+{
+	return 0;
+}
+
+/**
+ * debug_threshold_fread - Read function for "threshold" debugfs entry
+ * @filp: The active open file structure for the debugfs "file"
+ * @ubuf: The userspace provided buffer to read value into
+ * @cnt: The maximum number of bytes to read
+ * @ppos: The current "file" position
+ *
+ * This function provides a read implementation for the "threshold" debugfs
+ * interface to the hardware latency detector. It can be used to determine
+ * the current threshold level at which a latency will be recorded in the
+ * global ring buffer, typically on the order of 10us.
+ */
+static ssize_t debug_threshold_fread(struct file *filp, char __user *ubuf,
+					 size_t cnt, loff_t *ppos)
+{
+	return simple_data_read(filp, ubuf, cnt, ppos, &data.threshold);
+}
+
+/**
+ * debug_threshold_fwrite - Write function for "threshold" debugfs entry
+ * @filp: The active open file structure for the debugfs "file"
+ * @ubuf: The user buffer that contains the value to write
+ * @cnt: The maximum number of bytes to write to "file"
+ * @ppos: The current position in the debugfs "file"
+ *
+ * This function provides a write implementation for the "threshold" debugfs
+ * interface to the hardware latency detector. It can be used to configure
+ * the threshold level at which any subsequently detected latencies will
+ * be recorded into the global ring buffer.
+ */
+static ssize_t  debug_threshold_fwrite(struct file *filp,
+					const char __user *ubuf,
+					size_t cnt,
+					loff_t *ppos)
+{
+	int ret;
+
+	ret = simple_data_write(filp, ubuf, cnt, ppos, &data.threshold);
+
+	if (enabled)
+		wake_up_process(kthread);
+
+	return ret;
+}
+
+/**
+ * debug_width_fopen - Open function for "width" debugfs entry
+ * @inode: The in-kernel inode representation of the debugfs "file"
+ * @filp: The active open file structure for the debugfs "file"
+ *
+ * This function provides an open implementation for the "width" debugfs
+ * interface to the hardware latency detector.
+ */
+static int debug_width_fopen(struct inode *inode, struct file *filp)
+{
+	return 0;
+}
+
+/**
+ * debug_width_fread - Read function for "width" debugfs entry
+ * @filp: The active open file structure for the debugfs "file"
+ * @ubuf: The userspace provided buffer to read value into
+ * @cnt: The maximum number of bytes to read
+ * @ppos: The current "file" position
+ *
+ * This function provides a read implementation for the "width" debugfs
+ * interface to the hardware latency detector. It can be used to determine
+ * for how many us of the total window us we will actively sample for any
+ * hardware-induced latecy periods. Obviously, it is not possible to
+ * sample constantly and have the system respond to a sample reader, or,
+ * worse, without having the system appear to have gone out to lunch.
+ */
+static ssize_t debug_width_fread(struct file *filp, char __user *ubuf,
+				     size_t cnt, loff_t *ppos)
+{
+	return simple_data_read(filp, ubuf, cnt, ppos, &data.sample_width);
+}
+
+/**
+ * debug_width_fwrite - Write function for "width" debugfs entry
+ * @filp: The active open file structure for the debugfs "file"
+ * @ubuf: The user buffer that contains the value to write
+ * @cnt: The maximum number of bytes to write to "file"
+ * @ppos: The current position in the debugfs "file"
+ *
+ * This function provides a write implementation for the "width" debugfs
+ * interface to the hardware latency detector. It can be used to configure
+ * for how many us of the total window us we will actively sample for any
+ * hardware-induced latency periods. Obviously, it is not possible to
+ * sample constantly and have the system respond to a sample reader, or,
+ * worse, without having the system appear to have gone out to lunch. It
+ * is enforced that width is less that the total window size.
+ */
+static ssize_t  debug_width_fwrite(struct file *filp,
+				       const char __user *ubuf,
+				       size_t cnt,
+				       loff_t *ppos)
+{
+	char buf[U64STR_SIZE];
+	int csize = min(cnt, sizeof(buf));
+	u64 val = 0;
+	int err = 0;
+
+	memset(buf, '\0', sizeof(buf));
+	if (copy_from_user(buf, ubuf, csize))
+		return -EFAULT;
+
+	buf[U64STR_SIZE-1] = '\0';			/* just in case */
+	err = kstrtoull(buf, 10, &val);
+	if (err)
+		return -EINVAL;
+
+	mutex_lock(&data.lock);
+	if (val < data.sample_window)
+		data.sample_width = val;
+	else {
+		mutex_unlock(&data.lock);
+		return -EINVAL;
+	}
+	mutex_unlock(&data.lock);
+
+	if (enabled)
+		wake_up_process(kthread);
+
+	return csize;
+}
+
+/**
+ * debug_window_fopen - Open function for "window" debugfs entry
+ * @inode: The in-kernel inode representation of the debugfs "file"
+ * @filp: The active open file structure for the debugfs "file"
+ *
+ * This function provides an open implementation for the "window" debugfs
+ * interface to the hardware latency detector. The window is the total time
+ * in us that will be considered one sample period. Conceptually, windows
+ * occur back-to-back and contain a sample width period during which
+ * actual sampling occurs.
+ */
+static int debug_window_fopen(struct inode *inode, struct file *filp)
+{
+	return 0;
+}
+
+/**
+ * debug_window_fread - Read function for "window" debugfs entry
+ * @filp: The active open file structure for the debugfs "file"
+ * @ubuf: The userspace provided buffer to read value into
+ * @cnt: The maximum number of bytes to read
+ * @ppos: The current "file" position
+ *
+ * This function provides a read implementation for the "window" debugfs
+ * interface to the hardware latency detector. The window is the total time
+ * in us that will be considered one sample period. Conceptually, windows
+ * occur back-to-back and contain a sample width period during which
+ * actual sampling occurs. Can be used to read the total window size.
+ */
+static ssize_t debug_window_fread(struct file *filp, char __user *ubuf,
+				      size_t cnt, loff_t *ppos)
+{
+	return simple_data_read(filp, ubuf, cnt, ppos, &data.sample_window);
+}
+
+/**
+ * debug_window_fwrite - Write function for "window" debugfs entry
+ * @filp: The active open file structure for the debugfs "file"
+ * @ubuf: The user buffer that contains the value to write
+ * @cnt: The maximum number of bytes to write to "file"
+ * @ppos: The current position in the debugfs "file"
+ *
+ * This function provides a write implementation for the "window" debufds
+ * interface to the hardware latency detetector. The window is the total time
+ * in us that will be considered one sample period. Conceptually, windows
+ * occur back-to-back and contain a sample width period during which
+ * actual sampling occurs. Can be used to write a new total window size. It
+ * is enfoced that any value written must be greater than the sample width
+ * size, or an error results.
+ */
+static ssize_t  debug_window_fwrite(struct file *filp,
+					const char __user *ubuf,
+					size_t cnt,
+					loff_t *ppos)
+{
+	char buf[U64STR_SIZE];
+	int csize = min(cnt, sizeof(buf));
+	u64 val = 0;
+	int err = 0;
+
+	memset(buf, '\0', sizeof(buf));
+	if (copy_from_user(buf, ubuf, csize))
+		return -EFAULT;
+
+	buf[U64STR_SIZE-1] = '\0';			/* just in case */
+	err = kstrtoull(buf, 10, &val);
+	if (err)
+		return -EINVAL;
+
+	mutex_lock(&data.lock);
+	if (data.sample_width < val)
+		data.sample_window = val;
+	else {
+		mutex_unlock(&data.lock);
+		return -EINVAL;
+	}
+	mutex_unlock(&data.lock);
+
+	return csize;
+}
+
+/*
+ * Function pointers for the "count" debugfs file operations
+ */
+static const struct file_operations count_fops = {
+	.open		= debug_count_fopen,
+	.read		= debug_count_fread,
+	.write		= debug_count_fwrite,
+	.owner		= THIS_MODULE,
+};
+
+/*
+ * Function pointers for the "enable" debugfs file operations
+ */
+static const struct file_operations enable_fops = {
+	.open		= debug_enable_fopen,
+	.read		= debug_enable_fread,
+	.write		= debug_enable_fwrite,
+	.owner		= THIS_MODULE,
+};
+
+/*
+ * Function pointers for the "max" debugfs file operations
+ */
+static const struct file_operations max_fops = {
+	.open		= debug_max_fopen,
+	.read		= debug_max_fread,
+	.write		= debug_max_fwrite,
+	.owner		= THIS_MODULE,
+};
+
+/*
+ * Function pointers for the "sample" debugfs file operations
+ */
+static const struct file_operations sample_fops = {
+	.open		= debug_sample_fopen,
+	.read		= debug_sample_fread,
+	.release	= debug_sample_release,
+	.owner		= THIS_MODULE,
+};
+
+/*
+ * Function pointers for the "threshold" debugfs file operations
+ */
+static const struct file_operations threshold_fops = {
+	.open		= debug_threshold_fopen,
+	.read		= debug_threshold_fread,
+	.write		= debug_threshold_fwrite,
+	.owner		= THIS_MODULE,
+};
+
+/*
+ * Function pointers for the "width" debugfs file operations
+ */
+static const struct file_operations width_fops = {
+	.open		= debug_width_fopen,
+	.read		= debug_width_fread,
+	.write		= debug_width_fwrite,
+	.owner		= THIS_MODULE,
+};
+
+/*
+ * Function pointers for the "window" debugfs file operations
+ */
+static const struct file_operations window_fops = {
+	.open		= debug_window_fopen,
+	.read		= debug_window_fread,
+	.write		= debug_window_fwrite,
+	.owner		= THIS_MODULE,
+};
+
+/**
+ * init_debugfs - A function to initialize the debugfs interface files
+ *
+ * This function creates entries in debugfs for "hwlat_detector", including
+ * files to read values from the detector, current samples, and the
+ * maximum sample that has been captured since the hardware latency
+ * dectector was started.
+ */
+static int init_debugfs(void)
+{
+	int ret = -ENOMEM;
+
+	debug_dir = debugfs_create_dir(DRVNAME, NULL);
+	if (!debug_dir)
+		goto err_debug_dir;
+
+	debug_sample = debugfs_create_file("sample", 0444,
+					       debug_dir, NULL,
+					       &sample_fops);
+	if (!debug_sample)
+		goto err_sample;
+
+	debug_count = debugfs_create_file("count", 0444,
+					      debug_dir, NULL,
+					      &count_fops);
+	if (!debug_count)
+		goto err_count;
+
+	debug_max = debugfs_create_file("max", 0444,
+					    debug_dir, NULL,
+					    &max_fops);
+	if (!debug_max)
+		goto err_max;
+
+	debug_sample_window = debugfs_create_file("window", 0644,
+						      debug_dir, NULL,
+						      &window_fops);
+	if (!debug_sample_window)
+		goto err_window;
+
+	debug_sample_width = debugfs_create_file("width", 0644,
+						     debug_dir, NULL,
+						     &width_fops);
+	if (!debug_sample_width)
+		goto err_width;
+
+	debug_threshold = debugfs_create_file("threshold", 0644,
+						  debug_dir, NULL,
+						  &threshold_fops);
+	if (!debug_threshold)
+		goto err_threshold;
+
+	debug_enable = debugfs_create_file("enable", 0644,
+					       debug_dir, &enabled,
+					       &enable_fops);
+	if (!debug_enable)
+		goto err_enable;
+
+	else {
+		ret = 0;
+		goto out;
+	}
+
+err_enable:
+	debugfs_remove(debug_threshold);
+err_threshold:
+	debugfs_remove(debug_sample_width);
+err_width:
+	debugfs_remove(debug_sample_window);
+err_window:
+	debugfs_remove(debug_max);
+err_max:
+	debugfs_remove(debug_count);
+err_count:
+	debugfs_remove(debug_sample);
+err_sample:
+	debugfs_remove(debug_dir);
+err_debug_dir:
+out:
+	return ret;
+}
+
+/**
+ * free_debugfs - A function to cleanup the debugfs file interface
+ */
+static void free_debugfs(void)
+{
+	/* could also use a debugfs_remove_recursive */
+	debugfs_remove(debug_enable);
+	debugfs_remove(debug_threshold);
+	debugfs_remove(debug_sample_width);
+	debugfs_remove(debug_sample_window);
+	debugfs_remove(debug_max);
+	debugfs_remove(debug_count);
+	debugfs_remove(debug_sample);
+	debugfs_remove(debug_dir);
+}
+
+/**
+ * detector_init - Standard module initialization code
+ */
+static int detector_init(void)
+{
+	int ret = -ENOMEM;
+
+	pr_info(BANNER "version %s\n", VERSION);
+
+	ret = init_stats();
+	if (ret)
+		goto out;
+
+	ret = init_debugfs();
+	if (ret)
+		goto err_stats;
+
+	if (enabled)
+		ret = start_kthread();
+
+	goto out;
+
+err_stats:
+	ring_buffer_free(ring_buffer);
+out:
+	return ret;
+
+}
+
+/**
+ * detector_exit - Standard module cleanup code
+ */
+static void detector_exit(void)
+{
+	int err;
+
+	if (enabled) {
+		enabled = 0;
+		err = stop_kthread();
+		if (err)
+			pr_err(BANNER "cannot stop kthread\n");
+	}
+
+	free_debugfs();
+	ring_buffer_free(ring_buffer);	/* free up the ring buffer */
+
+}
+
+module_init(detector_init);
+module_exit(detector_exit);
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index acece3299756..58ea04a03fa9 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -1155,15 +1155,12 @@ static irqreturn_t mmci_pio_irq(int irq, void *dev_id)
 	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;
@@ -1203,8 +1200,6 @@ static irqreturn_t mmci_pio_irq(int irq, void *dev_id)
 
