diff --git a/Documentation/hwlat_detector.txt b/Documentation/hwlat_detector.txt
new file mode 100644
index 0000000..cb61516
--- /dev/null
+++ b/Documentation/hwlat_detector.txt
@@ -0,0 +1,64 @@
+Introduction:
+-------------
+
+The module hwlat_detector is a special purpose kernel module that is used to
+detect large system latencies induced by the behavior of certain underlying
+hardware or firmware, independent of Linux itself. The code was developed
+originally to detect SMIs (System Management Interrupts) on x86 systems,
+however there is nothing x86 specific about this patchset. It was
+originally written for use by the "RT" patch since the Real Time
+kernel is highly latency sensitive.
+
+SMIs are usually not serviced by the Linux kernel, which typically does not
+even know that they are occuring. SMIs are instead are set up by BIOS code
+and are serviced by BIOS code, usually for "critical" events such as
+management of thermal sensors and fans. Sometimes though, SMIs are used for
+other tasks and those tasks can spend an inordinate amount of time in the
+handler (sometimes measured in milliseconds). Obviously this is a problem if
+you are trying to keep event service latencies down in the microsecond range.
+
+The hardware latency detector works by hogging all of the cpus for configurable
+amounts of time (by calling stop_machine()), polling the CPU Time Stamp Counter
+for some period, then looking for gaps in the TSC data. Any gap indicates a
+time when the polling was interrupted and since the machine is stopped and
+interrupts turned off the only thing that could do that would be an SMI.
+
+Note that the SMI detector should *NEVER* be used in a production environment.
+It is intended to be run manually to determine if the hardware platform has a
+problem with long system firmware service routines.
+
+Usage:
+------
+
+Loading the module hwlat_detector passing the parameter "enabled=1" (or by
+setting the "enable" entry in "hwlat_detector" debugfs toggled on) is the only
+step required to start the hwlat_detector. It is possible to redefine the
+threshold in microseconds (us) above which latency spikes will be taken
+into account (parameter "threshold=").
+
+Example:
+
+	# modprobe hwlat_detector enabled=1 threshold=100
+
+After the module is loaded, it creates a directory named "hwlat_detector" under
+the debugfs mountpoint, "/debug/hwlat_detector" for this text. It is necessary
+to have debugfs mounted, which might be on /sys/debug on your system.
+
+The /debug/hwlat_detector interface contains the following files:
+
+count			- number of latency spikes observed since last reset
+enable			- a global enable/disable toggle (0/1), resets count
+max			- maximum hardware latency actually observed (usecs)
+sample			- a pipe from which to read current raw sample data
+			  in the format <timestamp> <latency observed usecs>
+			  (can be opened O_NONBLOCK for a single sample)
+threshold		- minimum latency value to be considered (usecs)
+width			- time period to sample with CPUs held (usecs)
+			  must be less than the total window size (enforced)
+window			- total period of sampling, width being inside (usecs)
+
+By default we will set width to 500,000 and window to 1,000,000, meaning that
+we will sample every 1,000,000 usecs (1s) for 500,000 usecs (0.5s). If we
+observe any latencies that exceed the threshold (initially 100 usecs),
+then we write to a global sample ring buffer of 8K samples, which is
+consumed by reading from the "sample" (pipe) debugfs file interface.
diff --git a/Documentation/sysrq.txt b/Documentation/sysrq.txt
index 312e375..9981f30 100644
--- a/Documentation/sysrq.txt
+++ b/Documentation/sysrq.txt
@@ -57,10 +57,17 @@
 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 0000000..6f2aeab
--- /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/MAINTAINERS b/MAINTAINERS
index 8659eba..35c5c22 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3008,6 +3008,15 @@
 S:	Odd Fixes
 F:	drivers/tty/hvc/
 
+HARDWARE LATENCY DETECTOR
+P:	Jon Masters
+M:	jcm@jonmasters.org
+W:	http://www.kernel.org/pub/linux/kernel/people/jcm/hwlat_detector/
+S:	Supported
+L:	linux-kernel@vger.kernel.org
+F:	Documentation/hwlat_detector.txt
+F:	drivers/misc/hwlat_detector.c
+
 HARDWARE MONITORING
 M:	Jean Delvare <khali@linux-fr.org>
 M:	Guenter Roeck <guenter.roeck@ericsson.com>
diff --git a/arch/Kconfig b/arch/Kconfig
index 4b0669c..73fc7cd 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -6,6 +6,7 @@
 	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
diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c
index e576b91..d913e9b 100644
--- a/arch/alpha/mm/fault.c
+++ b/arch/alpha/mm/fault.c
@@ -107,7 +107,7 @@
 
 	/* If we're in an interrupt context, or have no user context,
 	   we must not take the fault.  */
-	if (!mm || in_atomic())
+	if (!mm || pagefault_disabled())
 		goto no_context;
 
 #ifdef CONFIG_ALPHA_LARGE_VMALLOC
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 082bd36..fe8955f 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -29,6 +29,7 @@
 	select HAVE_GENERIC_HARDIRQS
 	select HAVE_SPARSE_IRQ
 	select GENERIC_IRQ_SHOW
+	select IRQ_FORCED_THREADING
 	select CPU_PM if (SUSPEND || CPU_IDLE)
 	help
 	  The ARM series is a line of low-power-consumption RISC chip designs
@@ -1677,7 +1678,7 @@
 
 config HIGHMEM
 	bool "High Memory Support"
-	depends on MMU
+	depends on MMU && !PREEMPT_RT_FULL
 	help
 	  The address space of ARM processors is only 4 Gigabytes large
 	  and it has to accommodate user address space, kernel address
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index aefd459..48fc90c 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -86,6 +86,8 @@
 	int ret = 0;
 	u32 val;
 
+	preempt_disable_rt();
+
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
@@ -100,6 +102,8 @@
 	: "cc", "memory");
 
 	*uval = val;
+
+	preempt_enable_rt();
 	return ret;
 }
 
diff --git a/arch/arm/kernel/early_printk.c b/arch/arm/kernel/early_printk.c
index 85aa2b2..4307653 100644
--- a/arch/arm/kernel/early_printk.c
+++ b/arch/arm/kernel/early_printk.c
@@ -29,28 +29,17 @@
 	early_write(s, n);
 }
 
-static struct console early_console = {
+static struct console early_console_dev = {
 	.name =		"earlycon",
 	.write =	early_console_write,
 	.flags =	CON_PRINTBUFFER | CON_BOOT,
 	.index =	-1,
 };
 
-asmlinkage void early_printk(const char *fmt, ...)
-{
-	char buf[512];
-	int n;
-	va_list ap;
-
-	va_start(ap, fmt);
-	n = vscnprintf(buf, sizeof(buf), fmt, ap);
-	early_write(buf, n);
-	va_end(ap);
-}
-
 static int __init setup_early_printk(char *buf)
 {
-	register_console(&early_console);
+	early_console = &early_console_dev;
+	register_console(&early_console_dev);
 	return 0;
 }
 
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 4a2db48..c00abc9 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -446,7 +446,7 @@
 		}
 
 		err = request_irq(irq, handle_irq,
-				  IRQF_DISABLED | IRQF_NOBALANCING,
+				  IRQF_NOBALANCING | IRQF_NO_THREAD,
 				  "arm-pmu", armpmu);
 		if (err) {
 			pr_err("unable to request IRQ%d for ARM PMU counters\n",
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index d9e3c61..38fc9ad 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -215,9 +215,7 @@
 		}
 		leds_event(led_idle_end);
 		tick_nohz_restart_sched_tick();
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 	}
 }
 
@@ -496,6 +494,31 @@
 }
 
 #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);
+
 /*
  * The vectors page is always readable from user space for the
  * atomic helpers and the signal restart code.  Let's declare a mapping
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 9e617bd..c7001bc 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -672,6 +672,9 @@
 	if (!user_mode(regs))
 		return;
 
+	local_irq_enable();
+	preempt_check_resched();
+
 	/*
 	 * If we were from a system call, check for system call restarting...
 	 */
diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c
index 7dcb352..02c5d2c 100644
--- a/arch/arm/kernel/smp_tlb.c
+++ b/arch/arm/kernel/smp_tlb.c
@@ -13,18 +13,6 @@
 #include <asm/smp_plat.h>
 #include <asm/tlbflush.h>
 
-static void on_each_cpu_mask(void (*func)(void *), void *info, int wait,
-	const struct cpumask *mask)
-{
-	preempt_disable();
-
-	smp_call_function_many(mask, func, info, wait);
-	if (cpumask_test_cpu(smp_processor_id(), mask))
-		func(info);
-
-	preempt_enable();
-}
-
 /**********************************************************************/
 
 /*
@@ -87,7 +75,7 @@
 void flush_tlb_mm(struct mm_struct *mm)
 {
 	if (tlb_ops_need_broadcast())
-		on_each_cpu_mask(ipi_flush_tlb_mm, mm, 1, mm_cpumask(mm));
+		on_each_cpu_mask(mm_cpumask(mm), ipi_flush_tlb_mm, mm, 1);
 	else
 		local_flush_tlb_mm(mm);
 }
@@ -98,7 +86,8 @@
 		struct tlb_args ta;
 		ta.ta_vma = vma;
 		ta.ta_start = uaddr;
-		on_each_cpu_mask(ipi_flush_tlb_page, &ta, 1, mm_cpumask(vma->vm_mm));
+		on_each_cpu_mask(mm_cpumask(vma->vm_mm), ipi_flush_tlb_page,
+					&ta, 1);
 	} else
 		local_flush_tlb_page(vma, uaddr);
 }
@@ -121,7 +110,8 @@
 		ta.ta_vma = vma;
 		ta.ta_start = start;
 		ta.ta_end = end;
-		on_each_cpu_mask(ipi_flush_tlb_range, &ta, 1, mm_cpumask(vma->vm_mm));
+		on_each_cpu_mask(mm_cpumask(vma->vm_mm), ipi_flush_tlb_range,
+					&ta, 1);
 	} else
 		local_flush_tlb_range(vma, start, end);
 }
diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c
index 00df012..bbafc67 100644
--- a/arch/arm/kernel/unwind.c
+++ b/arch/arm/kernel/unwind.c
@@ -87,7 +87,7 @@
 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 */
@@ -195,7 +195,7 @@
 		/* 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) {
@@ -207,7 +207,7 @@
 				break;
 			}
 		}
-		spin_unlock_irqrestore(&unwind_lock, flags);
+		raw_spin_unlock_irqrestore(&unwind_lock, flags);
 	}
 
 	pr_debug("%s: idx = %p\n", __func__, idx);
@@ -469,9 +469,9 @@
 	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;
 }
@@ -483,9 +483,9 @@
 	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/mach-at91/at91rm9200_time.c b/arch/arm/mach-at91/at91rm9200_time.c
index 1dd69c8..0666570 100644
--- a/arch/arm/mach-at91/at91rm9200_time.c
+++ b/arch/arm/mach-at91/at91rm9200_time.c
@@ -114,6 +114,7 @@
 	last_crtr = read_CRTR();
 	switch (mode) {
 	case CLOCK_EVT_MODE_PERIODIC:
+		setup_irq(AT91_ID_SYS, &at91rm9200_timer_irq);
 		/* PIT for periodic irqs; fixed rate of 1/HZ */
 		irqmask = AT91_ST_PITS;
 		at91_sys_write(AT91_ST_PIMR, LATCH);
@@ -127,6 +128,7 @@
 		break;
 	case CLOCK_EVT_MODE_SHUTDOWN:
 	case CLOCK_EVT_MODE_UNUSED:
+		remove_irq(AT91_ID_SYS, &at91rm9200_timer_irq);
 	case CLOCK_EVT_MODE_RESUME:
 		irqmask = 0;
 		break;
diff --git a/arch/arm/mach-at91/at91sam926x_time.c b/arch/arm/mach-at91/at91sam926x_time.c
index 4ba8549..97d1e14 100644
--- a/arch/arm/mach-at91/at91sam926x_time.c
+++ b/arch/arm/mach-at91/at91sam926x_time.c
@@ -54,7 +54,7 @@
 	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-
+static struct irqaction at91sam926x_pit_irq;
 /*
  * Clockevent device:  interrupts every 1/HZ (== pit_cycles * MCK/16)
  */
@@ -63,6 +63,9 @@
 {
 	switch (mode) {
 	case CLOCK_EVT_MODE_PERIODIC:
+		/* Set up irq handler */
+		setup_irq(AT91_ID_SYS, &at91sam926x_pit_irq);
+
 		/* update clocksource counter */
 		pit_cnt += pit_cycle * PIT_PICNT(at91_sys_read(AT91_PIT_PIVR));
 		at91_sys_write(AT91_PIT_MR, (pit_cycle - 1) | AT91_PIT_PITEN
@@ -75,6 +78,7 @@
 	case CLOCK_EVT_MODE_UNUSED:
 		/* disable irq, leaving the clocksource active */
 		at91_sys_write(AT91_PIT_MR, (pit_cycle - 1) | AT91_PIT_PITEN);
+		remove_irq(AT91_ID_SYS, &at91sam926x_pit_irq);
 		break;
 	case CLOCK_EVT_MODE_RESUME:
 		break;
diff --git a/arch/arm/mach-exynos/platsmp.c b/arch/arm/mach-exynos/platsmp.c
index 69ffb2f..fe321b0 100644
--- a/arch/arm/mach-exynos/platsmp.c
+++ b/arch/arm/mach-exynos/platsmp.c
@@ -63,7 +63,7 @@
 	return (void __iomem *)(S5P_VA_SCU);
 }
 