 	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.
diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c
index 2839af00f20c..4348b9c850d3 100644
--- a/drivers/net/ethernet/3com/3c59x.c
+++ b/drivers/net/ethernet/3com/3c59x.c
@@ -842,9 +842,9 @@ static void poll_vortex(struct net_device *dev)
 {
 	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
 
@@ -1916,12 +1916,12 @@ static void vortex_tx_timeout(struct net_device *dev)
 			 * 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);
 		}
 	}
 
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index 8b5988e210d5..cf9928ccdd7e 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -2221,11 +2221,7 @@ static netdev_tx_t atl1c_xmit_frame(struct sk_buff *skb,
 	}
 
 	tpd_req = atl1c_cal_tpd_req(skb);
-	if (!spin_trylock_irqsave(&adapter->tx_lock, flags)) {
-		if (netif_msg_pktdata(adapter))
-			dev_info(&adapter->pdev->dev, "tx locked\n");
-		return NETDEV_TX_LOCKED;
-	}
+	spin_lock_irqsave(&adapter->tx_lock, flags);
 
 	if (atl1c_tpd_avail(adapter, type) < tpd_req) {
 		/* no enough descriptor, just stop queue */
diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
index 59a03a193e83..734f7a7ad2c3 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
@@ -1880,8 +1880,7 @@ static netdev_tx_t atl1e_xmit_frame(struct sk_buff *skb,
 		return NETDEV_TX_OK;
 	}
 	tpd_req = atl1e_cal_tdp_req(skb);
-	if (!spin_trylock_irqsave(&adapter->tx_lock, flags))
-		return NETDEV_TX_LOCKED;
+	spin_lock_irqsave(&adapter->tx_lock, flags);
 
 	if (atl1e_tpd_avail(adapter) < tpd_req) {
 		/* no enough descriptor, just stop queue */
diff --git a/drivers/net/ethernet/chelsio/cxgb/sge.c b/drivers/net/ethernet/chelsio/cxgb/sge.c
index 526ea74e82d9..86f467a2c485 100644
--- a/drivers/net/ethernet/chelsio/cxgb/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb/sge.c
@@ -1664,8 +1664,7 @@ static int t1_sge_tx(struct sk_buff *skb, struct adapter *adapter,
 	struct cmdQ *q = &sge->cmdQ[qid];
 	unsigned int credits, pidx, genbit, count, use_sched_skb = 0;
 
-	if (!spin_trylock(&q->lock))
-		return NETDEV_TX_LOCKED;
+	spin_lock(&q->lock);
 
 	reclaim_completed_tx(sge, q);
 
diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c
index 9ba975853ec6..813cfa698160 100644
--- a/drivers/net/ethernet/neterion/s2io.c
+++ b/drivers/net/ethernet/neterion/s2io.c
@@ -4084,12 +4084,7 @@ static netdev_tx_t s2io_xmit(struct sk_buff *skb, struct net_device *dev)
 			[skb->priority & (MAX_TX_FIFOS - 1)];
 	fifo = &mac_control->fifos[queue];
 
-	if (do_spin_lock)
-		spin_lock_irqsave(&fifo->tx_lock, flags);
-	else {
-		if (unlikely(!spin_trylock_irqsave(&fifo->tx_lock, flags)))
-			return NETDEV_TX_LOCKED;
-	}
+	spin_lock_irqsave(&fifo->tx_lock, flags);
 
 	if (sp->config.multiq) {
 		if (__netif_subqueue_stopped(dev, fifo->fifo_no)) {
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
index 3b98b263bad0..ca4add749410 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -2137,10 +2137,8 @@ static int pch_gbe_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 	struct pch_gbe_tx_ring *tx_ring = adapter->tx_ring;
 	unsigned long flags;
 
-	if (!spin_trylock_irqsave(&tx_ring->tx_lock, flags)) {
-		/* Collision - tell upper layer to requeue */
-		return NETDEV_TX_LOCKED;
-	}
+	spin_lock_irqsave(&tx_ring->tx_lock, flags);
+
 	if (unlikely(!PCH_GBE_DESC_UNUSED(tx_ring))) {
 		netif_stop_queue(netdev);
 		spin_unlock_irqrestore(&tx_ring->tx_lock, flags);
diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c
index ef668d300800..d987d571fdd6 100644
--- a/drivers/net/ethernet/realtek/8139too.c
+++ b/drivers/net/ethernet/realtek/8139too.c
@@ -2229,7 +2229,7 @@ static void rtl8139_poll_controller(struct net_device *dev)
 	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);
 }
diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c
index 14c9d1baa85c..e1a5305418a8 100644
--- a/drivers/net/ethernet/tehuti/tehuti.c
+++ b/drivers/net/ethernet/tehuti/tehuti.c
@@ -1629,13 +1629,8 @@ static netdev_tx_t bdx_tx_transmit(struct sk_buff *skb,
 	unsigned long flags;
 
 	ENTER;
-	local_irq_save(flags);
-	if (!spin_trylock(&priv->tx_lock)) {
-		local_irq_restore(flags);
-		DBG("%s[%s]: TX locked, returning NETDEV_TX_LOCKED\n",
-		    BDX_DRV_NAME, ndev->name);
-		return NETDEV_TX_LOCKED;
-	}
+
+	spin_lock_irqsave(&priv->tx_lock, flags);
 
 	/* build tx descriptor */
 	BDX_ASSERT(f->m.wptr >= f->m.memsz);	/* started with valid wptr */
diff --git a/drivers/net/rionet.c b/drivers/net/rionet.c
index e7034c55e796..2e4ee0f912bf 100644
--- a/drivers/net/rionet.c
+++ b/drivers/net/rionet.c
@@ -174,11 +174,7 @@ static int rionet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	unsigned long flags;
 	int add_num = 1;
 
-	local_irq_save(flags);
-	if (!spin_trylock(&rnet->tx_lock)) {
-		local_irq_restore(flags);
-		return NETDEV_TX_LOCKED;
-	}
+	spin_lock_irqsave(&rnet->tx_lock, flags);
 
 	if (is_multicast_ether_addr(eth->h_dest))
 		add_num = nets[rnet->mport->id].nact;
diff --git a/drivers/net/wireless/orinoco/orinoco_usb.c b/drivers/net/wireless/orinoco/orinoco_usb.c
index f2cd513d54b2..6c0f4c9638a2 100644
--- a/drivers/net/wireless/orinoco/orinoco_usb.c
+++ b/drivers/net/wireless/orinoco/orinoco_usb.c
@@ -697,7 +697,7 @@ static void ezusb_req_ctx_wait(struct ezusb_priv *upriv,
 			while (!ctx->done.done && msecs--)
 				udelay(1000);
 		} else {
-			wait_event_interruptible(ctx->done.wait,
+			swait_event_interruptible(ctx->done.wait,
 						 ctx->done.done);
 		}
 		break;
diff --git a/drivers/pci/access.c b/drivers/pci/access.c
index 59ac36fe7c42..7a45a20af78a 100644
--- a/drivers/pci/access.c
+++ b/drivers/pci/access.c
@@ -561,7 +561,7 @@ void pci_cfg_access_unlock(struct pci_dev *dev)
 	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);
diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
index f4424063b860..cbbbebd86c6e 100644
--- a/drivers/scsi/fcoe/fcoe.c
+++ b/drivers/scsi/fcoe/fcoe.c
@@ -1286,7 +1286,7 @@ static void fcoe_percpu_thread_destroy(unsigned int cpu)
 	struct sk_buff *skb;
 #ifdef CONFIG_SMP
 	struct fcoe_percpu_s *p0;
-	unsigned targ_cpu = get_cpu();
+	unsigned targ_cpu = get_cpu_light();
 #endif /* CONFIG_SMP */
 
 	FCOE_DBG("Destroying receive thread for CPU %d\n", cpu);
@@ -1342,7 +1342,7 @@ static void fcoe_percpu_thread_destroy(unsigned int cpu)
 			kfree_skb(skb);
 		spin_unlock_bh(&p->fcoe_rx_list.lock);
 	}
-	put_cpu();
+	put_cpu_light();
 #else
 	/*
 	 * This a non-SMP scenario where the singular Rx thread is
@@ -1566,11 +1566,11 @@ 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;
 }
@@ -1766,11 +1766,11 @@ static inline int fcoe_filter_frames(struct fc_lport *lport,
 		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;
 }
 
@@ -1814,7 +1814,7 @@ static void fcoe_recv_frame(struct sk_buff *skb)
 	 */
 	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 "
@@ -1846,13 +1846,13 @@ static void fcoe_recv_frame(struct sk_buff *skb)
 		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);
 }
 
diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c
index 34a1b1f333b4..d91131210695 100644
--- a/drivers/scsi/fcoe/fcoe_ctlr.c
+++ b/drivers/scsi/fcoe/fcoe_ctlr.c
@@ -831,7 +831,7 @@ static unsigned long fcoe_ctlr_age_fcfs(struct fcoe_ctlr *fip)
 
 	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;
@@ -867,7 +867,7 @@ static unsigned long fcoe_ctlr_age_fcfs(struct fcoe_ctlr *fip)
 				sel_time = fcf->time;
 		}
 	}
-	put_cpu();
+	put_cpu_light();
 
 	list_for_each_entry_safe(fcf, next, &del_list, list) {
 		/* Removes fcf from current list */
diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c
index 30f9ef0c0d4f..6c686bc01a82 100644
--- a/drivers/scsi/libfc/fc_exch.c
+++ b/drivers/scsi/libfc/fc_exch.c
@@ -814,10 +814,10 @@ static struct fc_exch *fc_exch_em_alloc(struct fc_lport *lport,
 	}
 	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) {
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index 9c706d8c1441..d968ffc79c08 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -190,7 +190,7 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc)
 	/* 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 */
@@ -255,7 +255,7 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc)
 
  out:
 	spin_lock(ap->lock);
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 	return ret;
 }
 
diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h
index fee9eb7c8a60..b42d4adc42dc 100644
--- a/drivers/scsi/qla2xxx/qla_inline.h
+++ b/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 *
diff --git a/drivers/thermal/x86_pkg_temp_thermal.c b/drivers/thermal/x86_pkg_temp_thermal.c
index 7fc919f7da4d..e03fa17b8670 100644
--- a/drivers/thermal/x86_pkg_temp_thermal.c
+++ b/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>
 
@@ -352,7 +353,7 @@ static void pkg_temp_thermal_threshold_work_fn(struct work_struct *work)
 	}
 }
 
-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();
@@ -369,7 +370,7 @@ static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val)
 			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);
@@ -378,9 +379,48 @@ static int pkg_temp_thermal_platform_thermal_notify(__u64 msr_val)
 	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;
@@ -584,6 +624,9 @@ static int __init pkg_temp_thermal_init(void)
 	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;
@@ -608,7 +651,7 @@ err_ret:
 	kfree(pkg_work_scheduled);
 	platform_thermal_package_notify = NULL;
 	platform_thermal_package_rate_control = NULL;
-
+	thermal_notify_work_cleanup();
 	return -ENODEV;
 }
 
@@ -633,6 +676,7 @@ static void __exit pkg_temp_thermal_exit(void)
 	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));
diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index 39126460c1f5..af7701ca4d48 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/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>
 /*
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index 56ccbcefdd85..a0b9e854672c 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/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>
 
@@ -2843,9 +2844,9 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s,
 
 	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);
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index 899a77187bde..3ff6363b3751 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -2067,13 +2067,19 @@ pl011_console_write(struct console *co, const char *s, unsigned int count)
 
 	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
@@ -2098,8 +2104,7 @@ pl011_console_write(struct console *co, const char *s, unsigned int count)
 		writew(old_cr, uap->port.membase + UART011_CR);
 
 	if (locked)
-		spin_unlock(&uap->port.lock);
-	local_irq_restore(flags);
+		spin_unlock_irqrestore(&uap->port.lock, flags);
 
 	clk_disable(uap->clk);
 }
diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c
index 24280d9a05e9..9745fb8b7abb 100644
--- a/drivers/tty/serial/omap-serial.c
+++ b/drivers/tty/serial/omap-serial.c
@@ -1257,13 +1257,10 @@ serial_omap_console_write(struct console *co, const char *s,
 
 	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 *co, const char *s,
 	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
diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index edb5305b9d4d..7d5ee8a13ac6 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -1230,7 +1230,7 @@ static int sc16is7xx_probe(struct device *dev,
 
 	/* Setup interrupt */
 	ret = devm_request_irq(dev, irq, sc16is7xx_irq,
-			       IRQF_ONESHOT | flags, dev_name(dev), s);
+			       flags, dev_name(dev), s);
 	if (!ret)
 		return 0;
 
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index f44ce09367bc..5fc9a14721bd 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1735,9 +1735,9 @@ static void __usb_hcd_giveback_urb(struct urb *urb)
 	 * 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);
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 803c503a2e3d..8dd2720aab64 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -1404,7 +1404,7 @@ static void ffs_data_put(struct ffs_data *ffs)
 		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);
 	}
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index e57f48f9528f..7544a54056e4 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -345,7 +345,7 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len)
 	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)) {
@@ -354,7 +354,7 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len)
 				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 {
diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c
index f92f5aff0dd5..f9bba26e3655 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.c
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.c
@@ -17,7 +17,9 @@
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
 #include <linux/list.h>
+#include <linux/mfd/syscon.h>
 #include <linux/platform_device.h>
+#include <linux/regmap.h>
 #include <linux/usb/ch9.h>
 #include <linux/usb/gadget.h>
 #include <linux/usb/atmel_usba_udc.h>
@@ -1888,20 +1890,15 @@ static int atmel_usba_stop(struct usb_gadget *gadget)
 #ifdef CONFIG_OF
 static void at91sam9rl_toggle_bias(struct usba_udc *udc, int is_on)
 {
-	unsigned int uckr = at91_pmc_read(AT91_CKGR_UCKR);
-
-	if (is_on)
-		at91_pmc_write(AT91_CKGR_UCKR, uckr | AT91_PMC_BIASEN);
-	else
-		at91_pmc_write(AT91_CKGR_UCKR, uckr & ~(AT91_PMC_BIASEN));
+	regmap_update_bits(udc->pmc, AT91_CKGR_UCKR, AT91_PMC_BIASEN,
+			   is_on ? AT91_PMC_BIASEN : 0);
 }
 
 static void at91sam9g45_pulse_bias(struct usba_udc *udc)
 {
-	unsigned int uckr = at91_pmc_read(AT91_CKGR_UCKR);
-
-	at91_pmc_write(AT91_CKGR_UCKR, uckr & ~(AT91_PMC_BIASEN));
-	at91_pmc_write(AT91_CKGR_UCKR, uckr | AT91_PMC_BIASEN);
+	regmap_update_bits(udc->pmc, AT91_CKGR_UCKR, AT91_PMC_BIASEN, 0);
+	regmap_update_bits(udc->pmc, AT91_CKGR_UCKR, AT91_PMC_BIASEN,
+			   AT91_PMC_BIASEN);
 }
 
 static const struct usba_udc_errata at91sam9rl_errata = {
@@ -1938,6 +1935,9 @@ static struct usba_ep * atmel_udc_of_init(struct platform_device *pdev,
 		return ERR_PTR(-EINVAL);
 
 	udc->errata = match->data;
+	udc->pmc = syscon_regmap_lookup_by_compatible("atmel,at91sam9g45-pmc");
+	if (udc->errata && IS_ERR(udc->pmc))
+		return ERR_CAST(udc->pmc);
 
 	udc->num_ep = 0;
 
diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.h b/drivers/usb/gadget/udc/atmel_usba_udc.h
index ea448a344767..3e1c9d589dfa 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.h
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.h
@@ -354,6 +354,8 @@ struct usba_udc {
 	struct dentry *debugfs_root;
 	struct dentry *debugfs_regs;
 #endif
+
+	struct regmap *pmc;
 };
 
 static inline struct usba_ep *to_usba_ep(struct usb_ep *ep)
diff --git a/fs/aio.c b/fs/aio.c
index fe4f49212b99..c3194afdc3df 100644
--- a/fs/aio.c
+++ b/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.");
@@ -573,9 +575,9 @@ static int kiocb_cancel(struct aio_kiocb *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);
 
@@ -594,8 +596,8 @@ static void free_ioctx_reqs(struct percpu_ref *ref)
 	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);
 }
 
 /*
@@ -603,9 +605,9 @@ static void free_ioctx_reqs(struct percpu_ref *ref)
  * 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);
@@ -624,6 +626,14 @@ static void free_ioctx_users(struct percpu_ref *ref)
 	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;
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index 502d3892d8a4..05af8d3e6e88 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -34,6 +34,7 @@
 #include <linux/sched.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
+#include <linux/delay.h>
 #include <asm/current.h>
 #include <asm/uaccess.h>
 
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 7a5a598a2d94..d08bcdc30566 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -150,7 +150,7 @@ 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);
diff --git a/fs/buffer.c b/fs/buffer.c
index 4f4cd959da7c..72b27e17b907 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -305,8 +305,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
 	 * 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;
@@ -319,8 +318,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
 		}
 		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
@@ -332,9 +330,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
 	return;
 
 still_busy:
-	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
-	local_irq_restore(flags);
-	return;
+	bh_uptodate_unlock_irqrestore(first, flags);
 }
 
 /*
@@ -362,8 +358,7 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate)
 	}
 
 	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);
@@ -375,15 +370,12 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate)
 		}
 		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);
 
@@ -3325,6 +3317,7 @@ struct buffer_head *alloc_buffer_head(gfp_t gfp_flags)
 	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();
diff --git a/fs/dcache.c b/fs/dcache.c
index 71b6056ad35d..e80471cbfc19 100644
--- a/fs/dcache.c
+++ b/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>
@@ -747,6 +748,8 @@ static inline bool fast_dput(struct dentry *dentry)
  */
 void dput(struct dentry *dentry)
 {
+	struct dentry *parent;
+
 	if (unlikely(!dentry))
 		return;
 
@@ -783,9 +786,18 @@ 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;
 	}
 }
@@ -2394,7 +2406,7 @@ 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;
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 1e009cad8d5c..d0c12504d3b4 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -505,12 +505,12 @@ static int ep_poll_wakeup_proc(void *priv, void *cookie, int call_nests)
  */
 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)
diff --git a/fs/exec.c b/fs/exec.c
index b06623a9347f..e7760b7b692c 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -865,12 +865,14 @@ static int exec_mmap(struct mm_struct *mm)
 		}
 	}
 	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);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 9db5500d63d9..5951c495d124 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -24,7 +24,6 @@
 
 #ifdef CONFIG_F2FS_CHECK_FS
 #define f2fs_bug_on(sbi, condition)	BUG_ON(condition)
-#define f2fs_down_write(x, y)	down_write_nest_lock(x, y)
 #else
 #define f2fs_bug_on(sbi, condition)					\
 	do {								\
@@ -33,7 +32,6 @@
 			set_sbi_flag(sbi, SBI_NEED_FSCK);		\
 		}							\
 	} while (0)
-#define f2fs_down_write(x, y)	down_write(x)
 #endif
 
 /*
@@ -959,7 +957,7 @@ static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi)
 
 static inline void f2fs_lock_all(struct f2fs_sb_info *sbi)
 {
-	f2fs_down_write(&sbi->cp_rwsem, &sbi->cp_mutex);
+	down_write(&sbi->cp_rwsem);
 }
 
 static inline void f2fs_unlock_all(struct f2fs_sb_info *sbi)
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 684996c8a3a4..6e18a06aaabe 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -116,6 +116,8 @@ void __jbd2_log_wait_for_space(journal_t *journal)
 	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);
 
 		/*
diff --git a/fs/namespace.c b/fs/namespace.c
index 5be02a0635be..1f3725bbd04b 100644
--- a/fs/namespace.c
+++ b/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 */
@@ -353,8 +354,11 @@ 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
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index 7521e11db728..f0de4b6b8bf3 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -107,8 +107,7 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
 				"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(struct buffer_head *bh, int uptodate)
 		}
 		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(struct buffer_head *bh, int uptodate)
 		recs = PAGE_CACHE_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(struct buffer_head *bh, int uptodate)
 	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);
 }
 
 /**
diff --git a/fs/timerfd.c b/fs/timerfd.c
index 053818dd6c18..c4bc14fe0085 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -450,7 +450,10 @@ static int do_timerfd_settime(int ufd, int flags,
 				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);
 	}
 
 	/*
diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h
index 323e5daece54..cc5fbd534fd4 100644
--- a/include/acpi/platform/aclinux.h
+++ b/include/acpi/platform/aclinux.h
@@ -127,6 +127,7 @@
 
 #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 */
@@ -145,6 +146,20 @@
 #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
  */
diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index 630dd2372238..850e4d993a88 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -206,6 +206,20 @@ extern void warn_slowpath_null(const char *file, const 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
diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
index 5d8ffa3e6f8c..c1cde3577551 100644
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -7,10 +7,10 @@
 
 static __always_inline int preempt_count(void)
 {
-	return current_thread_info()->preempt_count;
+	return READ_ONCE(current_thread_info()->preempt_count);
 }
 
-static __always_inline int *preempt_count_ptr(void)
+static __always_inline volatile int *preempt_count_ptr(void)
 {
 	return &current_thread_info()->preempt_count;
 }
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index daf17d70aeca..463df8954255 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -212,6 +212,7 @@ static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag)
 
 struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *, const int ctx_index);
 struct blk_mq_hw_ctx *blk_mq_alloc_single_hw_queue(struct blk_mq_tag_set *, unsigned int, int);
+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);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index fe14382f9664..a82143ad6702 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -89,6 +89,7 @@ struct request {
 	struct list_head queuelist;
 	union {
 		struct call_single_data csd;
+		struct work_struct work;
 		unsigned long fifo_time;
 	};
 