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
 
 static void __cpuinit exynos4_gic_secondary_init(void)
 {
@@ -108,8 +108,8 @@
 	/*
 	 * Synchronise with the boot thread.
 	 */
-	spin_lock(&boot_lock);
-	spin_unlock(&boot_lock);
+	raw_spin_lock(&boot_lock);
+	raw_spin_unlock(&boot_lock);
 }
 
 int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
@@ -120,7 +120,7 @@
 	 * 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
@@ -149,7 +149,7 @@
 
 		if (timeout == 0) {
 			printk(KERN_ERR "cpu1 power enable failed");
-			spin_unlock(&boot_lock);
+			raw_spin_unlock(&boot_lock);
 			return -ETIMEDOUT;
 		}
 	}
@@ -177,7 +177,7 @@
 	 * 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-msm/platsmp.c b/arch/arm/mach-msm/platsmp.c
index fdec58a..cad6b81 100644
--- a/arch/arm/mach-msm/platsmp.c
+++ b/arch/arm/mach-msm/platsmp.c
@@ -39,7 +39,7 @@
  */
 volatile int pen_release = -1;
 
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
 
 static inline int get_core_count(void)
 {
@@ -69,8 +69,8 @@
 	/*
 	 * Synchronise with the boot thread.
 	 */
-	spin_lock(&boot_lock);
-	spin_unlock(&boot_lock);
+	raw_spin_lock(&boot_lock);
+	raw_spin_unlock(&boot_lock);
 }
 
 static __cpuinit void prepare_cold_cpu(unsigned int cpu)
@@ -107,7 +107,7 @@
 	 * 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
@@ -141,7 +141,7 @@
 	 * 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-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c
index 4412ddb..490de9c 100644
--- a/arch/arm/mach-omap2/omap-smp.c
+++ b/arch/arm/mach-omap2/omap-smp.c
@@ -29,7 +29,7 @@
 /* SCU base address */
 static void __iomem *scu_base;
 
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
 
 void __cpuinit platform_secondary_init(unsigned int cpu)
 {
@@ -43,8 +43,8 @@
 	/*
 	 * Synchronise with the boot thread.
 	 */
-	spin_lock(&boot_lock);
-	spin_unlock(&boot_lock);
+	raw_spin_lock(&boot_lock);
+	raw_spin_unlock(&boot_lock);
 }
 
 int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
@@ -53,7 +53,7 @@
 	 * 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.
@@ -70,7 +70,7 @@
 	 * 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-tegra/platsmp.c b/arch/arm/mach-tegra/platsmp.c
index 7d2b5d0..571f61a 100644
--- a/arch/arm/mach-tegra/platsmp.c
+++ b/arch/arm/mach-tegra/platsmp.c
@@ -28,7 +28,7 @@
 
 extern void tegra_secondary_startup(void);
 
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
 static void __iomem *scu_base = IO_ADDRESS(TEGRA_ARM_PERIF_BASE);
 
 #define EVP_CPU_RESET_VECTOR \
@@ -50,8 +50,8 @@
 	/*
 	 * Synchronise with the boot thread.
 	 */
-	spin_lock(&boot_lock);
-	spin_unlock(&boot_lock);
+	raw_spin_lock(&boot_lock);
+	raw_spin_unlock(&boot_lock);
 }
 
 int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
@@ -65,7 +65,7 @@
 	 * set synchronisation state between this boot processor
 	 * and the secondary one
 	 */
-	spin_lock(&boot_lock);
+	raw_spin_lock(&boot_lock);
 
 
 	/* set the reset vector to point to the secondary_startup routine */
@@ -101,7 +101,7 @@
 	 * 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-ux500/platsmp.c b/arch/arm/mach-ux500/platsmp.c
index a19e398..9e92c6c 100644
--- a/arch/arm/mach-ux500/platsmp.c
+++ b/arch/arm/mach-ux500/platsmp.c
@@ -57,7 +57,7 @@
 	return NULL;
 }
 
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
 
 void __cpuinit platform_secondary_init(unsigned int cpu)
 {
@@ -77,8 +77,8 @@
 	/*
 	 * Synchronise with the boot thread.
 	 */
-	spin_lock(&boot_lock);
-	spin_unlock(&boot_lock);
+	raw_spin_lock(&boot_lock);
+	raw_spin_unlock(&boot_lock);
 }
 
 int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
@@ -89,7 +89,7 @@
 	 * 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
@@ -110,7 +110,7 @@
 	 * 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 4b0bc37..61af818 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -296,7 +296,7 @@
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (!mm || pagefault_disabled())
 		goto no_context;
 
 	/*
@@ -416,6 +416,9 @@
 	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;
 
@@ -478,6 +481,9 @@
 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/plat-versatile/platsmp.c b/arch/arm/plat-versatile/platsmp.c
index 92f18d3..287bbb5 100644
--- a/arch/arm/plat-versatile/platsmp.c
+++ b/arch/arm/plat-versatile/platsmp.c
@@ -37,7 +37,7 @@
 	outer_clean_range(__pa(&pen_release), __pa(&pen_release + 1));
 }
 
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
 
 void __cpuinit platform_secondary_init(unsigned int cpu)
 {
@@ -57,8 +57,8 @@
 	/*
 	 * Synchronise with the boot thread.
 	 */
-	spin_lock(&boot_lock);
-	spin_unlock(&boot_lock);
+	raw_spin_lock(&boot_lock);
+	raw_spin_unlock(&boot_lock);
 }
 
 int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
@@ -69,7 +69,7 @@
 	 * 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
@@ -99,7 +99,7 @@
 	 * 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/avr32/kernel/process.c b/arch/avr32/kernel/process.c
index ef5a2a0..c8724c9 100644
--- a/arch/avr32/kernel/process.c
+++ b/arch/avr32/kernel/process.c
@@ -38,9 +38,7 @@
 		while (!need_resched())
 			cpu_idle_sleep();
 		tick_nohz_restart_sched_tick();
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 	}
 }
 
diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c
index 632b649..fe16234 100644
--- a/arch/avr32/mm/fault.c
+++ b/arch/avr32/mm/fault.c
@@ -81,7 +81,7 @@
 	 * If we're in an interrupt or have no user context, we must
 	 * not take the fault...
 	 */
-	if (in_atomic() || !mm || regs->sr & SYSREG_BIT(GM))
+	if (!mm || regs->sr & SYSREG_BIT(GM) || pagefault_disabled())
 		goto no_context;
 
 	local_irq_enable();
diff --git a/arch/blackfin/kernel/early_printk.c b/arch/blackfin/kernel/early_printk.c
index 84ed837..61fbd2d 100644
--- a/arch/blackfin/kernel/early_printk.c
+++ b/arch/blackfin/kernel/early_printk.c
@@ -25,8 +25,6 @@
 extern struct console *bfin_jc_early_init(void);
 #endif
 
-static struct console *early_console;
-
 /* Default console */
 #define DEFAULT_PORT 0
 #define DEFAULT_CFLAG CS8|B57600
diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c
index 6a80a9e..11acc10 100644
--- a/arch/blackfin/kernel/process.c
+++ b/arch/blackfin/kernel/process.c
@@ -92,9 +92,7 @@
 		while (!need_resched())
 			idle();
 		tick_nohz_restart_sched_tick();
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 	}
 }
 
diff --git a/arch/cris/kernel/process.c b/arch/cris/kernel/process.c
index aa585e4..d8f50ff 100644
--- a/arch/cris/kernel/process.c
+++ b/arch/cris/kernel/process.c
@@ -115,9 +115,7 @@
 				idle = default_idle;
 			idle();
 		}
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 	}
 }
 
diff --git a/arch/cris/mm/fault.c b/arch/cris/mm/fault.c
index 280c8ea..35aa283 100644
--- a/arch/cris/mm/fault.c
+++ b/arch/cris/mm/fault.c
@@ -111,7 +111,7 @@
 	 * user context, we must not take the fault.
 	 */
 
-	if (in_atomic() || !mm)
+	if (!mm || pagefault_disabled())
 		goto no_context;
 
 	down_read(&mm->mmap_sem);
diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c
index 3901df1..29cc497 100644
--- a/arch/frv/kernel/process.c
+++ b/arch/frv/kernel/process.c
@@ -92,9 +92,7 @@
 				idle();
 		}
 
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 	}
 }
 
diff --git a/arch/frv/mm/fault.c b/arch/frv/mm/fault.c
index 46a3c18..176093c 100644
--- a/arch/frv/mm/fault.c
+++ b/arch/frv/mm/fault.c
@@ -79,7 +79,7 @@
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (!mm || pagefault_disabled())
 		goto no_context;
 
 	down_read(&mm->mmap_sem);
diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c
index 933bd38..1a173b3 100644
--- a/arch/h8300/kernel/process.c
+++ b/arch/h8300/kernel/process.c
@@ -81,9 +81,7 @@
 	while (1) {
 		while (!need_resched())
 			idle();
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 	}
 }
 
diff --git a/arch/ia64/kernel/asm-offsets.c b/arch/ia64/kernel/asm-offsets.c
index af56501..106aeb6 100644
--- a/arch/ia64/kernel/asm-offsets.c
+++ b/arch/ia64/kernel/asm-offsets.c
@@ -269,8 +269,8 @@
 	BLANK();
 
 	/* used by fsys_gettimeofday in arch/ia64/kernel/fsys.S */
-	DEFINE(IA64_GTOD_LOCK_OFFSET,
-		offsetof (struct fsyscall_gtod_data_t, lock));
+	DEFINE(IA64_GTOD_SEQ_OFFSET,
+		offsetof (struct fsyscall_gtod_data_t, seq);
 	DEFINE(IA64_GTOD_WALL_TIME_OFFSET,
 		offsetof (struct fsyscall_gtod_data_t, wall_time));
 	DEFINE(IA64_GTOD_MONO_TIME_OFFSET,
diff --git a/arch/ia64/kernel/fsys.S b/arch/ia64/kernel/fsys.S
index 331d42b..fa77de7 100644
--- a/arch/ia64/kernel/fsys.S
+++ b/arch/ia64/kernel/fsys.S
@@ -174,7 +174,7 @@
 	FSYS_RETURN
 END(fsys_set_tid_address)
 
-#if IA64_GTOD_LOCK_OFFSET !=0
+#if IA64_GTOD_SEQ_OFFSET !=0
 #error fsys_gettimeofday incompatible with changes to struct fsyscall_gtod_data_t
 #endif
 #if IA64_ITC_JITTER_OFFSET !=0
diff --git a/arch/ia64/kernel/fsyscall_gtod_data.h b/arch/ia64/kernel/fsyscall_gtod_data.h
index 57d2ee6..146b15b 100644
--- a/arch/ia64/kernel/fsyscall_gtod_data.h
+++ b/arch/ia64/kernel/fsyscall_gtod_data.h
@@ -6,7 +6,7 @@
  */
 
 struct fsyscall_gtod_data_t {
-	seqlock_t	lock;
+	seqcount_t	seq;
 	struct timespec	wall_time;
 	struct timespec monotonic_time;
 	cycle_t		clk_mask;
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index 6d33c5c..9dc52b6 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -330,9 +330,7 @@
 			normal_xtp();
 #endif
 		}
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 		check_pgt_cache();
 		if (cpu_is_offline(cpu))
 			play_dead();
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index 43920de..8e991a0 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -35,9 +35,7 @@
 
 static cycle_t itc_get_cycles(struct clocksource *cs);
 
-struct fsyscall_gtod_data_t fsyscall_gtod_data = {
-	.lock = __SEQLOCK_UNLOCKED(fsyscall_gtod_data.lock),
-};
+struct fsyscall_gtod_data_t fsyscall_gtod_data;
 
 struct itc_jitter_data_t itc_jitter_data;
 
@@ -460,9 +458,7 @@
 void update_vsyscall(struct timespec *wall, struct timespec *wtm,
 			struct clocksource *c, u32 mult)
 {
-        unsigned long flags;
-
-        write_seqlock_irqsave(&fsyscall_gtod_data.lock, flags);
+	write_seqcount_begin(&fsyscall_gtod_data.seq);
 
         /* copy fsyscall clock data */
         fsyscall_gtod_data.clk_mask = c->mask;
@@ -485,6 +481,6 @@
 		fsyscall_gtod_data.monotonic_time.tv_sec++;
 	}
 
-        write_sequnlock_irqrestore(&fsyscall_gtod_data.lock, flags);
+	write_seqcount_end(&fsyscall_gtod_data.seq);
 }
 
diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c
index 1e362cd..d643140 100644
--- a/arch/ia64/mm/fault.c
+++ b/arch/ia64/mm/fault.c
@@ -89,7 +89,7 @@
 	/*
 	 * If we're in an interrupt or have no user context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (!mm || pagefault_disabled())
 		goto no_context;
 
 #ifdef CONFIG_VIRTUAL_MEM_MAP
diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c
index 422bea9..3a4a32b 100644
--- a/arch/m32r/kernel/process.c
+++ b/arch/m32r/kernel/process.c
@@ -90,9 +90,7 @@
 
 			idle();
 		}
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 	}
 }
 
diff --git a/arch/m32r/mm/fault.c b/arch/m32r/mm/fault.c
index beda9cc..af29c04 100644
--- a/arch/m32r/mm/fault.c
+++ b/arch/m32r/mm/fault.c
@@ -115,7 +115,7 @@
 	 * If we're in an interrupt or have no user context or are running in an
 	 * atomic region then we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (!mm || pagefault_disabled())
 		goto bad_area_nosemaphore;
 
 	/* When running in the kernel we expect faults to occur only to
diff --git a/arch/m68k/kernel/process_mm.c b/arch/m68k/kernel/process_mm.c
index aa4ffb8..c413aa0 100644
--- a/arch/m68k/kernel/process_mm.c
+++ b/arch/m68k/kernel/process_mm.c
@@ -94,9 +94,7 @@
 	while (1) {
 		while (!need_resched())
 			idle();
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 	}
 }
 
diff --git a/arch/m68k/kernel/process_no.c b/arch/m68k/kernel/process_no.c
index 5e1078c..f7fe6c3 100644
--- a/arch/m68k/kernel/process_no.c
+++ b/arch/m68k/kernel/process_no.c
@@ -73,9 +73,7 @@
 	/* endless idle loop with no priority at all */
 	while (1) {
 		idle();
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 	}
 }
 
diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c
index d605b93..ecefbdb 100644
--- a/arch/m68k/mm/fault.c
+++ b/arch/m68k/mm/fault.c
@@ -85,7 +85,7 @@
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (!mm || pagefault_disabled())
 		goto no_context;
 
 	down_read(&mm->mmap_sem);
diff --git a/arch/microblaze/kernel/early_printk.c b/arch/microblaze/kernel/early_printk.c
index d26d92d..0420624 100644
--- a/arch/microblaze/kernel/early_printk.c
+++ b/arch/microblaze/kernel/early_printk.c
@@ -21,7 +21,6 @@
 #include <asm/setup.h>
 #include <asm/prom.h>
 
-static u32 early_console_initialized;
 static u32 base_addr;
 
 #ifdef CONFIG_SERIAL_UARTLITE_CONSOLE
@@ -109,27 +108,11 @@
 };
 #endif /* CONFIG_SERIAL_8250_CONSOLE */
 
-static struct console *early_console;
-
-void early_printk(const char *fmt, ...)
-{
-	char buf[512];
-	int n;
-	va_list ap;
-
-	if (early_console_initialized) {
-		va_start(ap, fmt);
-		n = vscnprintf(buf, 512, fmt, ap);
-		early_console->write(early_console, buf, n);
-		va_end(ap);
-	}
-}
-
 int __init setup_early_printk(char *opt)
 {
 	int version = 0;
 
-	if (early_console_initialized)
+	if (early_console)
 		return 1;
 
 	base_addr = of_early_console(&version);
@@ -159,7 +142,6 @@
 		}
 
 		register_console(early_console);
-		early_console_initialized = 1;
 		return 0;
 	}
 	return 1;
@@ -169,7 +151,7 @@
  * only for early console because of performance degression */
 void __init remap_early_printk(void)
 {
-	if (!early_console_initialized || !early_console)
+	if (!early_console)
 		return;
 	printk(KERN_INFO "early_printk_console remaping from 0x%x to ",
 								base_addr);
@@ -179,9 +161,9 @@
 
 void __init disable_early_printk(void)
 {
-	if (!early_console_initialized || !early_console)
+	if (!early_console)
 		return;
 	printk(KERN_WARNING "disabling early console\n");
 	unregister_console(early_console);
-	early_console_initialized = 0;
+	early_console = NULL;
 }
diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c
index 95cc295..d3b2b42 100644
--- a/arch/microblaze/kernel/process.c
+++ b/arch/microblaze/kernel/process.c
@@ -108,9 +108,7 @@
 			idle();
 		tick_nohz_restart_sched_tick();
 
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 		check_pgt_cache();
 	}
 }
diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c
index 31bb381..35bf03d 100644
--- a/arch/microblaze/mm/fault.c
+++ b/arch/microblaze/mm/fault.c
@@ -107,7 +107,7 @@
 	if ((error_code & 0x13) == 0x13 || (error_code & 0x11) == 0x11)
 		is_write = 0;
 
-	if (unlikely(in_atomic() || !mm)) {
+	if (unlikely(!mm || pagefault_disabled())) {
 		if (kernel_mode(regs))
 			goto bad_area_nosemaphore;
 
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index d46f1da..9f02e8b 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2040,7 +2040,7 @@
 #
 config HIGHMEM
 	bool "High Memory Support"
-	depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM
+	depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !PREEMPT_RT_FULL
 
 config CPU_SUPPORTS_HIGHMEM
 	bool
diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c
index efcfff4..86fce15 100644
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@@ -257,8 +257,6 @@
 
 extern void fixup_irqs(void);
 
-static DEFINE_SPINLOCK(smp_reserve_lock);
-
 static int octeon_cpu_disable(void)
 {
 	unsigned int cpu = smp_processor_id();
@@ -266,8 +264,6 @@
 	if (cpu == 0)
 		return -EBUSY;
 
-	spin_lock(&smp_reserve_lock);
-
 	cpu_clear(cpu, cpu_online_map);
 	cpu_clear(cpu, cpu_callin_map);
 	local_irq_disable();
@@ -277,8 +273,6 @@
 	flush_cache_all();
 	local_flush_tlb_all();
 
-	spin_unlock(&smp_reserve_lock);
-
 	return 0;
 }
 
diff --git a/arch/mips/kernel/early_printk.c b/arch/mips/kernel/early_printk.c
index 9ae813e..973c995 100644
--- a/arch/mips/kernel/early_printk.c
+++ b/arch/mips/kernel/early_printk.c
@@ -25,20 +25,18 @@
 	}
 }
 
-static struct console early_console __initdata = {
+static struct console early_console_prom = {
 	.name	= "early",
 	.write	= early_console_write,
 	.flags	= CON_PRINTBUFFER | CON_BOOT,
 	.index	= -1
 };
 
-static int early_console_initialized __initdata;
-
 void __init setup_early_printk(void)
 {
-	if (early_console_initialized)
+	if (early_console)
 		return;
-	early_console_initialized = 1;
+	early_console = &early_console_prom;
 
-	register_console(&early_console);
+	register_console(&early_console_prom);
 }
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index bf128d7..b476ace 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -76,9 +76,7 @@
 			play_dead();
 #endif
 		tick_nohz_restart_sched_tick();
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 	}
 }
 
diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c
index f852400..1c8f34c 100644
--- a/arch/mips/kernel/signal.c
+++ b/arch/mips/kernel/signal.c
@@ -604,6 +604,9 @@
 	if (!user_mode(regs))
 		return;
 
+	local_irq_enable();
+	preempt_check_resched();
+
 	if (test_thread_flag(TIF_RESTORE_SIGMASK))
 		oldset = &current->saved_sigmask;
 	else
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index b8314cfe..42f77e9 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -88,7 +88,7 @@
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (!mm || pagefault_disabled())
 		goto bad_area_nosemaphore;
 
 	down_read(&mm->mmap_sem);
diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c
index 28eec31..cac401d 100644
--- a/arch/mn10300/kernel/process.c
+++ b/arch/mn10300/kernel/process.c
@@ -123,9 +123,7 @@
 			idle();
 		}
 
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 	}
 }
 
diff --git a/arch/mn10300/mm/fault.c b/arch/mn10300/mm/fault.c
index fe2ceb7..f8bdd57 100644
--- a/arch/mn10300/mm/fault.c
+++ b/arch/mn10300/mm/fault.c
@@ -168,7 +168,7 @@
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (!mm || pagefault_disabled())
 		goto no_context;
 
 	down_read(&mm->mmap_sem);
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index 4b4b918..f6eb367 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -71,9 +71,7 @@
 	while (1) {
 		while (!need_resched())
 			barrier();
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 		check_pgt_cache();
 	}
 }
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index a9b765a..34a5c37 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -176,7 +176,7 @@
 	unsigned long acc_type;
 	int fault;
 
-	if (in_atomic() || !mm)
+	if (!mm || pagefault_disabled())
 		goto no_context;
 
 	down_read(&mm->mmap_sem);
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index bec952d..dd2ab05 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -69,10 +69,11 @@
 
 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
@@ -132,6 +133,7 @@
 	select IRQ_PER_CPU
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IRQ_SHOW_LEVEL
+	select IRQ_FORCED_THREADING
 	select HAVE_RCU_TABLE_FREE if SMP
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_BPF_JIT if (PPC64 && NET)
@@ -275,7 +277,7 @@
 
 config HIGHMEM
 	bool "High memory support"
-	depends on PPC32
+	depends on PPC32 && !PREEMPT_RT_FULL
 
 source kernel/time/Kconfig
 source kernel/Kconfig.hz
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index 39a2baa..5d70d10 100644
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -94,11 +94,11 @@
 		HMT_medium();
 		ppc64_runlatch_on();
 		tick_nohz_restart_sched_tick();
-		preempt_enable_no_resched();
-		if (cpu_should_die())
+		if (cpu_should_die()) {
+			__preempt_enable_no_resched();
 			cpu_die();
-		schedule();
-		preempt_disable();
+		}
+		schedule_preempt_disabled();
 	}
 }
 
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 745c1e7..e0ee531 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -440,6 +440,7 @@
 	}
 }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 static inline void do_softirq_onstack(void)
 {
 	struct thread_info *curtp, *irqtp;
@@ -476,7 +477,7 @@
 
 	local_irq_restore(flags);
 }
-
+#endif
 
 /*
  * IRQ controller and virtual interrupts
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 7cd07b4..46c6073 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -36,6 +36,7 @@
 
 	.text
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 _GLOBAL(call_do_softirq)
 	mflr	r0
 	stw	r0,4(r1)
@@ -46,6 +47,7 @@
 	lwz	r0,4(r1)
 	mtlr	r0
 	blr
+#endif
 
 _GLOBAL(call_handle_irq)
 	mflr	r0
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 616921e..2961d75 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -29,6 +29,7 @@
 
 	.text
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 _GLOBAL(call_do_softirq)
 	mflr	r0
 	std	r0,16(r1)
@@ -39,6 +40,7 @@
 	ld	r0,16(r1)
 	mtlr	r0
 	blr
+#endif
 
 _GLOBAL(call_handle_irq)
 	ld	r8,0(r6)
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index fe04b4a..2216eb2 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -187,8 +187,8 @@
 		return 1;
 	}
 #endif
-	err = request_irq(virq, smp_ipi_action[msg], IRQF_PERCPU,
-			  smp_ipi_name[msg], 0);
+	err = request_irq(virq, smp_ipi_action[msg],
+			  IRQF_PERCPU | IRQF_NO_THREAD, smp_ipi_name[msg], 0);
 	WARN(err < 0, "unable to request_irq %d for %s (rc %d)\n",
 		virq, smp_ipi_name[msg], err);
 
diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c
index 57fa2c0..1b9174d 100644
--- a/arch/powerpc/kernel/udbg.c
+++ b/arch/powerpc/kernel/udbg.c
@@ -182,15 +182,13 @@
 	.index	= 0,
 };
 