@@ -455,7 +456,7 @@ 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;
 
diff --git a/include/linux/bottom_half.h b/include/linux/bottom_half.h
index 8fdcb783197d..d07dbeec7bc1 100644
--- a/include/linux/bottom_half.h
+++ b/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 */
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 89d9aa9e79bf..4a201008b02d 100644
--- a/include/linux/buffer_head.h
+++ b/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.
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 8da263299754..0cc474291e08 100644
--- a/include/linux/cgroup-defs.h
+++ b/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
 
@@ -142,6 +143,7 @@ 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;
 };
 
 /*
diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h
index 1e6932222e11..17f413bbbedf 100644
--- a/include/linux/clk/at91_pmc.h
+++ b/include/linux/clk/at91_pmc.h
@@ -16,18 +16,6 @@
 #ifndef AT91_PMC_H
 #define AT91_PMC_H
 
-#ifndef __ASSEMBLY__
-extern void __iomem *at91_pmc_base;
-
-#define at91_pmc_read(field) \
-	readl_relaxed(at91_pmc_base + field)
-
-#define at91_pmc_write(field, value) \
-	writel_relaxed(value, at91_pmc_base + field)
-#else
-.extern at91_pmc_base
-#endif
-
 #define	AT91_PMC_SCER		0x00			/* System Clock Enable Register */
 #define	AT91_PMC_SCDR		0x04			/* System Clock Disable Register */
 
diff --git a/include/linux/completion.h b/include/linux/completion.h
index 5d5aaae3af43..3bca1590e29f 100644
--- a/include/linux/completion.h
+++ b/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);
 }
 
 /**
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 3ea9aae2387d..5de5f28a5ef3 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -224,6 +224,8 @@ 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)
@@ -241,6 +243,8 @@ 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. */
diff --git a/include/linux/delay.h b/include/linux/delay.h
index a6ecb34cf547..37caab306336 100644
--- a/include/linux/delay.h
+++ b/include/linux/delay.h
@@ -52,4 +52,10 @@ static inline void ssleep(unsigned int seconds)
 	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) */
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 60048c50404e..f2cd67624f18 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -694,6 +694,18 @@ static inline void __ftrace_enabled_restore(int enabled)
 #define CALLER_ADDR5 ((unsigned long)ftrace_return_address(5))
 #define CALLER_ADDR6 ((unsigned long)ftrace_return_address(6))
 
+static inline unsigned long get_lock_parent_ip(void)
+{
+	unsigned long addr = CALLER_ADDR0;
+
+	if (!in_lock_functions(addr))
+		return addr;
+	addr = CALLER_ADDR1;
+	if (!in_lock_functions(addr))
+		return addr;
+	return CALLER_ADDR2;
+}
+
 #ifdef CONFIG_IRQSOFF_TRACER
   extern void time_hardirqs_on(unsigned long a0, unsigned long a1);
   extern void time_hardirqs_off(unsigned long a0, unsigned long a1);
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index bb3f3297062a..a117a33ef72c 100644
--- a/include/linux/highmem.h
+++ b/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 *page)
 
 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 page *page)
 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 *addr)
 
 #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
 }
 
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 2ead22dd74a0..8fbcdfa5dc77 100644
--- a/include/linux/hrtimer.h
+++ b/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(struct hrtimer *timer)
 	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);
 
@@ -436,7 +453,7 @@ static inline int hrtimer_is_queued(struct hrtimer *timer)
  * 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;
 }
diff --git a/include/linux/idr.h b/include/linux/idr.h
index 013fd9bc4cb6..f62be0aec911 100644
--- a/include/linux/idr.h
+++ b/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
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 1c1ff7e4faa4..60fadde71a44 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -148,9 +148,15 @@ 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_seqlock = __SEQLOCK_UNLOCKED(tsk.vtime_seqlock),	\
+	.vtime_seqcount = SEQCNT_ZERO(tsk.vtime_seqcount),	\
 	.vtime_snap = 0,				\
 	.vtime_snap_whence = VTIME_SYS,
 #else
@@ -239,6 +245,7 @@ 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),		\
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index ad16809c8596..655cee096aed 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -61,6 +61,7 @@
  *                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 +75,7 @@
 #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)
 
@@ -186,7 +188,7 @@ extern void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id);
 #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);
@@ -206,6 +208,7 @@ extern void resume_device_irqs(void);
  * @irq:		Interrupt to which notification applies
  * @kref:		Reference count, for internal use
  * @work:		Work item, for internal use
+ * @list:		List item for deferred callbacks
  * @notify:		Function to be called on change.  This will be
  *			called in process context.
  * @release:		Function to be called on release.  This will be
@@ -217,6 +220,7 @@ struct irq_affinity_notify {
 	unsigned int irq;
 	struct kref kref;
 	struct work_struct work;
+	struct list_head list;
 	void (*notify)(struct irq_affinity_notify *, const cpumask_t *mask);
 	void (*release)(struct kref *ref);
 };
@@ -379,9 +383,13 @@ extern int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which,
 				 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
@@ -438,9 +446,10 @@ 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
@@ -449,13 +458,25 @@ static inline void do_softirq_own_stack(void)
 	__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);
 
@@ -477,8 +498,9 @@ static inline struct task_struct *this_cpu_ksoftirqd(void)
      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.
@@ -503,27 +525,36 @@ struct tasklet_struct name = { NULL, 0, ATOMIC_INIT(1), func, data }
 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
@@ -572,12 +603,7 @@ static inline void tasklet_disable(struct tasklet_struct *t)
 	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,
@@ -608,6 +634,12 @@ void tasklet_hrtimer_cancel(struct tasklet_hrtimer *ttimer)
 	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:
  *
diff --git a/include/linux/irq.h b/include/linux/irq.h
index f7cade00c525..dac9e11ba037 100644
--- a/include/linux/irq.h
+++ b/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)
 
diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h
index 47b9ebd4a74f..2543aab05daa 100644
--- a/include/linux/irq_work.h
+++ b/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(void) { return false; }
 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 */
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index a587a33363c7..ad57402a242d 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -61,6 +61,7 @@ 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;
 #ifdef CONFIG_SMP
diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
index 5dd1272d1ab2..9b77034f7c5e 100644
--- a/include/linux/irqflags.h
+++ b/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
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 65407f6c9120..eb5aabe4e18c 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -352,32 +352,56 @@ static inline struct journal_head *bh2jh(struct buffer_head *bh)
 
 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))
diff --git a/include/linux/kdb.h b/include/linux/kdb.h
index a19bcf9e762e..897495386446 100644
--- a/include/linux/kdb.h
+++ b/include/linux/kdb.h
@@ -167,6 +167,7 @@ extern __printf(2, 0) int vkdb_printf(enum kdb_msgsrc src, const char *fmt,
 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 *, kdb_func_t, char *, char *,
 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; }
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 50220cab738c..d68f639f7330 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -188,6 +188,9 @@ 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,
@@ -195,6 +198,7 @@ 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
 
@@ -255,6 +259,7 @@ extern long (*panic_blink)(int state);
 __printf(1, 2)
 void panic(const char *fmt, ...)
 	__noreturn __cold;
+void nmi_panic(struct pt_regs *regs, const char *msg);
 extern void oops_enter(void);
 extern void oops_exit(void);
 void print_oops_end_marker(void);
@@ -448,6 +453,14 @@ extern int sysctl_panic_on_stackoverflow;
 extern bool crash_kexec_post_notifiers;
 
 /*
+ * panic_cpu is used for synchronizing panic() and crash_kexec() execution. It
+ * holds a CPU number which is executing panic() currently. A value of
+ * PANIC_CPU_INVALID means no CPU has entered panic() or crash_kexec().
+ */
+extern atomic_t panic_cpu;
+#define PANIC_CPU_INVALID	-1
+
+/*
  * Only to be used by arch init code. If the user over-wrote the default
  * CONFIG_PANIC_TIMEOUT, honor it.
  */
@@ -475,6 +488,7 @@ extern enum system_states {
 	SYSTEM_HALT,
 	SYSTEM_POWER_OFF,
 	SYSTEM_RESTART,
+	SYSTEM_SUSPEND,
 } system_state;
 
 #define TAINT_PROPRIETARY_MODULE	0
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index c923350ca20a..c690acc6900e 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -25,6 +25,7 @@
 #include <linux/irqflags.h>
 #include <linux/context_tracking.h>
 #include <linux/irqbypass.h>
+#include <linux/swait.h>
 #include <asm/signal.h>
 
 #include <linux/kvm.h>
@@ -243,7 +244,7 @@ struct kvm_vcpu {
 	int fpu_active;
 	int guest_fpu_loaded, guest_xcr0_loaded;
 	unsigned char fpu_counter;
-	wait_queue_head_t wq;
+	struct swait_queue_head wq;
 	struct pid *pid;
 	int sigset_active;
 	sigset_t sigset;
@@ -794,7 +795,7 @@ static inline bool kvm_arch_has_assigned_device(struct kvm *kvm)
 }
 #endif
 
-static inline wait_queue_head_t *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu)
+static inline struct swait_queue_head *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu)
 {
 #ifdef __KVM_HAVE_ARCH_WQP
 	return vcpu->arch.wqp;
diff --git a/include/linux/lglock.h b/include/linux/lglock.h
index c92ebd100d9b..6f035f635d0e 100644
--- a/include/linux/lglock.h
+++ b/include/linux/lglock.h
@@ -34,13 +34,30 @@
 #endif
 
 struct lglock {
+#ifdef CONFIG_PREEMPT_RT_FULL
+	struct rt_mutex __percpu *lock;
+#else
 	arch_spinlock_t __percpu *lock;
+#endif
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lock_class_key lock_key;
 	struct lockdep_map    lock_dep_map;
 #endif
 };
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+# define DEFINE_LGLOCK(name)						\
+	static DEFINE_PER_CPU(struct rt_mutex, name ## _lock)		\
+	= __RT_MUTEX_INITIALIZER( name ## _lock);			\
+	struct lglock name = { .lock = &name ## _lock }
+
+# define DEFINE_STATIC_LGLOCK(name)					\
+	static DEFINE_PER_CPU(struct rt_mutex, name ## _lock)		\
+	= __RT_MUTEX_INITIALIZER( name ## _lock);			\
+	static struct lglock name = { .lock = &name ## _lock }
+
+#else
+
 #define DEFINE_LGLOCK(name)						\
 	static DEFINE_PER_CPU(arch_spinlock_t, name ## _lock)		\
 	= __ARCH_SPIN_LOCK_UNLOCKED;					\
@@ -50,6 +67,7 @@ struct lglock {
 	static DEFINE_PER_CPU(arch_spinlock_t, name ## _lock)		\
 	= __ARCH_SPIN_LOCK_UNLOCKED;					\
 	static struct lglock name = { .lock = &name ## _lock }
+#endif
 
 void lg_lock_init(struct lglock *lg, char *name);
 
@@ -64,6 +82,12 @@ void lg_double_unlock(struct lglock *lg, int cpu1, int cpu2);
 void lg_global_lock(struct lglock *lg);
 void lg_global_unlock(struct lglock *lg);
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+#define lg_global_trylock_relax(name)	lg_global_lock(name)
+#else
+void lg_global_trylock_relax(struct lglock *lg);
+#endif
+
 #else
 /* When !CONFIG_SMP, map lglock to spinlock */
 #define lglock spinlock
diff --git a/include/linux/list_bl.h b/include/linux/list_bl.h
index 8132214e8efd..89ffaa7bd342 100644
--- a/include/linux/list_bl.h
+++ b/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(struct hlist_bl_node *n)
 