-static int early_console_initialized;
-
 /*
  * Called by setup_system after ppc_md->probe and ppc_md->early_init.
  * Call it again after setting udbg_putc in ppc_md->setup_arch.
  */
 void __init register_early_udbg_console(void)
 {
-	if (early_console_initialized)
+	if (early_console)
 		return;
 
 	if (!udbg_putc)
@@ -200,7 +198,7 @@
 		printk(KERN_INFO "early console immortal !\n");
 		udbg_console.flags &= ~CON_BOOT;
 	}
-	early_console_initialized = 1;
+	early_console = &udbg_console;
 	register_console(&udbg_console);
 }
 
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 7450843..e605ce8 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -162,7 +162,7 @@
 	}
 #endif
 
-	if (in_atomic() || mm == NULL) {
+	if (!mm || pagefault_disabled()) {
 		if (!user_mode(regs))
 			return SIGSEGV;
 		/* in_atomic() in user mode is really bad,
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_cds.c b/arch/powerpc/platforms/85xx/mpc85xx_cds.c
index 66cb8d6..7e2a4d2 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_cds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_cds.c
@@ -177,7 +177,7 @@
 
 static struct irqaction mpc85xxcds_8259_irqaction = {
 	.handler = mpc85xx_8259_cascade_action,
-	.flags = IRQF_SHARED,
+	.flags = IRQF_SHARED | IRQF_NO_THREAD,
 	.name = "8259 cascade",
 };
 #endif /* PPC_I8259 */
diff --git a/arch/powerpc/platforms/iseries/setup.c b/arch/powerpc/platforms/iseries/setup.c
index ea0acbd..e0c5b49 100644
--- a/arch/powerpc/platforms/iseries/setup.c
+++ b/arch/powerpc/platforms/iseries/setup.c
@@ -582,9 +582,7 @@
 		if (hvlpevent_is_pending())
 			process_iSeries_events();
 
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 	}
 }
 
@@ -611,9 +609,7 @@
 
 		ppc64_runlatch_on();
 		tick_nohz_restart_sched_tick();
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 	}
 }
 
diff --git a/arch/powerpc/platforms/powermac/smp.c b/arch/powerpc/platforms/powermac/smp.c
index 3394254..8d75ac8 100644
--- a/arch/powerpc/platforms/powermac/smp.c
+++ b/arch/powerpc/platforms/powermac/smp.c
@@ -200,7 +200,7 @@
 
 	if (psurge_secondary_virq)
 		rc = request_irq(psurge_secondary_virq, psurge_ipi_intr,
-			IRQF_PERCPU, "IPI", NULL);
+				 IRQF_NO_THREAD | IRQF_PERCPU, "IPI", NULL);
 
 	if (rc)
 		pr_err("Failed to setup secondary cpu IPI\n");
@@ -408,7 +408,7 @@
 
 static struct irqaction psurge_irqaction = {
 	.handler = psurge_ipi_intr,
-	.flags = IRQF_PERCPU,
+	.flags = IRQF_PERCPU | IRQF_NO_THREAD,
 	.name = "primary IPI",
 };
 
diff --git a/arch/powerpc/platforms/wsp/opb_pic.c b/arch/powerpc/platforms/wsp/opb_pic.c
index be05631..19f353d 100644
--- a/arch/powerpc/platforms/wsp/opb_pic.c
+++ b/arch/powerpc/platforms/wsp/opb_pic.c
@@ -320,7 +320,8 @@
 		}
 
 		/* Attach opb interrupt handler to new virtual IRQ */
-		rc = request_irq(virq, opb_irq_handler, 0, "OPB LS Cascade", opb);
+		rc = request_irq(virq, opb_irq_handler, IRQF_NO_THREAD,
+				 "OPB LS Cascade", opb);
 		if (rc) {
 			printk("opb: request_irq failed: %d\n", rc);
 			continue;
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index 63762c6..4ba6194 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -134,10 +134,11 @@
 	BUG_ON(ipi == NO_IRQ);
 
 	/*
-	 * IPIs are marked IRQF_PERCPU. The handler was set in map.
+	 * IPIs are marked PERCPU and also IRQF_NO_THREAD as they must
+	 * run in hard interrupt context. The handler was set in map.
 	 */
 	BUG_ON(request_irq(ipi, icp_ops->ipi_action,
-			   IRQF_PERCPU, "IPI", NULL));
+			   IRQF_NO_THREAD|IRQF_PERCPU, "IPI", NULL));
 }
 
 int __init xics_smp_probe(void)
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 2ba1226..db9c038 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -94,9 +94,7 @@
 		while (!need_resched())
 			default_idle();
 		tick_nohz_restart_sched_tick();
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 	}
 }
 
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index b53339d..229ca60 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -301,7 +301,8 @@
 	 * user context.
 	 */
 	fault = VM_FAULT_BADCONTEXT;
-	if (unlikely(!user_space_fault(trans_exc_code) || in_atomic() || !mm))
+	if (unlikely(!user_space_fault(trans_exc_code) ||
+		     !mm || pagefault_disabled()))
 		goto out;
 
 	address = trans_exc_code & __FAIL_ADDR_MASK;
@@ -432,7 +433,8 @@
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 
-	if (unlikely(!user_space_fault(trans_exc_code) || in_atomic() || !mm))
+	if (unlikely(!user_space_fault(trans_exc_code) ||
+		     !mm || pagefault_disabled()))
 		goto no_context;
 
 	down_read(&mm->mmap_sem);
diff --git a/arch/score/kernel/process.c b/arch/score/kernel/process.c
index 25d0803..2707023 100644
--- a/arch/score/kernel/process.c
+++ b/arch/score/kernel/process.c
@@ -53,9 +53,7 @@
 		while (!need_resched())
 			barrier();
 
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 	}
 }
 
diff --git a/arch/score/mm/fault.c b/arch/score/mm/fault.c
index b3744ca..7dce742 100644
--- a/arch/score/mm/fault.c
+++ b/arch/score/mm/fault.c
@@ -72,7 +72,7 @@
 	* If we're in an interrupt or have no user
 	* context, we must not take the fault..
 	*/
-	if (in_atomic() || !mm)
+	if (!mm || pagefault_disabled())
 		goto bad_area_nosemaphore;
 
 	down_read(&mm->mmap_sem);
diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c
index db4ecd7..b7c18f08 100644
--- a/arch/sh/kernel/idle.c
+++ b/arch/sh/kernel/idle.c
@@ -112,9 +112,7 @@
 		}
 
 		tick_nohz_restart_sched_tick();
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 	}
 }
 
diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c
index a3ee919..9127bc0 100644
--- a/arch/sh/kernel/irq.c
+++ b/arch/sh/kernel/irq.c
@@ -149,6 +149,7 @@
 	hardirq_ctx[cpu] = NULL;
 }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 asmlinkage void do_softirq(void)
 {
 	unsigned long flags;
@@ -191,6 +192,7 @@
 
 	local_irq_restore(flags);
 }
+#endif
 #else
 static inline void handle_one_irq(unsigned int irq)
 {
diff --git a/arch/sh/kernel/sh_bios.c b/arch/sh/kernel/sh_bios.c
index 47475cc..a5b51b9 100644
--- a/arch/sh/kernel/sh_bios.c
+++ b/arch/sh/kernel/sh_bios.c
@@ -144,8 +144,6 @@
 	.index		= -1,
 };
 
-static struct console *early_console;
-
 static int __init setup_early_printk(char *buf)
 {
 	int keep_early = 0;
diff --git a/arch/sh/mm/fault_32.c b/arch/sh/mm/fault_32.c
index db14482..da16a99 100644
--- a/arch/sh/mm/fault_32.c
+++ b/arch/sh/mm/fault_32.c
@@ -166,7 +166,7 @@
 	 * If we're in an interrupt, have no user context or are running
 	 * in an atomic region then we must not take the fault:
 	 */
-	if (in_atomic() || !mm)
+	if (!mm || pagefault_disabled())
 		goto no_context;
 
 	down_read(&mm->mmap_sem);
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index d45b710..c3a3737 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -699,6 +699,7 @@
 	set_irq_regs(old_regs);
 }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 void do_softirq(void)
 {
 	unsigned long flags;
@@ -724,6 +725,7 @@
 
 	local_irq_restore(flags);
 }
+#endif
 
 #ifdef CONFIG_HOTPLUG_CPU
 void fixup_irqs(void)
diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index f793742..935fdbc 100644
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -113,9 +113,7 @@
 			while (!need_resched())
 				cpu_relax();
 		}
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 		check_pgt_cache();
 	}
 }
@@ -138,9 +136,7 @@
 			while (!need_resched())
 				cpu_relax();
 		}
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 		check_pgt_cache();
 	}
 }
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index 3739a06..86fe09a 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -102,15 +102,13 @@
 
 		tick_nohz_restart_sched_tick();
 
-		preempt_enable_no_resched();
-
 #ifdef CONFIG_HOTPLUG_CPU
-		if (cpu_is_offline(cpu))
+		if (cpu_is_offline(cpu)) {
+			__preempt_enable_no_resched();
 			cpu_play_dead();
+		}
 #endif
-
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 	}
 }
 
diff --git a/arch/sparc/kernel/prom_common.c b/arch/sparc/kernel/prom_common.c
index 741df91..ca73a28 100644
--- a/arch/sparc/kernel/prom_common.c
+++ b/arch/sparc/kernel/prom_common.c
@@ -65,7 +65,7 @@
 	err = -ENODEV;
 
 	mutex_lock(&of_set_property_mutex);
-	write_lock(&devtree_lock);
+	raw_spin_lock(&devtree_lock);
 	prevp = &dp->properties;
 	while (*prevp) {
 		struct property *prop = *prevp;
@@ -92,7 +92,7 @@
 		}
 		prevp = &(*prevp)->next;
 	}
-	write_unlock(&devtree_lock);
+	raw_spin_unlock(&devtree_lock);
 	mutex_unlock(&of_set_property_mutex);
 
 	/* XXX Upate procfs if necessary... */
diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c
index fe1e3fc..e6475f0 100644
--- a/arch/sparc/kernel/setup_32.c
+++ b/arch/sparc/kernel/setup_32.c
@@ -221,6 +221,7 @@
 
 	boot_flags_init(*cmdline_p);
 
+	early_console = &prom_early_console;
 	register_console(&prom_early_console);
 
 	/* Set sparc_cpu_model */
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index a854a1c..b85d039 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -487,6 +487,12 @@
 		popc_patch();
 }
 
+static inline void register_prom_console(void)
+{
+	early_console = &prom_early_console;
+	register_console(&prom_early_console);
+}
+
 void __init setup_arch(char **cmdline_p)
 {
 	/* Initialize PROM console and command line. */
@@ -498,7 +504,7 @@
 #ifdef CONFIG_EARLYFB
 	if (btext_find_display())
 #endif
-		register_console(&prom_early_console);
+		register_prom_console();
 
 	if (tlb_type == hypervisor)
 		printk("ARCH: SUN4V\n");
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index 802b806..76fd06d 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -247,8 +247,8 @@
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-        if (in_atomic() || !mm)
-                goto no_context;
+	if (!mm || pagefault_disabled())
+		goto no_context;
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
 
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index bfd7c02..6255243 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -330,7 +330,7 @@
 	 * If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm)
+	if (!mm || pagefault_disabled())
 		goto intr_or_no_mm;
 
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
diff --git a/arch/tile/include/asm/smp.h b/arch/tile/include/asm/smp.h
index 532124a..1aa759a 100644
--- a/arch/tile/include/asm/smp.h
+++ b/arch/tile/include/asm/smp.h
@@ -43,10 +43,6 @@
 /* Boot a secondary cpu */
 void online_secondary(void);
 
-/* Call a function on a specified set of CPUs (may include this one). */
-extern void on_each_cpu_mask(const struct cpumask *mask,
-			     void (*func)(void *), void *info, bool wait);
-
 /* Topology of the supervisor tile grid, and coordinates of boot processor */
 extern HV_Topology smp_topology;
 
@@ -91,9 +87,6 @@
 
 #else /* !CONFIG_SMP */
 
-#define on_each_cpu_mask(mask, func, info, wait)		\
-  do { if (cpumask_test_cpu(0, (mask))) func(info); } while (0)
-
 #define smp_master_cpu		0
 #define smp_height		1
 #define smp_width		1
diff --git a/arch/tile/kernel/early_printk.c b/arch/tile/kernel/early_printk.c
index 493a0e6..ba2ac00 100644
--- a/arch/tile/kernel/early_printk.c
+++ b/arch/tile/kernel/early_printk.c
@@ -32,25 +32,8 @@
 };
 
 /* Direct interface for emergencies */
-static struct console *early_console = &early_hv_console;
-static int early_console_initialized;
 static int early_console_complete;
 
-static void early_vprintk(const char *fmt, va_list ap)
-{
-	char buf[512];
-	int n = vscnprintf(buf, sizeof(buf), fmt, ap);
-	early_console->write(early_console, buf, n);
-}
-
-void early_printk(const char *fmt, ...)
-{
-	va_list ap;
-	va_start(ap, fmt);
-	early_vprintk(fmt, ap);
-	va_end(ap);
-}
-
 void early_panic(const char *fmt, ...)
 {
 	va_list ap;
@@ -68,14 +51,13 @@
 
 static int __init setup_early_printk(char *str)
 {
-	if (early_console_initialized)
+	if (early_console)
 		return 1;
 
 	if (str != NULL && strncmp(str, "keep", 4) == 0)
 		keep_early = 1;
 
 	early_console = &early_hv_console;
-	early_console_initialized = 1;
 	register_console(early_console);
 
 	return 0;
@@ -84,12 +66,12 @@
 void __init disable_early_printk(void)
 {
 	early_console_complete = 1;
-	if (!early_console_initialized || !early_console)
+	if (!early_console)
 		return;
 	if (!keep_early) {
 		early_printk("disabling early console\n");
 		unregister_console(early_console);
-		early_console_initialized = 0;
+		early_console = NULL;
 	} else {
 		early_printk("keeping early console\n");
 	}
@@ -97,7 +79,7 @@
 
 void warn_early_printk(void)
 {
-	if (early_console_complete || early_console_initialized)
+	if (early_console_complete || early_console)
 		return;
 	early_printk("\
 Machine shutting down before console output is fully initialized.\n\
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index 9c45d8b..5a8b631 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -106,9 +106,7 @@
 			current_thread_info()->status |= TS_POLLING;
 		}
 		tick_nohz_restart_sched_tick();
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 	}
 }
 
diff --git a/arch/tile/kernel/smp.c b/arch/tile/kernel/smp.c
index c52224d..a44e103 100644
--- a/arch/tile/kernel/smp.c
+++ b/arch/tile/kernel/smp.c
@@ -87,25 +87,6 @@
 	send_IPI_many(&mask, tag);
 }
 
-
-/*
- * Provide smp_call_function_mask, but also run function locally
- * if specified in the mask.
- */
-void on_each_cpu_mask(const struct cpumask *mask, void (*func)(void *),
-		      void *info, bool wait)
-{
-	int cpu = get_cpu();
-	smp_call_function_many(mask, func, info, wait);
-	if (cpumask_test_cpu(cpu, mask)) {
-		local_irq_disable();
-		func(info);
-		local_irq_enable();
-	}
-	put_cpu();
-}
-
-
 /*
  * Functions related to starting/stopping cpus.
  */
diff --git a/arch/tile/mm/fault.c b/arch/tile/mm/fault.c
index c796ce44..bd8f35c 100644
--- a/arch/tile/mm/fault.c
+++ b/arch/tile/mm/fault.c
@@ -346,7 +346,7 @@
 	 * If we're in an interrupt, have no user context or are running in an
 	 * atomic region then we must not take the fault.
 	 */
-	if (in_atomic() || !mm) {
+	if (!mm || pagefault_disabled()) {
 		vma = NULL;  /* happy compiler */
 		goto bad_area_nosemaphore;
 	}
diff --git a/arch/um/kernel/early_printk.c b/arch/um/kernel/early_printk.c
index ec649bf..183060f 100644
--- a/arch/um/kernel/early_printk.c
+++ b/arch/um/kernel/early_printk.c
@@ -16,7 +16,7 @@
 	um_early_printk(s, n);
 }
 
-static struct console early_console = {
+static struct console early_console_dev = {
 	.name = "earlycon",
 	.write = early_console_write,
 	.flags = CON_BOOT,
@@ -25,8 +25,10 @@
 
 static int __init setup_early_printk(char *buf)
 {
-	register_console(&early_console);
-
+	if (!early_console) {
+		early_console = &early_console_dev;
+		register_console(&early_console_dev);
+	}
 	return 0;
 }
 
diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c
index f79ffc9..846737e 100644
--- a/arch/um/kernel/trap.c
+++ b/arch/um/kernel/trap.c
@@ -37,7 +37,7 @@
 	 * If the fault was during atomic operation, don't take the fault, just
 	 * fail.
 	 */
-	if (in_atomic())
+	if (!mm || pagefault_disabled())
 		goto out_nosemaphore;
 
 	down_read(&mm->mmap_sem);
diff --git a/arch/unicore32/kernel/early_printk.c b/arch/unicore32/kernel/early_printk.c
index 3922255..9be0d5d 100644
--- a/arch/unicore32/kernel/early_printk.c
+++ b/arch/unicore32/kernel/early_printk.c
@@ -33,21 +33,17 @@
 	.index =	-1,
 };
 
-/* Direct interface for emergencies */
-static struct console *early_console = &early_ocd_console;
-
-static int __initdata keep_early;
-
 static int __init setup_early_printk(char *buf)
 {
-	if (!buf)
+	int keep_early;
+
+	if (!buf || early_console)
 		return 0;
 
 	if (strstr(buf, "keep"))
 		keep_early = 1;
 
-	if (!strncmp(buf, "ocd", 3))
-		early_console = &early_ocd_console;
+	early_console = &early_ocd_console;
 
 	if (keep_early)
 		early_console->flags &= ~CON_BOOT;
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index d720208..ac49759 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -163,10 +163,10 @@
 	def_bool ISA_DMA_API
 
 config RWSEM_GENERIC_SPINLOCK
-	def_bool !X86_XADD
+	def_bool !X86_XADD || PREEMPT_RT_FULL
 
 config RWSEM_XCHGADD_ALGORITHM
-	def_bool X86_XADD
+	def_bool X86_XADD && !RWSEM_GENERIC_SPINLOCK && !PREEMPT_RT_FULL
 
 config ARCH_HAS_CPU_IDLE_WAIT
 	def_bool y
@@ -732,7 +732,7 @@
 config MAXSMP
 	bool "Enable Maximum number of SMP Processors and NUMA Nodes"
 	depends on X86_64 && SMP && DEBUG_KERNEL && EXPERIMENTAL
-	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 3b3a62f..0d0e6e1 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -289,14 +289,14 @@
 	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;
 }
@@ -313,14 +313,14 @@
 	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;
 }
@@ -359,14 +359,14 @@
 	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;
 }
@@ -383,14 +383,14 @@
 	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;
 }
@@ -445,18 +445,20 @@
 	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(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/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 610001d..c1c23d2 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -51,8 +51,8 @@
 
 #define ACPI_ASM_MACROS
 #define BREAKPOINT3
-#define ACPI_DISABLE_IRQS() local_irq_disable()
-#define ACPI_ENABLE_IRQS()  local_irq_enable()
+#define ACPI_DISABLE_IRQS() local_irq_disable_nort()
+#define ACPI_ENABLE_IRQS()  local_irq_enable_nort()
 #define ACPI_FLUSH_CPU_CACHE()	wbinvd()
 
 int __acpi_acquire_global_lock(unsigned int *lock);
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index 6cbc795..76475dc 100644
--- a/arch/x86/include/asm/signal.h
+++ b/arch/x86/include/asm/signal.h
@@ -31,6 +31,19 @@
 	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) && defined(CONFIG_X86_64)
+#define ARCH_RT_DELAYS_SIGNAL_SEND
+#endif
+
 #else
 /* Here we must cater to libcs that poke about in kernel headers.  */
 
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 1575177..ac0703b 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -58,7 +58,7 @@
  */
 static __always_inline void boot_init_stack_canary(void)
 {
-	u64 canary;
+	u64 uninitialized_var(canary);
 	u64 tsc;
 
 #ifdef CONFIG_X86_64
@@ -69,8 +69,16 @@
 	 * 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 = __native_read_tsc();
 	canary += tsc + (tsc << 32UL);
 
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 679229f..8ec3813 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -601,8 +601,8 @@
 	unsigned short		uvhub_quiesce;
 	short			socket_acknowledge_count[DEST_Q_SIZE];
 	cycles_t		send_message;
-	spinlock_t		uvhub_lock;
-	spinlock_t		queue_lock;
+	raw_spinlock_t		uvhub_lock;
+	raw_spinlock_t		queue_lock;
 	/* tunables */
 	int			max_concurr;
 	int			max_concurr_const;
@@ -759,15 +759,15 @@
  * 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 21f7385..953f5c6 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -475,7 +475,7 @@
 	unsigned short	nr_online_cpus;
 	unsigned short	pnode;
 	short		memory_nid;
-	spinlock_t	nmi_lock;
+	raw_spinlock_t	nmi_lock;
 	unsigned long	nmi_count;
 };
 extern struct uv_blade_info *uv_blade_info;
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index 815285b..1f00717 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -5,7 +5,7 @@
 #include <linux/clocksource.h>
 
 struct vsyscall_gtod_data {
-	seqlock_t	lock;
+	seqcount_t	seq;
 
 	/* open coded 'struct timespec' */
 	time_t		wall_time_sec;
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 838a3b4..b3aa9f5 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -876,8 +876,8 @@
 	 * Besides, if we don't timer interrupts ignore the global
 	 * interrupt lock, which is the WrongThing (tm) to do.
 	 */
-	exit_idle();
 	irq_enter();
+	exit_idle();
 	local_apic_timer_interrupt();
 	irq_exit();
 
@@ -1815,8 +1815,8 @@
 {
 	u32 v;
 
-	exit_idle();
 	irq_enter();
+	exit_idle();
 	/*
 	 * Check if this really is a spurious interrupt and ACK it
 	 * if it is a vectored one.  Just in case...
@@ -1852,8 +1852,8 @@
 		"Illegal register address",	/* APIC Error Bit 7 */
 	};
 
-	exit_idle();
 	irq_enter();
+	exit_idle();
 	/* First tickle the hardware, only then report what went on. -- REW */
 	v0 = apic_read(APIC_ESR);
 	apic_write(APIC_ESR, 0);
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 6d939d7..91527bc 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2421,8 +2421,8 @@
 	unsigned vector, me;
 
 	ack_APIC_irq();
-	exit_idle();
 	irq_enter();
+	exit_idle();
 
 	me = smp_processor_id();
 	for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
@@ -2521,7 +2521,8 @@
 	irq_complete_move(cfg);
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	/* 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))) {
 		do_unmask_irq = 1;
 		mask_ioapic(cfg);
 	}
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 79b05b8..8703c96 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -56,7 +56,7 @@
 EXPORT_SYMBOL_GPL(uv_min_hub_revision_id);
 unsigned int uv_apicid_hibits;
 EXPORT_SYMBOL_GPL(uv_apicid_hibits);
-static DEFINE_SPINLOCK(uv_nmi_lock);
+static DEFINE_RAW_SPINLOCK(uv_nmi_lock);
 
 static struct apic apic_x2apic_uv_x;
 
@@ -689,13 +689,13 @@
 	real_uv_nmi = (uv_read_local_mmr(UVH_NMI_MMR) & UV_NMI_PENDING_MASK);
 
 	if (unlikely(real_uv_nmi)) {
-		spin_lock(&uv_blade_info[bid].nmi_lock);
+		raw_spin_lock(&uv_blade_info[bid].nmi_lock);
 		real_uv_nmi = (uv_read_local_mmr(UVH_NMI_MMR) & UV_NMI_PENDING_MASK);
 		if (real_uv_nmi) {
 			uv_blade_info[bid].nmi_count++;
 			uv_write_local_mmr(UVH_NMI_MMR_CLEAR, UV_NMI_PENDING_MASK);
 		}
-		spin_unlock(&uv_blade_info[bid].nmi_lock);
+		raw_spin_unlock(&uv_blade_info[bid].nmi_lock);
 	}
 
 	if (likely(__get_cpu_var(cpu_last_nmi_count) == uv_blade_info[bid].nmi_count))
@@ -707,10 +707,10 @@
 	 * Use a lock so only one cpu prints at a time.
 	 * This prevents intermixed output.
 	 */
-	spin_lock(&uv_nmi_lock);
+	raw_spin_lock(&uv_nmi_lock);
 	pr_info("UV NMI stack dump cpu %u:\n", smp_processor_id());
 	dump_stack();
-	spin_unlock(&uv_nmi_lock);
+	raw_spin_unlock(&uv_nmi_lock);
 
 	return NMI_HANDLED;
 }
@@ -805,7 +805,7 @@
 			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);
 			max_pnode = max(pnode, max_pnode);
 			blade++;
 		}
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 3b67877..b08a373 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -15,6 +15,7 @@
 #include <linux/rcupdate.h>
 #include <linux/kobject.h>
 #include <linux/uaccess.h>
+#include <linux/kthread.h>
 #include <linux/kdebug.h>
 #include <linux/kernel.h>
 #include <linux/percpu.h>
@@ -38,6 +39,7 @@
 #include <linux/debugfs.h>
 #include <linux/irq_work.h>
 #include <linux/export.h>
+#include <linux/jiffies.h>
 