 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)
diff --git a/include/linux/locallock.h b/include/linux/locallock.h
new file mode 100644
index 000000000000..e572a3971631
--- /dev/null
+++ b/include/linux/locallock.h
@@ -0,0 +1,276 @@
+#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_unlock_irq(lvar)			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
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index f8d1492a114f..b238ebfbb4d6 100644
--- a/include/linux/mm_types.h
+++ b/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 <asm/page.h>
 #include <asm/mmu.h>
@@ -504,6 +505,9 @@ struct mm_struct {
 	bool tlb_flush_pending;
 #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;
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index 2cb7531e7d7a..b3fdfc820216 100644
--- a/include/linux/mutex.h
+++ b/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_killable(struct mutex *lock);
 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 */
diff --git a/include/linux/mutex_rt.h b/include/linux/mutex_rt.h
new file mode 100644
index 000000000000..c38a44b14da5
--- /dev/null
+++ b/include/linux/mutex_rt.h
@@ -0,0 +1,84 @@
+#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)
+#define mutex_destroy(l)		rt_mutex_destroy(&(l)->lock)
+
+#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
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 9d6025703f73..a7f37ec4a1ee 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2286,11 +2286,20 @@ void netdev_freemem(struct net_device *dev);
 void synchronize_net(void);
 int init_dummy_netdev(struct net_device *dev);
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+static inline int dev_recursion_level(void)
+{
+	return current->xmit_recursion;
+}
+
+#else
+
 DECLARE_PER_CPU(int, xmit_recursion);
 static inline int dev_recursion_level(void)
 {
 	return this_cpu_read(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);
@@ -2601,6 +2610,7 @@ struct softnet_data {
 	unsigned int		dropped;
 	struct sk_buff_head	input_pkt_queue;
 	struct napi_struct	backlog;
+	struct sk_buff_head	tofree_queue;
 
 };
 
diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 04078e8a4803..a61c9609e32f 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/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>
 
 /**
@@ -289,6 +290,8 @@ void xt_free_table_info(struct xt_table_info *info);
  */
 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.
@@ -309,6 +312,9 @@ static inline unsigned int xt_write_recseq_begin(void)
 {
 	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().
@@ -339,6 +345,7 @@ static inline void xt_write_recseq_end(unsigned int addend)
 	/* 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);
 }
 
 /*
diff --git a/include/linux/notifier.h b/include/linux/notifier.h
index d14a4c362465..2e4414a0c1c4 100644
--- a/include/linux/notifier.h
+++ b/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.
  */
 
 typedef	int (*notifier_fn_t)(struct notifier_block *nb,
@@ -88,7 +86,7 @@ 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);
@@ -101,7 +99,13 @@ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh);
 		.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 =			\
@@ -113,6 +117,18 @@ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh);
 	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,
@@ -182,12 +198,12 @@ static inline int notifier_to_errno(int ret)
 
 /*
  *	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 */
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index caebf2a758dc..53a60a51c758 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -24,6 +24,35 @@
 	 PERCPU_MODULE_RESERVE)
 #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)
 
diff --git a/include/linux/pid.h b/include/linux/pid.h
index 23705a53abba..2cc64b779f03 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -2,6 +2,7 @@
 #define _LINUX_PID_H
 
 #include <linux/rcupdate.h>
+#include <linux/atomic.h>
 
 enum pid_type
 {
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 75e4e30677f1..1cfb1cb72354 100644
--- a/include/linux/preempt.h
+++ b/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;
diff --git a/include/linux/printk.h b/include/linux/printk.h
index 9729565c25ff..9cdca696b718 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -117,9 +117,11 @@ int no_printk(const char *fmt, ...)
 #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
 
 typedef __printf(1, 0) int (*printk_func_t)(const char *fmt, va_list args);
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 5d5174b59802..8ddbd6e15a3c 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -277,8 +277,13 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results,
 unsigned int radix_tree_gang_lookup_slot(struct radix_tree_root *root,
 			void ***results, unsigned long *indices,
 			unsigned long first_index, unsigned int max_items);
+#ifndef CONFIG_PREEMPT_RT_FULL
 int radix_tree_preload(gfp_t gfp_mask);
 int radix_tree_maybe_preload(gfp_t gfp_mask);
+#else
+static inline int radix_tree_preload(gfp_t gm) { return 0; }
+static inline int radix_tree_maybe_preload(gfp_t gfp_mask) { return 0; }
+#endif
 void radix_tree_init(void);
 void *radix_tree_tag_set(struct radix_tree_root *root,
 			unsigned long index, unsigned int tag);
@@ -303,7 +308,7 @@ unsigned long radix_tree_locate_item(struct radix_tree_root *root, void *item);
 
 static inline void radix_tree_preload_end(void)
 {
-	preempt_enable();
+	preempt_enable_nort();
 }
 
 /**
diff --git a/include/linux/random.h b/include/linux/random.h
index a75840c1aa71..1a804361670c 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -20,7 +20,7 @@ struct random_ready_callback {
 extern void add_device_randomness(const void *, unsigned int);
 extern void add_input_randomness(unsigned int type, unsigned int code,
 				 unsigned int value);
-extern void add_interrupt_randomness(int irq, int irq_flags);
+extern void add_interrupt_randomness(int irq, int irq_flags, __u64 ip);
 
 extern void get_random_bytes(void *buf, int nbytes);
 extern int add_random_ready_callback(struct random_ready_callback *rdy);
diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h
index a5aa7ae671f4..24ddffd25492 100644
--- a/include/linux/rbtree.h
+++ b/include/linux/rbtree.h
@@ -31,7 +31,6 @@
 
 #include <linux/kernel.h>
 #include <linux/stddef.h>
-#include <linux/rcupdate.h>
 
 struct rb_node {
 	unsigned long  __rb_parent_color;
@@ -86,14 +85,8 @@ static inline void rb_link_node(struct rb_node *node, struct rb_node *parent,
 	*rb_link = node;
 }
 
-static inline void rb_link_node_rcu(struct rb_node *node, struct rb_node *parent,
-				    struct rb_node **rb_link)
-{
-	node->__rb_parent_color = (unsigned long)parent;
-	node->rb_left = node->rb_right = NULL;
-
-	rcu_assign_pointer(*rb_link, node);
-}
+void rb_link_node_rcu(struct rb_node *node, struct rb_node *parent,
+		      struct rb_node **rb_link);
 
 #define rb_entry_safe(ptr, type, member) \
 	({ typeof(ptr) ____ptr = (ptr); \
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index a0189ba67fde..c2f5f955163d 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -169,6 +169,9 @@ 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.
@@ -192,6 +195,7 @@ 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.
@@ -292,6 +296,11 @@ 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 */
 
@@ -317,6 +326,8 @@ 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 */
@@ -489,7 +500,14 @@ extern struct lockdep_map rcu_callback_map;
 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?
@@ -937,10 +955,14 @@ 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
 }
 
 /*
@@ -950,10 +972,14 @@ 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();
 }
 
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 60d15a080d7c..436c9e62bfc6 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -44,7 +44,11 @@ static inline void rcu_virt_note_context_switch(int cpu)
 	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_expedited(void)
 }
 
 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);
@@ -85,12 +93,10 @@ 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);
 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);
@@ -105,6 +111,14 @@ extern int rcu_scheduler_active __read_mostly;
 
 bool rcu_is_watching(void);
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+void rcu_bh_force_quiescent_state(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
+#endif
+
 void rcu_all_qs(void);
 
 #endif /* __LINUX_RCUTREE_H */
diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h
index 1abba5ce2a2f..30211c627511 100644
--- a/include/linux/rtmutex.h
+++ b/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)
@@ -91,6 +106,7 @@ extern void rt_mutex_destroy(struct rt_mutex *lock);
 
 extern void rt_mutex_lock(struct rt_mutex *lock);
 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);
 
diff --git a/include/linux/rwlock_rt.h b/include/linux/rwlock_rt.h
new file mode 100644
index 000000000000..49ed2d45d3be
--- /dev/null
+++ b/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
diff --git a/include/linux/rwlock_types.h b/include/linux/rwlock_types.h
index cc0072e93e36..d0da966ad7a0 100644
--- a/include/linux/rwlock_types.h
+++ b/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
@@ -43,6 +47,7 @@ typedef struct {
 				RW_DEP_MAP_INIT(lockname) }
 #endif
 
-#define DEFINE_RWLOCK(x)	rwlock_t x = __RW_LOCK_UNLOCKED(x)
+#define DEFINE_RWLOCK(name) \
+	rwlock_t name __cacheline_aligned_in_smp = __RW_LOCK_UNLOCKED(name)
 
 #endif /* __LINUX_RWLOCK_TYPES_H */
diff --git a/include/linux/rwlock_types_rt.h b/include/linux/rwlock_types_rt.h
new file mode 100644
index 000000000000..b13832119591
--- /dev/null
+++ b/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 __cacheline_aligned_in_smp = __RW_LOCK_UNLOCKED(name)
+
+#endif
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 8f498cdde280..2b2148431f14 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -18,6 +18,10 @@
 #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
@@ -177,4 +181,6 @@ extern void up_read_non_owner(struct rw_semaphore *sem);
 # define up_read_non_owner(sem)			up_read(sem)
 #endif
 
+#endif /* !PREEMPT_RT_FULL */
+
 #endif /* _LINUX_RWSEM_H */
diff --git a/include/linux/rwsem_rt.h b/include/linux/rwsem_rt.h
new file mode 100644
index 000000000000..f97860b2e2a4
--- /dev/null
+++ b/include/linux/rwsem_rt.h
@@ -0,0 +1,152 @@
+#ifndef _LINUX_RWSEM_RT_H
+#define _LINUX_RWSEM_RT_H
+
+#ifndef _LINUX_RWSEM_H
+#error "Include rwsem.h"
+#endif
+
+/*
+ * RW-semaphores are a spinlock plus a reader-depth count.
+ *
+ * Note that the semantics are different from the usual
+ * Linux rw-sems, in PREEMPT_RT mode we do not allow
+ * multiple readers to hold the lock at once, we only allow
+ * a read-lock owner to read-lock recursively. This is
+ * better for latency, makes the implementation inherently
+ * fair and makes it simpler as well.
+ */
+
+#include <linux/rtmutex.h>
+
+struct rw_semaphore {
+	struct rt_mutex		lock;
+	int			read_depth;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	dep_map;
+#endif
+};
+
+#define __RWSEM_INITIALIZER(name) \
+	{ .lock = __RT_MUTEX_INITIALIZER(name.lock), \
+	  RW_DEP_MAP_INIT(name) }
+
+#define DECLARE_RWSEM(lockname) \
+	struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname)
+
+extern void  __rt_rwsem_init(struct rw_semaphore *rwsem, const char *name,
+				     struct lock_class_key *key);
+
+#define __rt_init_rwsem(sem, name, key)			\
+	do {						\
+		rt_mutex_init(&(sem)->lock);		\
+		__rt_rwsem_init((sem), (name), (key));\
+	} while (0)
+
+#define __init_rwsem(sem, name, key) __rt_init_rwsem(sem, name, key)
+
+# define rt_init_rwsem(sem)				\
+do {							\
+	static struct lock_class_key __key;		\
+							\
+	__rt_init_rwsem((sem), #sem, &__key);		\
+} while (0)
+
+extern void rt_down_write(struct rw_semaphore *rwsem);
+extern void rt_down_read_nested(struct rw_semaphore *rwsem, int subclass);
+extern void rt_down_write_nested(struct rw_semaphore *rwsem, int subclass);
+extern void rt_down_write_nested_lock(struct rw_semaphore *rwsem,
+				      struct lockdep_map *nest);
+extern void rt__down_read(struct rw_semaphore *rwsem);
+extern void rt_down_read(struct rw_semaphore *rwsem);
+extern int  rt_down_write_trylock(struct rw_semaphore *rwsem);
+extern int  rt__down_read_trylock(struct rw_semaphore *rwsem);
+extern int  rt_down_read_trylock(struct rw_semaphore *rwsem);
+extern void __rt_up_read(struct rw_semaphore *rwsem);
+extern void rt_up_read(struct rw_semaphore *rwsem);
+extern void rt_up_write(struct rw_semaphore *rwsem);
+extern void rt_downgrade_write(struct rw_semaphore *rwsem);
+
+#define init_rwsem(sem)		rt_init_rwsem(sem)
+#define rwsem_is_locked(s)	rt_mutex_is_locked(&(s)->lock)
+
+static inline int rwsem_is_contended(struct rw_semaphore *sem)
+{
+	/* rt_mutex_has_waiters() */
+	return !RB_EMPTY_ROOT(&sem->lock.waiters);
+}
+
+static inline void __down_read(struct rw_semaphore *sem)
+{
+	rt__down_read(sem);
+}
+
+static inline void down_read(struct rw_semaphore *sem)
+{
+	rt_down_read(sem);
+}
+
+static inline int __down_read_trylock(struct rw_semaphore *sem)
+{
+	return rt__down_read_trylock(sem);
+}
+
+static inline int down_read_trylock(struct rw_semaphore *sem)
+{
+	return rt_down_read_trylock(sem);
+}
+
+static inline void down_write(struct rw_semaphore *sem)
+{
+	rt_down_write(sem);
+}
+
+static inline int down_write_trylock(struct rw_semaphore *sem)
+{
+	return rt_down_write_trylock(sem);
+}
+
+static inline void __up_read(struct rw_semaphore *sem)
+{
+	__rt_up_read(sem);
+}
+
+static inline void up_read(struct rw_semaphore *sem)
+{
+	rt_up_read(sem);
+}
+
+static inline void up_write(struct rw_semaphore *sem)
+{
+	rt_up_write(sem);
+}
+
+static inline void downgrade_write(struct rw_semaphore *sem)
+{
+	rt_downgrade_write(sem);
+}
+
+static inline void down_read_nested(struct rw_semaphore *sem, int subclass)
+{
+	return rt_down_read_nested(sem, subclass);
+}
+
+static inline void down_write_nested(struct rw_semaphore *sem, int subclass)
+{
+	rt_down_write_nested(sem, subclass);
+}
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+static inline void down_write_nest_lock(struct rw_semaphore *sem,
+		struct rw_semaphore *nest_lock)
+{
+	rt_down_write_nested_lock(sem, &nest_lock->dep_map);
+}
+
+#else
+
+static inline void down_write_nest_lock(struct rw_semaphore *sem,
+		struct rw_semaphore *nest_lock)
+{
+	rt_down_write_nested_lock(sem, NULL);
+}
+#endif
+#endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1c0193baea2a..0570d8e022ec 100644
--- a/include/linux/sched.h
+++ b/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>
@@ -182,8 +183,6 @@ extern void update_cpu_load_nohz(void);
 static inline void update_cpu_load_nohz(void) { }
 #endif
 
-extern unsigned long get_parent_ip(unsigned long addr);
-
 extern void dump_cpu_task(int cpu);
 
 struct seq_file;
@@ -242,10 +241,7 @@ extern char ___assert_task_state[1 - 2*!!(
 				 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 && \
@@ -311,6 +307,11 @@ 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
 
@@ -970,8 +971,18 @@ struct wake_q_head {
 	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);
+			      struct task_struct *task);
+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:
@@ -1379,6 +1390,7 @@ struct tlbflush_unmap_batch {
 
 struct task_struct {
 	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 */
@@ -1415,6 +1427,12 @@ struct task_struct {
 #endif
 
 	unsigned int policy;
+#ifdef CONFIG_PREEMPT_RT_FULL
+	int migrate_disable;
+# ifdef CONFIG_SCHED_DEBUG
+	int migrate_disable_atomic;
+# endif
+#endif
 	int nr_cpus_allowed;
 	cpumask_t cpus_allowed;
 
@@ -1522,11 +1540,14 @@ struct task_struct {
 	cputime_t gtime;
 	struct prev_cputime prev_cputime;
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
-	seqlock_t vtime_seqlock;
+	seqcount_t vtime_seqcount;
 	unsigned long long vtime_snap;
 	enum {
-		VTIME_SLEEPING = 0,
+		/* Task is sleeping or running in a CPU with VTIME inactive */
+		VTIME_INACTIVE = 0,
+		/* Task runs in userspace in a CPU with VTIME active */
 		VTIME_USER,
+		/* Task runs in kernelspace in a CPU with VTIME active */
 		VTIME_SYS,
 	} vtime_snap_whence;
 #endif
@@ -1538,6 +1559,9 @@ 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 *real_cred; /* objective and real subjective task
@@ -1568,10 +1592,15 @@ 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;
@@ -1795,6 +1824,12 @@ struct task_struct {
 	unsigned long trace;
 	/* bitmask and counter of trace recursion */
 	unsigned long trace_recursion;
+#ifdef CONFIG_WAKEUP_LATENCY_HIST
+	u64 preempt_timestamp_hist;
+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
+	long timer_offset;
+#endif
+#endif
 #endif /* CONFIG_TRACING */
 #ifdef CONFIG_MEMCG
 	struct mem_cgroup *memcg_in_oom;
@@ -1811,9 +1846,23 @@ 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;
 /* CPU-specific state of this task */
 	struct thread_struct thread;
@@ -1831,9 +1880,6 @@ extern int arch_task_struct_size __read_mostly;
 # define arch_task_struct_size (sizeof(struct task_struct))
 #endif
 
-/* Future-safe accessor for struct task_struct's cpus_allowed. */
-#define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
-
 #define TNF_MIGRATED	0x01
 #define TNF_NO_GROUP	0x02
 #define TNF_SHARED	0x04
@@ -2023,6 +2069,15 @@ 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)
@@ -2030,6 +2085,7 @@ static inline void put_task_struct(struct task_struct *t)
 	if (atomic_dec_and_test(&t->usage))
 		__put_task_struct(t);
 }
+#endif
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 extern void task_cputime(struct task_struct *t,
@@ -2068,6 +2124,7 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut,
 /*
  * 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 */
@@ -2232,6 +2289,10 @@ extern void do_set_cpus_allowed(struct task_struct *p,
 
 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)
@@ -2244,6 +2305,9 @@ static inline int set_cpus_allowed_ptr(struct task_struct *p,
 		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
@@ -2453,6 +2517,7 @@ extern void xtime_update(unsigned long ticks);
 
 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);
@@ -2576,12 +2641,24 @@ extern struct mm_struct * mm_alloc(void);
 
 /* mmdrop drops the mm and the page tables */
 extern void __mmdrop(struct mm_struct *);
+
 static inline void mmdrop(struct mm_struct * mm)
 {
 	if (unlikely(atomic_dec_and_test(&mm->mm_count)))
 		__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
+
 /* mmput gets rid of the mappings and all user-space */
 extern void mmput(struct mm_struct *);
 /* Grab a reference to a task's mm, if it is not already going away */
@@ -2891,6 +2968,43 @@ static inline int test_tsk_need_resched(struct task_struct *tsk)
 	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);
@@ -2922,6 +3036,51 @@ static inline int signal_pending_state(long state, struct task_struct *p)
 	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
@@ -2943,12 +3102,16 @@ extern int __cond_resched_lock(spinlock_t *lock);
 	__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)
 {
@@ -3110,6 +3273,31 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
 
 #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);
 
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index e0582106ef4f..b14f4d2368aa 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -220,20 +220,30 @@ static inline int read_seqcount_retry(const seqcount_t *s, unsigned start)
 	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
@@ -425,10 +435,32 @@ 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)
 {
@@ -443,36 +475,36 @@ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
 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 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);
 }
 
@@ -481,7 +513,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl)
 	unsigned long flags;
 
 	spin_lock_irqsave(&sl->lock, flags);
-	write_seqcount_begin(&sl->seqcount);
+	__raw_write_seqcount_begin(&sl->seqcount);
 	return flags;
 }
 
@@ -491,7 +523,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl)
 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);
 }
 
diff --git a/include/linux/signal.h b/include/linux/signal.h
index d80259afb9e5..ddd1e6866a54 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -233,6 +233,7 @@ static inline void init_sigpending(struct sigpending *sig)
 }
 
 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)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index d443d9ab0236..2d1c7f9b7fd0 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -203,6 +203,7 @@ struct sk_buff_head {
 
 	__u32		qlen;
 	spinlock_t	lock;
+	raw_spinlock_t	raw_lock;
 };
 
 struct sk_buff;
@@ -1465,6 +1466,12 @@ static inline void skb_queue_head_init(struct sk_buff_head *list)
 	__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)
 {
diff --git a/include/linux/smp.h b/include/linux/smp.h
index c4414074bd88..e6ab36aeaaab 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -185,6 +185,9 @@ 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:
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 47dd0cebd204..02928fa5499d 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -271,7 +271,11 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
 #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(raw_spinlock_t *lock) __releases(lock)
 # 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
  */
@@ -347,6 +355,12 @@ static __always_inline void spin_unlock(spinlock_t *lock)
 	raw_spin_unlock(&lock->rlock);
 }
 
+static __always_inline int spin_unlock_no_deboost(spinlock_t *lock)
+{
+	raw_spin_unlock(&lock->rlock);
+	return 0;
+}
+
 static __always_inline void spin_unlock_bh(spinlock_t *lock)
 {
 	raw_spin_unlock_bh(&lock->rlock);
@@ -416,4 +430,6 @@ extern int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock);
 #define atomic_dec_and_lock(atomic, lock) \
 		__cond_lock(lock, _atomic_dec_and_lock(atomic, lock))
 
+#endif /* !PREEMPT_RT_FULL */
+
 #endif /* __LINUX_SPINLOCK_H */
diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h
index 5344268e6e62..043263f30e81 100644
--- a/include/linux/spinlock_api_smp.h
+++ b/include/linux/spinlock_api_smp.h
@@ -189,6 +189,8 @@ static inline int __raw_spin_trylock_bh(raw_spinlock_t *lock)
 	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 */
diff --git a/include/linux/spinlock_rt.h b/include/linux/spinlock_rt.h
new file mode 100644
index 000000000000..7eb87584e843
--- /dev/null
+++ b/include/linux/spinlock_rt.h
@@ -0,0 +1,165 @@
+#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 int __lockfunc rt_spin_unlock_no_deboost(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);
+extern int __lockfunc __rt_spin_trylock(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_no_deboost(lock)		rt_spin_unlock_no_deboost(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
diff --git a/include/linux/spinlock_types.h b/include/linux/spinlock_types.h
index 73548eb13a5d..10bac715ea96 100644
--- a/include/linux/spinlock_types.h
+++ b/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 */
diff --git a/include/linux/spinlock_types_nort.h b/include/linux/spinlock_types_nort.h
new file mode 100644
index 000000000000..f1dac1fb1d6a
--- /dev/null
+++ b/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
diff --git a/include/linux/spinlock_types_raw.h b/include/linux/spinlock_types_raw.h
new file mode 100644
index 000000000000..edffc4d53fc9
--- /dev/null
+++ b/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
diff --git a/include/linux/spinlock_types_rt.h b/include/linux/spinlock_types_rt.h
new file mode 100644
index 000000000000..9fd431967abc
--- /dev/null
+++ b/include/linux/spinlock_types_rt.h
@@ -0,0 +1,51 @@
+#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)
+
+#define DEFINE_SPINLOCK(name) \
+	spinlock_t name __cacheline_aligned_in_smp = __SPIN_LOCK_UNLOCKED(name)
+
+#endif
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index f5f80c5643ac..ec1a8f01563c 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -84,10 +84,10 @@ int init_srcu_struct(struct srcu_struct *sp);
 
 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),	\
@@ -104,7 +104,7 @@ void process_srcu(struct work_struct *work);
  */
 #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)
 