 #include <asm/processor.h>
 #include <asm/mce.h>
@@ -1112,17 +1114,14 @@
  * poller finds an MCE, poll 2x faster.  When the poller finds no more
  * errors, poll 2x slower (up to check_interval seconds).
  */
-static int check_interval = 5 * 60; /* 5 minutes */
+static unsigned long check_interval = 5 * 60; /* 5 minutes */
 
-static DEFINE_PER_CPU(int, mce_next_interval); /* in jiffies */
-static DEFINE_PER_CPU(struct timer_list, mce_timer);
+static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */
+static DEFINE_PER_CPU(struct hrtimer, mce_timer);
 
-static void mce_start_timer(unsigned long data)
+static enum hrtimer_restart mce_start_timer(struct hrtimer *timer)
 {
-	struct timer_list *t = &per_cpu(mce_timer, data);
-	int *n;
-
-	WARN_ON(smp_processor_id() != data);
+	unsigned long *n;
 
 	if (mce_available(__this_cpu_ptr(&cpu_info))) {
 		machine_check_poll(MCP_TIMESTAMP,
@@ -1135,21 +1134,22 @@
 	 */
 	n = &__get_cpu_var(mce_next_interval);
 	if (mce_notify_irq())
-		*n = max(*n/2, HZ/100);
+		*n = max(*n/2, HZ/100UL);
 	else
-		*n = min(*n*2, (int)round_jiffies_relative(check_interval*HZ));
+		*n = min(*n*2, round_jiffies_relative(check_interval*HZ));
 
-	t->expires = jiffies + *n;
-	add_timer_on(t, smp_processor_id());
+	hrtimer_forward(timer, timer->base->get_time(),
+			ns_to_ktime(jiffies_to_usecs(*n) * 1000ULL));
+	return HRTIMER_RESTART;
 }
 
-/* Must not be called in IRQ context where del_timer_sync() can deadlock */
+/* Must not be called in IRQ context where hrtimer_cancel() can deadlock */
 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)
@@ -1159,6 +1159,63 @@
 
 static DECLARE_WORK(mce_trigger_work, mce_do_trigger);
 
+static void __mce_notify_work(void)
+{
+	/* 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
+struct task_struct *mce_notify_helper;
+
+static int mce_notify_helper_thread(void *unused)
+{
+	while (1) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		schedule();
+		if (kthread_should_stop())
+			break;
+		__mce_notify_work();
+	}
+	return 0;
+}
+
+static int mce_notify_work_init(void)
+{
+	mce_notify_helper = kthread_run(mce_notify_helper_thread, NULL,
+					   "mce-notify");
+	if (!mce_notify_helper)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void mce_notify_work(void)
+{
+	wake_up_process(mce_notify_helper);
+}
+#else
+static void mce_notify_work(void)
+{
+	__mce_notify_work();
+}
+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
@@ -1166,26 +1223,10 @@
  */
 int mce_notify_irq(void)
 {
-	/* Not more than two messages every minute */
-	static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2);
-
 	clear_thread_flag(TIF_MCE_NOTIFY);
 
 	if (test_and_clear_bit(0, &mce_need_notify)) {
-		/* 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");
-
+		mce_notify_work();
 		return 1;
 	}
 	return 0;
@@ -1381,10 +1422,11 @@
 
 static void __mcheck_cpu_init_timer(void)
 {
-	struct timer_list *t = &__get_cpu_var(mce_timer);
-	int *n = &__get_cpu_var(mce_next_interval);
+	struct hrtimer *t = &__get_cpu_var(mce_timer);
+	unsigned long *n = &__get_cpu_var(mce_next_interval);
 
-	setup_timer(t, mce_start_timer, smp_processor_id());
+	hrtimer_init(t, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	t->function = mce_start_timer;
 
 	if (mce_ignore_ce)
 		return;
@@ -1392,8 +1434,9 @@
 	*n = check_interval * HZ;
 	if (!*n)
 		return;
-	t->expires = round_jiffies(jiffies + *n);
-	add_timer_on(t, smp_processor_id());
+
+	hrtimer_start_range_ns(t, ns_to_ktime(jiffies_to_usecs(*n) * 1000ULL),
+			       0 , HRTIMER_MODE_REL_PINNED);
 }
 
 /* Handle unconfigured int18 (should never happen) */
@@ -2029,6 +2072,8 @@
 	if (!mce_available(__this_cpu_ptr(&cpu_info)))
 		return;
 
+	hrtimer_cancel(&__get_cpu_var(mce_timer));
+
 	if (!(action & CPU_TASKS_FROZEN))
 		cmci_clear();
 	for (i = 0; i < banks; i++) {
@@ -2055,6 +2100,7 @@
 		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. */
@@ -2062,7 +2108,6 @@
 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) {
 	case CPU_ONLINE:
@@ -2079,16 +2124,10 @@
 		break;
 	case CPU_DOWN_PREPARE:
 	case CPU_DOWN_PREPARE_FROZEN:
-		del_timer_sync(t);
 		smp_call_function_single(cpu, mce_disable_cpu, &action, 1);
 		break;
 	case CPU_DOWN_FAILED:
 	case CPU_DOWN_FAILED_FROZEN:
-		if (!mce_ignore_ce && check_interval) {
-			t->expires = round_jiffies(jiffies +
-					   __get_cpu_var(mce_next_interval));
-			add_timer_on(t, cpu);
-		}
 		smp_call_function_single(cpu, mce_reenable_cpu, &action, 1);
 		break;
 	case CPU_POST_DEAD:
@@ -2149,6 +2188,8 @@
 	/* register character device /dev/mcelog */
 	misc_register(&mce_chrdev_device);
 
+	err = mce_notify_work_init();
+
 	return err;
 }
 device_initcall(mcheck_init_device);
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index ce04b58..39c6089 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -382,8 +382,8 @@
 
 asmlinkage void smp_thermal_interrupt(struct pt_regs *regs)
 {
-	exit_idle();
 	irq_enter();
+	exit_idle();
 	inc_irq_stat(irq_thermal_count);
 	smp_thermal_vector();
 	irq_exit();
diff --git a/arch/x86/kernel/cpu/mcheck/threshold.c b/arch/x86/kernel/cpu/mcheck/threshold.c
index d746df2..aa578ca 100644
--- a/arch/x86/kernel/cpu/mcheck/threshold.c
+++ b/arch/x86/kernel/cpu/mcheck/threshold.c
@@ -19,8 +19,8 @@
 
 asmlinkage void smp_threshold_interrupt(void)
 {
-	exit_idle();
 	irq_enter();
+	exit_idle();
 	inc_irq_stat(irq_threshold_count);
 	mce_threshold_vector();
 	irq_exit();
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index cd28a35..5f3d9c5 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -169,25 +169,9 @@
 	.index =	-1,
 };
 
-/* Direct interface for emergencies */
-static struct console *early_console = &early_vga_console;
-static int __initdata early_console_initialized;
-
-asmlinkage void early_printk(const char *fmt, ...)
-{
-	char buf[512];
-	int n;
-	va_list ap;
-
-	va_start(ap, fmt);
-	n = vscnprintf(buf, sizeof(buf), fmt, ap);
-	early_console->write(early_console, buf, n);
-	va_end(ap);
-}
-
 static inline void early_console_register(struct console *con, int keep_early)
 {
-	if (early_console->index != -1) {
+	if (con->index != -1) {
 		printk(KERN_CRIT "ERROR: earlyprintk= %s already used\n",
 		       con->name);
 		return;
@@ -207,9 +191,8 @@
 	if (!buf)
 		return 0;
 
-	if (early_console_initialized)
+	if (early_console)
 		return 0;
-	early_console_initialized = 1;
 
 	keep = (strstr(buf, "keep") != NULL);
 
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 0fa4f89..5b7e058 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -630,7 +630,11 @@
 	jne work_notifysig_v86		# returning to kernel-space or
 					# vm86-space
 	xorl %edx, %edx
+	TRACE_IRQS_ON
+	ENABLE_INTERRUPTS(CLBR_NONE)
 	call do_notify_resume
+	DISABLE_INTERRUPTS(CLBR_ANY)
+	TRACE_IRQS_OFF
 	jmp resume_userspace_sig
 
 	ALIGN
@@ -643,7 +647,11 @@
 	movl %esp, %eax
 #endif
 	xorl %edx, %edx
+	TRACE_IRQS_ON
+	ENABLE_INTERRUPTS(CLBR_NONE)
 	call do_notify_resume
+	DISABLE_INTERRUPTS(CLBR_ANY)
+	TRACE_IRQS_OFF
 	jmp resume_userspace_sig
 END(work_pending)
 
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 8d15c69..6dda40f 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1210,6 +1210,7 @@
 	CFI_ENDPROC
 END(kernel_execve)
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /* Call softirq on interrupt stack. Interrupts are off. */
 ENTRY(call_softirq)
 	CFI_STARTPROC
@@ -1229,6 +1230,7 @@
 	ret
 	CFI_ENDPROC
 END(call_softirq)
+#endif
 
 #ifdef CONFIG_XEN
 zeroentry xen_hypervisor_callback xen_do_hypervisor_callback
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 4970ef0..424ae2e 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -9,6 +9,7 @@
 #include <linux/slab.h>
 #include <linux/hpet.h>
 #include <linux/init.h>
+#include <linux/dmi.h>
 #include <linux/cpu.h>
 #include <linux/pm.h>
 #include <linux/io.h>
@@ -568,6 +569,30 @@
 #define RESERVE_TIMERS 0
 #endif
 
+static int __init dmi_disable_hpet_msi(const struct dmi_system_id *d)
+{
+	hpet_msi_disable = 1;
+	return 0;
+}
+
+static struct dmi_system_id __initdata dmi_hpet_table[] = {
+	/*
+	 * MSI based per cpu timers lose interrupts when intel_idle()
+	 * is enabled - independent of the c-state. With idle=poll the
+	 * problem cannot be observed. We have no idea yet, whether
+	 * this is a W510 specific issue or a general chipset oddity.
+	 */
+	{
+	 .callback = dmi_disable_hpet_msi,
+	 .ident = "Lenovo W510",
+	 .matches = {
+		     DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+		     DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad W510"),
+		     },
+	 },
+	{}
+};
+
 static void hpet_msi_capability_lookup(unsigned int start_timer)
 {
 	unsigned int id;
@@ -575,6 +600,8 @@
 	unsigned int num_timers_used = 0;
 	int i;
 
+	dmi_check_system(dmi_hpet_table);
+
 	if (hpet_msi_disable)
 		return;
 
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 687637b..6724ff1 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -177,8 +177,8 @@
 	unsigned vector = ~regs->orig_ax;
 	unsigned irq;
 
-	exit_idle();
 	irq_enter();
+	exit_idle();
 
 	irq = __this_cpu_read(vector_irq[vector]);
 
@@ -205,10 +205,10 @@
 
 	ack_APIC_irq();
 
-	exit_idle();
-
 	irq_enter();
 
+	exit_idle();
+
 	inc_irq_stat(x86_platform_ipis);
 
 	if (x86_platform_ipi_callback)
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 7209070..84417a2 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -149,6 +149,7 @@
 	       cpu, per_cpu(hardirq_ctx, cpu),  per_cpu(softirq_ctx, cpu));
 }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 asmlinkage void do_softirq(void)
 {
 	unsigned long flags;
@@ -179,6 +180,7 @@
 
 	local_irq_restore(flags);
 }
+#endif
 
 bool handle_irq(unsigned irq, struct pt_regs *regs)
 {
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 69bca46..3fbc07d 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -65,7 +65,7 @@
 	return true;
 }
 
-
+#ifndef CONFIG_PREEMPT_RT_FULL
 extern void call_softirq(void);
 
 asmlinkage void do_softirq(void)
@@ -85,3 +85,4 @@
 	}
 	local_irq_restore(flags);
 }
+#endif
diff --git a/arch/x86/kernel/irq_work.c b/arch/x86/kernel/irq_work.c
index ca8f703..129b8bb 100644
--- a/arch/x86/kernel/irq_work.c
+++ b/arch/x86/kernel/irq_work.c
@@ -18,6 +18,7 @@
 	irq_exit();
 }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 void arch_irq_work_raise(void)
 {
 #ifdef CONFIG_X86_LOCAL_APIC
@@ -28,3 +29,4 @@
 	apic_wait_icr_idle();
 #endif
 }
+#endif
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index 083848f..02cc07c 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -478,7 +478,6 @@
 		 * stepping.
 		 */
 		regs->ip = (unsigned long)p->ainsn.insn;
-		preempt_enable_no_resched();
 		return;
 	}
 #endif
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 8598296..66ee590 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -39,6 +39,7 @@
 #include <linux/io.h>
 #include <linux/kdebug.h>
 #include <linux/cpuidle.h>
+#include <linux/highmem.h>
 