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 8b6ec7ef0854..9b77d4cc929f 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -194,6 +194,12 @@ 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
diff --git a/include/linux/swait.h b/include/linux/swait.h
new file mode 100644
index 000000000000..83f004a72320
--- /dev/null
+++ b/include/linux/swait.h
@@ -0,0 +1,173 @@
+#ifndef _LINUX_SWAIT_H
+#define _LINUX_SWAIT_H
+
+#include <linux/list.h>
+#include <linux/stddef.h>
+#include <linux/spinlock.h>
+#include <asm/current.h>
+
+/*
+ * Simple wait queues
+ *
+ * While these are very similar to the other/complex wait queues (wait.h) the
+ * most important difference is that the simple waitqueue allows for
+ * deterministic behaviour -- IOW it has strictly bounded IRQ and lock hold
+ * times.
+ *
+ * In order to make this so, we had to drop a fair number of features of the
+ * other waitqueue code; notably:
+ *
+ *  - mixing INTERRUPTIBLE and UNINTERRUPTIBLE sleeps on the same waitqueue;
+ *    all wakeups are TASK_NORMAL in order to avoid O(n) lookups for the right
+ *    sleeper state.
+ *
+ *  - the exclusive mode; because this requires preserving the list order
+ *    and this is hard.
+ *
+ *  - custom wake functions; because you cannot give any guarantees about
+ *    random code.
+ *
+ * As a side effect of this; the data structures are slimmer.
+ *
+ * One would recommend using this wait queue where possible.
+ */
+
+struct task_struct;
+
+struct swait_queue_head {
+	raw_spinlock_t		lock;
+	struct list_head	task_list;
+};
+
+struct swait_queue {
+	struct task_struct	*task;
+	struct list_head	task_list;
+};
+
+#define __SWAITQUEUE_INITIALIZER(name) {				\
+	.task		= current,					\
+	.task_list	= LIST_HEAD_INIT((name).task_list),		\
+}
+
+#define DECLARE_SWAITQUEUE(name)					\
+	struct swait_queue name = __SWAITQUEUE_INITIALIZER(name)
+
+#define __SWAIT_QUEUE_HEAD_INITIALIZER(name) {				\
+	.lock		= __RAW_SPIN_LOCK_UNLOCKED(name.lock),		\
+	.task_list	= LIST_HEAD_INIT((name).task_list),		\
+}
+
+#define DECLARE_SWAIT_QUEUE_HEAD(name)					\
+	struct swait_queue_head name = __SWAIT_QUEUE_HEAD_INITIALIZER(name)
+
+extern void __init_swait_queue_head(struct swait_queue_head *q, const char *name,
+				    struct lock_class_key *key);
+
+#define init_swait_queue_head(q)				\
+	do {							\
+		static struct lock_class_key __key;		\
+		__init_swait_queue_head((q), #q, &__key);	\
+	} while (0)
+
+#ifdef CONFIG_LOCKDEP
+# define __SWAIT_QUEUE_HEAD_INIT_ONSTACK(name)			\
+	({ init_swait_queue_head(&name); name; })
+# define DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(name)			\
+	struct swait_queue_head name = __SWAIT_QUEUE_HEAD_INIT_ONSTACK(name)
+#else
+# define DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(name)			\
+	DECLARE_SWAIT_QUEUE_HEAD(name)
+#endif
+
+static inline int swait_active(struct swait_queue_head *q)
+{
+	return !list_empty(&q->task_list);
+}
+
+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);
+extern long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state);
+
+extern void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait);
+extern void finish_swait(struct swait_queue_head *q, struct swait_queue *wait);
+
+/* as per ___wait_event() but for swait, therefore "exclusive == 0" */
+#define ___swait_event(wq, condition, state, ret, cmd)			\
+({									\
+	struct swait_queue __wait;					\
+	long __ret = ret;						\
+									\
+	INIT_LIST_HEAD(&__wait.task_list);				\
+	for (;;) {							\
+		long __int = prepare_to_swait_event(&wq, &__wait, state);\
+									\
+		if (condition)						\
+			break;						\
+									\
+		if (___wait_is_interruptible(state) && __int) {		\
+			__ret = __int;					\
+			break;						\
+		}							\
+									\
+		cmd;							\
+	}								\
+	finish_swait(&wq, &__wait);					\
+	__ret;								\
+})
+
+#define __swait_event(wq, condition)					\
+	(void)___swait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0,	\
+			    schedule())
+
+#define swait_event(wq, condition)					\
+do {									\
+	if (condition)							\
+		break;							\
+	__swait_event(wq, condition);					\
+} while (0)
+
+#define __swait_event_timeout(wq, condition, timeout)			\
+	___swait_event(wq, ___wait_cond_timeout(condition),		\
+		      TASK_UNINTERRUPTIBLE, timeout,			\
+		      __ret = schedule_timeout(__ret))
+
+#define swait_event_timeout(wq, condition, timeout)			\
+({									\
+	long __ret = timeout;						\
+	if (!___wait_cond_timeout(condition))				\
+		__ret = __swait_event_timeout(wq, condition, timeout);	\
+	__ret;								\
+})
+
+#define __swait_event_interruptible(wq, condition)			\
+	___swait_event(wq, condition, TASK_INTERRUPTIBLE, 0,		\
+		      schedule())
+
+#define swait_event_interruptible(wq, condition)			\
+({									\
+	int __ret = 0;							\
+	if (!(condition))						\
+		__ret = __swait_event_interruptible(wq, condition);	\
+	__ret;								\
+})
+
+#define __swait_event_interruptible_timeout(wq, condition, timeout)	\
+	___swait_event(wq, ___wait_cond_timeout(condition),		\
+		      TASK_INTERRUPTIBLE, timeout,			\
+		      __ret = schedule_timeout(__ret))
+
+#define swait_event_interruptible_timeout(wq, condition, timeout)	\
+({									\
+	long __ret = timeout;						\
+	if (!___wait_cond_timeout(condition))				\
+		__ret = __swait_event_interruptible_timeout(wq,		\
+						condition, timeout);	\
+	__ret;								\
+})
+
+#endif /* _LINUX_SWAIT_H */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index d8ca2eaa3a8b..19e038054914 100644
--- a/include/linux/swap.h
+++ b/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;
@@ -252,7 +253,8 @@ 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)
 {
@@ -298,6 +300,7 @@ extern unsigned long nr_free_pagecache_pages(void);
 
 
 /* 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);
diff --git a/include/linux/swork.h b/include/linux/swork.h
new file mode 100644
index 000000000000..f175fa9a6016
--- /dev/null
+++ b/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 */
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index ff307b548ed3..be9f9dc6a4e1 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -102,7 +102,17 @@ static inline int test_ti_thread_flag(struct thread_info *ti, int flag)
 #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
 
 #if defined TIF_RESTORE_SIGMASK && !defined HAVE_SET_RESTORE_SIGMASK
 /*
diff --git a/include/linux/timer.h b/include/linux/timer.h
index 61aa61dc410c..299d2b78591f 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -225,7 +225,7 @@ extern void add_timer(struct timer_list *timer);
 
 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)
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 925730bc9fc1..a591f414da6f 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -66,6 +66,9 @@ 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						\
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 558129af828a..cf5c472bbc79 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -24,6 +24,7 @@ static __always_inline void pagefault_disabled_dec(void)
  */
 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();
 }
 
 /*
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 4a29c75b146e..0a294e950df8 100644
--- a/include/linux/uprobes.h
+++ b/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;
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 3e5d9075960f..7eaa847cd5a5 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -33,7 +33,9 @@ DECLARE_PER_CPU(struct vm_event_state, vm_event_states);
  */
 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 vm_event_item item)
 
 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)
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 513b36f04dfd..981c8a840f96 100644
--- a/include/linux/wait.h
+++ b/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);
diff --git a/include/net/dst.h b/include/net/dst.h
index c7329dcd90cc..35c3dba16728 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -437,7 +437,7 @@ static inline void dst_confirm(struct dst_entry *dst)
 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;
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 8b683841e574..bf656008f6e7 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -446,7 +446,7 @@ static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb)
 }
 #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;
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index c68926b4899c..dd0751e76065 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -70,6 +70,7 @@ 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;
diff --git a/include/trace/events/hist.h b/include/trace/events/hist.h
new file mode 100644
index 000000000000..f7710de1b1f3
--- /dev/null
+++ b/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>
diff --git a/include/trace/events/latency_hist.h b/include/trace/events/latency_hist.h
new file mode 100644
index 000000000000..d3f2fbd560b1
--- /dev/null
+++ b/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 */
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index fff846b512e6..73614ce1d204 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -134,58 +134,28 @@ DEFINE_EVENT(writeback_dirty_inode_template, writeback_dirty_inode,
 #ifdef CREATE_TRACE_POINTS
 #ifdef CONFIG_CGROUP_WRITEBACK
 
-static inline size_t __trace_wb_cgroup_size(struct bdi_writeback *wb)
+static inline unsigned int __trace_wb_assign_cgroup(struct bdi_writeback *wb)
 {
-	return kernfs_path_len(wb->memcg_css->cgroup->kn) + 1;
+	return wb->memcg_css->cgroup->kn->ino;
 }
 
-static inline void __trace_wb_assign_cgroup(char *buf, struct bdi_writeback *wb)
-{
-	struct cgroup *cgrp = wb->memcg_css->cgroup;
-	char *path;
-
-	path = cgroup_path(cgrp, buf, kernfs_path_len(cgrp->kn) + 1);
-	WARN_ON_ONCE(path != buf);
-}
-
-static inline size_t __trace_wbc_cgroup_size(struct writeback_control *wbc)
-{
-	if (wbc->wb)
-		return __trace_wb_cgroup_size(wbc->wb);
-	else
-		return 2;
-}
-
-static inline void __trace_wbc_assign_cgroup(char *buf,
-					     struct writeback_control *wbc)
+static inline unsigned int __trace_wbc_assign_cgroup(struct writeback_control *wbc)
 {
 	if (wbc->wb)
-		__trace_wb_assign_cgroup(buf, wbc->wb);
+		return __trace_wb_assign_cgroup(wbc->wb);
 	else
-		strcpy(buf, "/");
+		return -1U;
 }
-
 #else	/* CONFIG_CGROUP_WRITEBACK */
 
-static inline size_t __trace_wb_cgroup_size(struct bdi_writeback *wb)
-{
-	return 2;
-}
-
-static inline void __trace_wb_assign_cgroup(char *buf, struct bdi_writeback *wb)
-{
-	strcpy(buf, "/");
-}
-
-static inline size_t __trace_wbc_cgroup_size(struct writeback_control *wbc)
+static inline unsigned int __trace_wb_assign_cgroup(struct bdi_writeback *wb)
 {
-	return 2;
+	return -1U;
 }
 
-static inline void __trace_wbc_assign_cgroup(char *buf,
-					     struct writeback_control *wbc)
+static inline unsigned int __trace_wbc_assign_cgroup(struct writeback_control *wbc)
 {
-	strcpy(buf, "/");
+	return -1U;
 }
 
 #endif	/* CONFIG_CGROUP_WRITEBACK */
@@ -201,7 +171,7 @@ DECLARE_EVENT_CLASS(writeback_write_inode_template,
 		__array(char, name, 32)
 		__field(unsigned long, ino)
 		__field(int, sync_mode)
-		__dynamic_array(char, cgroup, __trace_wbc_cgroup_size(wbc))
+		__field(unsigned int, cgroup_ino)
 	),
 
 	TP_fast_assign(
@@ -209,14 +179,14 @@ DECLARE_EVENT_CLASS(writeback_write_inode_template,
 			dev_name(inode_to_bdi(inode)->dev), 32);
 		__entry->ino		= inode->i_ino;
 		__entry->sync_mode	= wbc->sync_mode;
-		__trace_wbc_assign_cgroup(__get_str(cgroup), wbc);
+		__entry->cgroup_ino	= __trace_wbc_assign_cgroup(wbc);
 	),
 
-	TP_printk("bdi %s: ino=%lu sync_mode=%d cgroup=%s",
+	TP_printk("bdi %s: ino=%lu sync_mode=%d cgroup_ino=%u",
 		__entry->name,
 		__entry->ino,
 		__entry->sync_mode,
-		__get_str(cgroup)
+		__entry->cgroup_ino
 	)
 );
 
@@ -246,7 +216,7 @@ DECLARE_EVENT_CLASS(writeback_work_class,
 		__field(int, range_cyclic)
 		__field(int, for_background)
 		__field(int, reason)
-		__dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb))
+		__field(unsigned int, cgroup_ino)
 	),
 	TP_fast_assign(
 		strncpy(__entry->name,
@@ -258,10 +228,10 @@ DECLARE_EVENT_CLASS(writeback_work_class,
 		__entry->range_cyclic = work->range_cyclic;
 		__entry->for_background	= work->for_background;
 		__entry->reason = work->reason;
-		__trace_wb_assign_cgroup(__get_str(cgroup), wb);
+		__entry->cgroup_ino = __trace_wb_assign_cgroup(wb);
 	),
 	TP_printk("bdi %s: sb_dev %d:%d nr_pages=%ld sync_mode=%d "
-		  "kupdate=%d range_cyclic=%d background=%d reason=%s cgroup=%s",
+		  "kupdate=%d range_cyclic=%d background=%d reason=%s cgroup_ino=%u",
 		  __entry->name,
 		  MAJOR(__entry->sb_dev), MINOR(__entry->sb_dev),
 		  __entry->nr_pages,
@@ -270,7 +240,7 @@ DECLARE_EVENT_CLASS(writeback_work_class,
 		  __entry->range_cyclic,
 		  __entry->for_background,
 		  __print_symbolic(__entry->reason, WB_WORK_REASON),
-		  __get_str(cgroup)
+		  __entry->cgroup_ino
 	)
 );
 #define DEFINE_WRITEBACK_WORK_EVENT(name) \
@@ -300,15 +270,15 @@ DECLARE_EVENT_CLASS(writeback_class,
 	TP_ARGS(wb),
 	TP_STRUCT__entry(
 		__array(char, name, 32)
-		__dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb))
+		__field(unsigned int, cgroup_ino)
 	),
 	TP_fast_assign(
 		strncpy(__entry->name, dev_name(wb->bdi->dev), 32);
-		__trace_wb_assign_cgroup(__get_str(cgroup), wb);
+		__entry->cgroup_ino = __trace_wb_assign_cgroup(wb);
 	),
-	TP_printk("bdi %s: cgroup=%s",
+	TP_printk("bdi %s: cgroup_ino=%u",
 		  __entry->name,
-		  __get_str(cgroup)
+		  __entry->cgroup_ino
 	)
 );
 #define DEFINE_WRITEBACK_EVENT(name) \
@@ -347,7 +317,7 @@ DECLARE_EVENT_CLASS(wbc_class,
 		__field(int, range_cyclic)
 		__field(long, range_start)
 		__field(long, range_end)
-		__dynamic_array(char, cgroup, __trace_wbc_cgroup_size(wbc))
+		__field(unsigned int, cgroup_ino)
 	),
 
 	TP_fast_assign(
@@ -361,12 +331,12 @@ DECLARE_EVENT_CLASS(wbc_class,
 		__entry->range_cyclic	= wbc->range_cyclic;
 		__entry->range_start	= (long)wbc->range_start;
 		__entry->range_end	= (long)wbc->range_end;
-		__trace_wbc_assign_cgroup(__get_str(cgroup), wbc);
+		__entry->cgroup_ino	= __trace_wbc_assign_cgroup(wbc);
 	),
 
 	TP_printk("bdi %s: towrt=%ld skip=%ld mode=%d kupd=%d "
 		"bgrd=%d reclm=%d cyclic=%d "
-		"start=0x%lx end=0x%lx cgroup=%s",
+		"start=0x%lx end=0x%lx cgroup_ino=%u",
 		__entry->name,
 		__entry->nr_to_write,
 		__entry->pages_skipped,
@@ -377,7 +347,7 @@ DECLARE_EVENT_CLASS(wbc_class,
 		__entry->range_cyclic,
 		__entry->range_start,
 		__entry->range_end,
-		__get_str(cgroup)
+		__entry->cgroup_ino
 	)
 )
 
@@ -398,7 +368,7 @@ TRACE_EVENT(writeback_queue_io,
 		__field(long,		age)
 		__field(int,		moved)
 		__field(int,		reason)
-		__dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb))
+		__field(unsigned int,	cgroup_ino)
 	),
 	TP_fast_assign(
 		unsigned long *older_than_this = work->older_than_this;
@@ -408,15 +378,15 @@ TRACE_EVENT(writeback_queue_io,
 				  (jiffies - *older_than_this) * 1000 / HZ : -1;
 		__entry->moved	= moved;
 		__entry->reason	= work->reason;
-		__trace_wb_assign_cgroup(__get_str(cgroup), wb);
+		__entry->cgroup_ino	= __trace_wb_assign_cgroup(wb);
 	),
-	TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s cgroup=%s",
+	TP_printk("bdi %s: older=%lu age=%ld enqueue=%d reason=%s cgroup_ino=%u",
 		__entry->name,
 		__entry->older,	/* older_than_this in jiffies */
 		__entry->age,	/* older_than_this in relative milliseconds */
 		__entry->moved,
 		__print_symbolic(__entry->reason, WB_WORK_REASON),
-		__get_str(cgroup)
+		__entry->cgroup_ino
 	)
 );
 
@@ -484,7 +454,7 @@ TRACE_EVENT(bdi_dirty_ratelimit,
 		__field(unsigned long,	dirty_ratelimit)
 		__field(unsigned long,	task_ratelimit)
 		__field(unsigned long,	balanced_dirty_ratelimit)
-		__dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb))
+		__field(unsigned int,	cgroup_ino)
 	),
 
 	TP_fast_assign(
@@ -496,13 +466,13 @@ TRACE_EVENT(bdi_dirty_ratelimit,
 		__entry->task_ratelimit	= KBps(task_ratelimit);
 		__entry->balanced_dirty_ratelimit =
 					KBps(wb->balanced_dirty_ratelimit);
-		__trace_wb_assign_cgroup(__get_str(cgroup), wb);
+		__entry->cgroup_ino	= __trace_wb_assign_cgroup(wb);
 	),
 
 	TP_printk("bdi %s: "
 		  "write_bw=%lu awrite_bw=%lu dirty_rate=%lu "
 		  "dirty_ratelimit=%lu task_ratelimit=%lu "
-		  "balanced_dirty_ratelimit=%lu cgroup=%s",
+		  "balanced_dirty_ratelimit=%lu cgroup_ino=%u",
 		  __entry->bdi,
 		  __entry->write_bw,		/* write bandwidth */
 		  __entry->avg_write_bw,	/* avg write bandwidth */
@@ -510,7 +480,7 @@ TRACE_EVENT(bdi_dirty_ratelimit,
 		  __entry->dirty_ratelimit,	/* base ratelimit */
 		  __entry->task_ratelimit, /* ratelimit with position control */
 		  __entry->balanced_dirty_ratelimit, /* the balanced ratelimit */
-		  __get_str(cgroup)
+		  __entry->cgroup_ino
 	)
 );
 
@@ -548,7 +518,7 @@ TRACE_EVENT(balance_dirty_pages,
 		__field(	 long,	pause)
 		__field(unsigned long,	period)
 		__field(	 long,	think)
-		__dynamic_array(char, cgroup, __trace_wb_cgroup_size(wb))
+		__field(unsigned int,	cgroup_ino)
 	),
 
 	TP_fast_assign(
@@ -571,7 +541,7 @@ TRACE_EVENT(balance_dirty_pages,
 		__entry->period		= period * 1000 / HZ;
 		__entry->pause		= pause * 1000 / HZ;
 		__entry->paused		= (jiffies - start_time) * 1000 / HZ;
-		__trace_wb_assign_cgroup(__get_str(cgroup), wb);
+		__entry->cgroup_ino	= __trace_wb_assign_cgroup(wb);
 	),
 
 
@@ -580,7 +550,7 @@ TRACE_EVENT(balance_dirty_pages,
 		  "bdi_setpoint=%lu bdi_dirty=%lu "
 		  "dirty_ratelimit=%lu task_ratelimit=%lu "
 		  "dirtied=%u dirtied_pause=%u "
-		  "paused=%lu pause=%ld period=%lu think=%ld cgroup=%s",
+		  "paused=%lu pause=%ld period=%lu think=%ld cgroup_ino=%u",
 		  __entry->bdi,
 		  __entry->limit,
 		  __entry->setpoint,
@@ -595,7 +565,7 @@ TRACE_EVENT(balance_dirty_pages,
 		  __entry->pause,	/* ms */
 		  __entry->period,	/* ms */
 		  __entry->think,	/* ms */
-		  __get_str(cgroup)
+		  __entry->cgroup_ino
 	  )
 );
 
@@ -609,8 +579,7 @@ TRACE_EVENT(writeback_sb_inodes_requeue,
 		__field(unsigned long, ino)
 		__field(unsigned long, state)
 		__field(unsigned long, dirtied_when)
-		__dynamic_array(char, cgroup,
-				__trace_wb_cgroup_size(inode_to_wb(inode)))
+		__field(unsigned int, cgroup_ino)
 	),
 
 	TP_fast_assign(
@@ -619,16 +588,16 @@ TRACE_EVENT(writeback_sb_inodes_requeue,
 		__entry->ino		= inode->i_ino;
 		__entry->state		= inode->i_state;
 		__entry->dirtied_when	= inode->dirtied_when;
-		__trace_wb_assign_cgroup(__get_str(cgroup), inode_to_wb(inode));
+		__entry->cgroup_ino	= __trace_wb_assign_cgroup(inode_to_wb(inode));
 	),
 
-	TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu cgroup=%s",
+	TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu cgroup_ino=%u",
 		  __entry->name,
 		  __entry->ino,
 		  show_inode_state(__entry->state),
 		  __entry->dirtied_when,
 		  (jiffies - __entry->dirtied_when) / HZ,
-		  __get_str(cgroup)
+		  __entry->cgroup_ino
 	)
 );
 
@@ -684,7 +653,7 @@ DECLARE_EVENT_CLASS(writeback_single_inode_template,
 		__field(unsigned long, writeback_index)
 		__field(long, nr_to_write)
 		__field(unsigned long, wrote)
-		__dynamic_array(char, cgroup, __trace_wbc_cgroup_size(wbc))
+		__field(unsigned int, cgroup_ino)
 	),
 
 	TP_fast_assign(
@@ -696,11 +665,11 @@ DECLARE_EVENT_CLASS(writeback_single_inode_template,
 		__entry->writeback_index = inode->i_mapping->writeback_index;
 		__entry->nr_to_write	= nr_to_write;
 		__entry->wrote		= nr_to_write - wbc->nr_to_write;
-		__trace_wbc_assign_cgroup(__get_str(cgroup), wbc);
+		__entry->cgroup_ino	= __trace_wbc_assign_cgroup(wbc);
 	),
 
 	TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu "
-		  "index=%lu to_write=%ld wrote=%lu cgroup=%s",
+		  "index=%lu to_write=%ld wrote=%lu cgroup_ino=%u",
 		  __entry->name,
 		  __entry->ino,
 		  show_inode_state(__entry->state),
@@ -709,7 +678,7 @@ DECLARE_EVENT_CLASS(writeback_single_inode_template,
 		  __entry->writeback_index,
 		  __entry->nr_to_write,
 		  __entry->wrote,
-		  __get_str(cgroup)
+		  __entry->cgroup_ino
 	)
 );
 
diff --git a/init/Kconfig b/init/Kconfig
index 235c7a2c0d20..a7c81c0911da 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -498,7 +498,7 @@ 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,
@@ -614,7 +614,7 @@ 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
@@ -641,7 +641,7 @@ 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.
@@ -1106,6 +1106,7 @@ 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
@@ -1719,6 +1720,7 @@ choice
 
 config SLAB
 	bool "SLAB"
+	depends on !PREEMPT_RT_FULL
 	help
 	  The regular slab allocator that is established and known to work
 	  well in all environments. It organizes cache hot objects in
@@ -1737,6 +1739,7 @@ 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
@@ -1746,7 +1749,7 @@ endchoice
 
 config SLUB_CPU_PARTIAL
 	default y
-	depends on SLUB && SMP