 #include <asm/pgtable.h>
 #include <asm/system.h>
@@ -117,9 +118,7 @@
 			start_critical_timings();
 		}
 		tick_nohz_restart_sched_tick();
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 	}
 }
 
@@ -341,6 +340,41 @@
 		     task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT))
 		__switch_to_xtra(prev_p, next_p, tss);
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+	/*
+	 * Save @prev's kmap_atomic stack
+	 */
+	prev_p->kmap_idx = __this_cpu_read(__kmap_atomic_idx);
+	if (unlikely(prev_p->kmap_idx)) {
+		int i;
+
+		for (i = 0; i < prev_p->kmap_idx; i++) {
+			int idx = i + KM_TYPE_NR * smp_processor_id();
+
+			pte_t *ptep = kmap_pte - idx;
+			prev_p->kmap_pte[i] = *ptep;
+			kpte_clear_flush(ptep, __fix_to_virt(FIX_KMAP_BEGIN + idx));
+		}
+
+		__this_cpu_write(__kmap_atomic_idx, 0);
+	}
+
+	/*
+	 * Restore @next_p's kmap_atomic stack
+	 */
+	if (unlikely(next_p->kmap_idx)) {
+		int i;
+
+		__this_cpu_write(__kmap_atomic_idx, next_p->kmap_idx);
+
+		for (i = 0; i < next_p->kmap_idx; i++) {
+			int idx = i + KM_TYPE_NR * smp_processor_id();
+
+			set_pte(kmap_pte - idx, next_p->kmap_pte[i]);
+		}
+	}
+#endif
+
 	/*
 	 * Leave lazy mode, flushing any hypercalls made here.
 	 * This must be done before restoring TLS segments so
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index e361095..a8a8192 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -150,9 +150,7 @@
 		}
 
 		tick_nohz_restart_sched_tick();
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 	}
 }
 
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 54ddaeb2..12c4d53 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -820,6 +820,15 @@
 		mce_notify_process();
 #endif /* CONFIG_X86_64 && CONFIG_X86_MCE */
 
+#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
+
 	/* deal with pending signal delivery */
 	if (thread_info_flags & _TIF_SIGPENDING)
 		do_signal(regs);
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index edbd30a..7cbf5e3 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -87,9 +87,21 @@
 		local_irq_enable();
 }
 
-static inline void preempt_conditional_sti(struct pt_regs *regs)
+static inline void conditional_sti_ist(struct pt_regs *regs)
 {
+#ifdef CONFIG_X86_64
+	/*
+	 * X86_64 uses a per CPU stack on the IST for certain traps
+	 * like int3. The task can not be preempted when using one
+	 * of these stacks, thus preemption must be disabled, otherwise
+	 * the stack can be corrupted if the task is scheduled out,
+	 * and another task comes in and uses this stack.
+	 *
+	 * On x86_32 the task keeps its own stack and it is OK if the
+	 * task schedules out.
+	 */
 	inc_preempt_count();
+#endif
 	if (regs->flags & X86_EFLAGS_IF)
 		local_irq_enable();
 }
@@ -100,11 +112,13 @@
 		local_irq_disable();
 }
 
-static inline void preempt_conditional_cli(struct pt_regs *regs)
+static inline void conditional_cli_ist(struct pt_regs *regs)
 {
 	if (regs->flags & X86_EFLAGS_IF)
 		local_irq_disable();
+#ifdef CONFIG_X86_64
 	dec_preempt_count();
+#endif
 }
 
 static void __kprobes
@@ -333,9 +347,9 @@
 		return;
 #endif
 
-	preempt_conditional_sti(regs);
+	conditional_sti_ist(regs);
 	do_trap(X86_TRAP_BP, SIGTRAP, "int3", regs, error_code, NULL);
-	preempt_conditional_cli(regs);
+	conditional_cli_ist(regs);
 }
 
 #ifdef CONFIG_X86_64
@@ -458,12 +472,12 @@
 		return;
 
 	/* It's safe to allow irq's after DR6 has been saved */
-	preempt_conditional_sti(regs);
+	conditional_sti_ist(regs);
 
 	if (regs->flags & X86_VM_MASK) {
 		handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code,
 					X86_TRAP_DB);
-		preempt_conditional_cli(regs);
+		conditional_cli_ist(regs);
 		return;
 	}
 
@@ -482,7 +496,7 @@
 	si_code = get_si_code(tsk->thread.debugreg6);
 	if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp)
 		send_sigtrap(tsk, regs, error_code, si_code);
-	preempt_conditional_cli(regs);
+	conditional_cli_ist(regs);
 
 	return;
 }
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index e4d4a22..50392ee 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -52,10 +52,7 @@
 #include "vsyscall_trace.h"
 
 DEFINE_VVAR(int, vgetcpu_mode);
-DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data) =
-{
-	.lock = __SEQLOCK_UNLOCKED(__vsyscall_gtod_data.lock),
-};
+DEFINE_VVAR(struct vsyscall_gtod_data, vsyscall_gtod_data);
 
 static enum { EMULATE, NATIVE, NONE } vsyscall_mode = NATIVE;
 
@@ -80,20 +77,13 @@
 
 void update_vsyscall_tz(void)
 {
-	unsigned long flags;
-
-	write_seqlock_irqsave(&vsyscall_gtod_data.lock, flags);
-	/* sys_tz has changed */
 	vsyscall_gtod_data.sys_tz = sys_tz;
-	write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags);
 }
 
 void update_vsyscall(struct timespec *wall_time, struct timespec *wtm,
 			struct clocksource *clock, u32 mult)
 {
-	unsigned long flags;
-
-	write_seqlock_irqsave(&vsyscall_gtod_data.lock, flags);
+	write_seqcount_begin(&vsyscall_gtod_data.seq);
 
 	/* copy vsyscall data */
 	vsyscall_gtod_data.clock.vclock_mode	= clock->archdata.vclock_mode;
@@ -106,7 +96,7 @@
 	vsyscall_gtod_data.wall_to_monotonic	= *wtm;
 	vsyscall_gtod_data.wall_time_coarse	= __current_kernel_time();
 
-	write_sequnlock_irqrestore(&vsyscall_gtod_data.lock, flags);
+	write_seqcount_end(&vsyscall_gtod_data.seq);
 }
 
 static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 055cc49..7198be0 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -679,8 +679,38 @@
 				   apic->divide_count);
 }
 
+
+static enum hrtimer_restart apic_timer_fn(struct hrtimer *data);
+
+static void apic_timer_expired(struct hrtimer *data)
+{
+	int ret, i = 0;
+	enum hrtimer_restart r;
+	struct kvm_timer *ktimer = container_of(data, struct kvm_timer, timer);
+
+	r = apic_timer_fn(data);
+
+	if (r == HRTIMER_RESTART) {
+		do {
+			ret = hrtimer_start_expires(data, HRTIMER_MODE_ABS);
+			if (ret == -ETIME)
+				hrtimer_add_expires_ns(&ktimer->timer,
+							ktimer->period);
+			i++;
+		} while (ret == -ETIME && i < 10);
+
+		if (ret == -ETIME) {
+			printk_once(KERN_ERR "%s: failed to reprogram timer\n",
+			       __func__);
+			WARN_ON_ONCE(1);
+		}
+	}
+}
+
+
 static void start_apic_timer(struct kvm_lapic *apic)
 {
+	int ret;
 	ktime_t now;
 	atomic_set(&apic->lapic_timer.pending, 0);
 
@@ -710,9 +740,11 @@
 			}
 		}
 
-		hrtimer_start(&apic->lapic_timer.timer,
+		ret = hrtimer_start(&apic->lapic_timer.timer,
 			      ktime_add_ns(now, apic->lapic_timer.period),
 			      HRTIMER_MODE_ABS);
+		if (ret == -ETIME)
+			apic_timer_expired(&apic->lapic_timer.timer);
 
 		apic_debug("%s: bus cycle is %" PRId64 "ns, now 0x%016"
 			   PRIx64 ", "
@@ -742,8 +774,10 @@
 			ns = (tscdeadline - guest_tsc) * 1000000ULL;
 			do_div(ns, this_tsc_khz);
 		}
-		hrtimer_start(&apic->lapic_timer.timer,
+		ret = hrtimer_start(&apic->lapic_timer.timer,
 			ktime_add_ns(now, ns), HRTIMER_MODE_ABS);
+		if (ret == -ETIME)
+			apic_timer_expired(&apic->lapic_timer.timer);
 
 		local_irq_restore(flags);
 	}
@@ -1173,6 +1207,7 @@
 	hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC,
 		     HRTIMER_MODE_ABS);
 	apic->lapic_timer.timer.function = kvm_timer_fn;
+	apic->lapic_timer.timer.irqsafe = 1;
 	apic->lapic_timer.t_ops = &lapic_timer_ops;
 	apic->lapic_timer.kvm = vcpu->kvm;
 	apic->lapic_timer.vcpu = vcpu;
@@ -1270,7 +1305,8 @@
 
 	timer = &apic->lapic_timer.timer;
 	if (hrtimer_cancel(timer))
-		hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
+		if (hrtimer_start_expires(timer, HRTIMER_MODE_ABS) == -ETIME)
+			apic_timer_expired(timer);
 }
 
 void kvm_lapic_sync_from_vapic(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index bb179cc..03cd705 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5231,6 +5231,13 @@
 		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;
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 351590e..151d957 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1090,7 +1090,7 @@
 	 * If we're in an interrupt, have no user context or are running
 	 * in an atomic region then we must not take the fault:
 	 */
-	if (unlikely(in_atomic() || !mm)) {
+	if (unlikely(!mm || pagefault_disabled())) {
 		bad_area_nosemaphore(regs, error_code, address);
 		return;
 	}
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index f4f29b1..71bd7d6 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -43,7 +43,7 @@
 	type = kmap_atomic_idx_push();
 	idx = type + KM_TYPE_NR*smp_processor_id();
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-	BUG_ON(!pte_none(*(kmap_pte-idx)));
+	WARN_ON(!pte_none(*(kmap_pte-idx)));
 	set_pte(kmap_pte-idx, mk_pte(page, prot));
 	arch_flush_lazy_mmu_mode();
 
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 29a69550..2e9a93f 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -39,7 +39,7 @@
 static int timeout_us;
 static int nobau;
 static int baudisabled;
-static spinlock_t disable_lock;
+static raw_spinlock_t disable_lock;
 static cycles_t congested_cycles;
 
 /* tunables: */
@@ -545,7 +545,7 @@
 	cycles_t ttm;
 
 	stat->s_uv2_wars++;
-	spin_lock(&hmaster->uvhub_lock);
+	raw_spin_lock(&hmaster->uvhub_lock);
 	/* try for the original first */
 	if (busy_one != normal) {
 		if (!normal_busy(bcp))
@@ -595,12 +595,12 @@
 		 * free up.
 		 */
 		stat->s_uv2_war_waits++;
-		spin_unlock(&hmaster->uvhub_lock);
+		raw_spin_unlock(&hmaster->uvhub_lock);
 		ttm = get_cycles();
 		do {
 			cpu_relax();
 		} while (normal_busy(bcp));
-		spin_lock(&hmaster->uvhub_lock);
+		raw_spin_lock(&hmaster->uvhub_lock);
 		/* switch to the original descriptor */
 		bcp->using_desc = normal;
 		bau_desc_old = bcp->descriptor_base;
@@ -610,7 +610,7 @@
 		bau_desc_new += (ITEMS_PER_DESC * normal);
 		*bau_desc_new = *bau_desc_old; /* copy the entire descriptor */
 	}
-	spin_unlock(&hmaster->uvhub_lock);
+	raw_spin_unlock(&hmaster->uvhub_lock);
 	return FLUSH_RETRY_BUSYBUG;
 }
 
@@ -732,9 +732,9 @@
 
 		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);
 
@@ -754,9 +754,9 @@
 
 		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);
 
@@ -773,7 +773,7 @@
 					struct ptc_stats *stat)
 {
 	/* let only one cpu do this disabling */
-	spin_lock(&disable_lock);
+	raw_spin_lock(&disable_lock);
 
 	if (!baudisabled && bcp->period_requests &&
 	    ((bcp->period_time / bcp->period_requests) > congested_cycles)) {
@@ -792,7 +792,7 @@
 		}
 	}
 
-	spin_unlock(&disable_lock);
+	raw_spin_unlock(&disable_lock);
 }
 
 static void count_max_concurr(int stat, struct bau_control *bcp,
@@ -841,7 +841,7 @@
  */
 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;
@@ -1859,8 +1859,8 @@
 		bcp->cong_reps			= congested_reps;
 		bcp->cong_period		= congested_period;
 		bcp->clocks_per_100_usec =	usec_2_cycles(100);
-		spin_lock_init(&bcp->queue_lock);
-		spin_lock_init(&bcp->uvhub_lock);
+		raw_spin_lock_init(&bcp->queue_lock);
+		raw_spin_lock_init(&bcp->uvhub_lock);
 	}
 }
 
@@ -2087,7 +2087,7 @@
 	}
 
 	nuvhubs = uv_num_possible_blades();
-	spin_lock_init(&disable_lock);
+	raw_spin_lock_init(&disable_lock);
 	congested_cycles = usec_2_cycles(congested_respns_us);
 
 	uv_base_pnode = 0x7fffffff;
diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c
index 9f29a01..d2e2f23 100644
--- a/arch/x86/platform/uv/uv_time.c
+++ b/arch/x86/platform/uv/uv_time.c
@@ -58,7 +58,7 @@
 
 /* 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: */
@@ -178,7 +178,7 @@
 				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;
@@ -232,7 +232,7 @@
 	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;
@@ -244,12 +244,12 @@
 		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;
 }
 
@@ -268,7 +268,7 @@
 	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;
@@ -280,7 +280,7 @@
 			uv_rtc_find_next_timer(head, pnode);
 	}
 
-	spin_unlock_irqrestore(&head->lock, flags);
+	raw_spin_unlock_irqrestore(&head->lock, flags);
 
 	return rc;
 }
@@ -300,13 +300,18 @@
 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/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index 6bc0e72..d8511fb 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -86,11 +86,11 @@
 {
 	unsigned long seq, ns;
 	do {
-		seq = read_seqbegin(&gtod->lock);
+		seq = read_seqcount_begin(&gtod->seq);
 		ts->tv_sec = gtod->wall_time_sec;
 		ts->tv_nsec = gtod->wall_time_nsec;
 		ns = vgetns();
-	} while (unlikely(read_seqretry(&gtod->lock, seq)));
+	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
 	timespec_add_ns(ts, ns);
 	return 0;
 }
@@ -99,12 +99,12 @@
 {
 	unsigned long seq, ns, secs;
 	do {
-		seq = read_seqbegin(&gtod->lock);
+		seq = read_seqcount_begin(&gtod->seq);
 		secs = gtod->wall_time_sec;
 		ns = gtod->wall_time_nsec + vgetns();
 		secs += gtod->wall_to_monotonic.tv_sec;
 		ns += gtod->wall_to_monotonic.tv_nsec;
-	} while (unlikely(read_seqretry(&gtod->lock, seq)));
+	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
 
 	/* wall_time_nsec, vgetns(), and wall_to_monotonic.tv_nsec
 	 * are all guaranteed to be nonnegative.
@@ -123,10 +123,10 @@
 {
 	unsigned long seq;
 	do {
-		seq = read_seqbegin(&gtod->lock);
+		seq = read_seqcount_begin(&gtod->seq);
 		ts->tv_sec = gtod->wall_time_coarse.tv_sec;
 		ts->tv_nsec = gtod->wall_time_coarse.tv_nsec;
-	} while (unlikely(read_seqretry(&gtod->lock, seq)));
+	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
 	return 0;
 }
 
@@ -134,12 +134,12 @@
 {
 	unsigned long seq, ns, secs;
 	do {
-		seq = read_seqbegin(&gtod->lock);
+		seq = read_seqcount_begin(&gtod->seq);
 		secs = gtod->wall_time_coarse.tv_sec;
 		ns = gtod->wall_time_coarse.tv_nsec;
 		secs += gtod->wall_to_monotonic.tv_sec;
 		ns += gtod->wall_to_monotonic.tv_nsec;
-	} while (unlikely(read_seqretry(&gtod->lock, seq)));
+	} while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
 
 	/* wall_time_nsec and wall_to_monotonic.tv_nsec are
 	 * guaranteed to be between 0 and NSEC_PER_SEC.
diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c
index 47041e7..2c90047 100644
--- a/arch/xtensa/kernel/process.c
+++ b/arch/xtensa/kernel/process.c
@@ -113,9 +113,7 @@
 	while (1) {
 		while (!need_resched())
 			platform_idle();
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 	}
 }
 
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index 4439a1d..e1cdf65 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -57,7 +57,7 @@
 	/* If we're in an interrupt or have no user
 	 * context, we must not take the fault..
 	 */
-	if (in_atomic() || !mm) {
+	if (!mm || pagefault_disabled()) {
 		bad_page_fault(regs, address, SIGSEGV);
 		return;
 	}
diff --git a/block/blk-core.c b/block/blk-core.c
index ec494ff..6795c54 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -235,7 +235,7 @@
  **/
 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);
@@ -300,7 +300,11 @@
 {
 	if (unlikely(blk_queue_stopped(q)))
 		return;
-
+	/*
+	 * q->request_fn() can drop q->queue_lock and reenable
+	 * interrupts, but must return with q->queue_lock held and
+	 * interrupts disabled.
+	 */
 	q->request_fn(q);
 }
 EXPORT_SYMBOL(__blk_run_queue);
@@ -2747,11 +2751,11 @@
 	 * this lock).
 	 */
 	if (from_schedule) {
-		spin_unlock(q->queue_lock);
+		spin_unlock_irq(q->queue_lock);
 		blk_run_queue_async(q);
 	} else {
 		__blk_run_queue(q);
-		spin_unlock(q->queue_lock);
+		spin_unlock_irq(q->queue_lock);
 	}
 
 }
@@ -2777,7 +2781,6 @@
 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;
@@ -2798,11 +2801,6 @@
 	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);
@@ -2815,7 +2813,7 @@
 				queue_unplugged(q, depth, from_schedule);
 			q = rq->q;
 			depth = 0;
-			spin_lock(q->queue_lock);
+			spin_lock_irq(q->queue_lock);
 		}
 		/*
 		 * rq is already accounted, so use raw insert
@@ -2833,8 +2831,6 @@
 	 */
 	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-iopoll.c b/block/blk-iopoll.c
index 58916af..f7ca9b4 100644
--- a/block/blk-iopoll.c
+++ b/block/blk-iopoll.c
@@ -38,6 +38,7 @@
 	list_add_tail(&iop->list, &__get_cpu_var(blk_cpu_iopoll));
 	__raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
 	local_irq_restore(flags);
+	preempt_check_resched_rt();
 }
 EXPORT_SYMBOL(blk_iopoll_sched);
 
@@ -135,6 +136,7 @@
 		__raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
 
 	local_irq_enable();
+	preempt_check_resched_rt();
 }
 
 /**
@@ -204,6 +206,7 @@
 				 &__get_cpu_var(blk_cpu_iopoll));
 		__raise_softirq_irqoff(BLOCK_IOPOLL_SOFTIRQ);
 		local_irq_enable();
+		preempt_check_resched_rt();
 	}
 
 	return NOTIFY_OK;
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index 1366a89..60a88ab 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -50,6 +50,7 @@
 		raise_softirq_irqoff(BLOCK_SOFTIRQ);
 
 	local_irq_restore(flags);
+	preempt_check_resched_rt();
 }
 
 /*
@@ -92,6 +93,7 @@
 				 &__get_cpu_var(blk_cpu_done));
 		raise_softirq_irqoff(BLOCK_SOFTIRQ);
 		local_irq_enable();
+		preempt_check_resched_rt();
 	}
 
 	return NOTIFY_OK;
@@ -150,6 +152,7 @@
 		goto do_local;
 
 	local_irq_restore(flags);
+	preempt_check_resched_rt();
 }
 
 /**
diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h
index 76dc02f1..ca6bbe7 100644
--- a/drivers/acpi/acpica/acglobal.h
+++ b/drivers/acpi/acpica/acglobal.h
@@ -236,7 +236,7 @@
  * interrupt level
  */
 ACPI_EXTERN acpi_spinlock acpi_gbl_gpe_lock;	/* For GPE data structs and registers */
-ACPI_EXTERN acpi_spinlock acpi_gbl_hardware_lock;	/* For ACPI H/W except GPE registers */
+ACPI_EXTERN acpi_raw_spinlock acpi_gbl_hardware_lock;	/* For ACPI H/W except GPE registers */
 
 /*****************************************************************************
  *
diff --git a/drivers/acpi/acpica/hwregs.c b/drivers/acpi/acpica/hwregs.c
index cc70f3f..1df2ce6 100644
--- a/drivers/acpi/acpica/hwregs.c
+++ b/drivers/acpi/acpica/hwregs.c
@@ -263,14 +263,14 @@
 			  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 c2793a8..5b28769 100644
--- a/drivers/acpi/acpica/hwxface.c
+++ b/drivers/acpi/acpica/hwxface.c
@@ -387,7 +387,7 @@
 		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
@@ -448,7 +448,7 @@
 
 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 7d797e2..b611bf3 100644
--- a/drivers/acpi/acpica/utmutex.c
+++ b/drivers/acpi/acpica/utmutex.c
@@ -88,7 +88,7 @@
 		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);
 	}
@@ -135,7 +135,7 @@
 	/* 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);
 
 	/* Delete the reader/writer lock */
 
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index 22edc92..e73dc2d 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -678,9 +678,9 @@
 	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 @@
 		unsigned long flags;
 
 		/* FIXME: use a bounce buffer */
-		local_irq_save(flags);
+		local_irq_save_nort(flags);
 		buf = kmap_atomic(page, KM_IRQ0);
 
 		/* do the actual data transfer */
@@ -727,7 +727,7 @@
 				       do_write);
 
 		kunmap_atomic(buf, KM_IRQ0);
-		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 @@
 		unsigned long flags;
 
 		/* FIXME: use bounce buffer */
-		local_irq_save(flags);
+		local_irq_save_nort(flags);
 		buf = kmap_atomic(page, KM_IRQ0);
 
 		/* do the actual data transfer */
@@ -872,7 +872,7 @@
 								count, rw);
 
 		kunmap_atomic(buf, KM_IRQ0);
-		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/char/random.c b/drivers/char/random.c
index edf45ae..ba79a0f 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -445,7 +445,7 @@
 	.poolinfo = &poolinfo_table[0],
 	.name = "input",
 	.limit = 1,
-	.lock = __SPIN_LOCK_UNLOCKED(&input_pool.lock),
+	.lock = __SPIN_LOCK_UNLOCKED(input_pool.lock),
 	.pool = input_pool_data
 };
 
@@ -454,7 +454,7 @@
 	.name = "blocking",
 	.limit = 1,
 	.pull = &input_pool,
-	.lock = __SPIN_LOCK_UNLOCKED(&blocking_pool.lock),
+	.lock = __SPIN_LOCK_UNLOCKED(blocking_pool.lock),
 	.pool = blocking_pool_data
 };
 
@@ -462,7 +462,7 @@
 	.poolinfo = &poolinfo_table[1],
 	.name = "nonblocking",
 	.pull = &input_pool,
-	.lock = __SPIN_LOCK_UNLOCKED(&nonblocking_pool.lock),
+	.lock = __SPIN_LOCK_UNLOCKED(nonblocking_pool.lock),
 	.pool = nonblocking_pool_data
 };
 
@@ -701,8 +701,11 @@
 	preempt_disable();
 	/* if over the trickle threshold, use only 1 in 4096 samples */
 	if (input_pool.entropy_count > trickle_thresh &&
-	    ((__this_cpu_inc_return(trickle_count) - 1) & 0xfff))
-		goto out;
+	    ((__this_cpu_inc_return(trickle_count) - 1) & 0xfff)) {
+		preempt_enable();
+		return;
+	}
+	preempt_enable();
 
 	sample.jiffies = jiffies;
 	sample.cycles = random_get_entropy();
@@ -744,8 +747,6 @@
 		credit_entropy_bits(&input_pool,
 				    min_t(int, fls(delta>>1), 11));
 	}
-out:
-	preempt_enable();
 }
 
 void add_input_randomness(unsigned int type, unsigned int code,
@@ -766,18 +767,16 @@
 
 static DEFINE_PER_CPU(struct fast_pool, irq_randomness);
 
-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 = &__get_cpu_var(irq_randomness);
-	struct pt_regs		*regs = get_irq_regs();
 	unsigned long		now = jiffies;
 	__u32			input[4], cycles = random_get_entropy();
 
 	input[0] = cycles ^ jiffies;
 	input[1] = irq;
-	if (regs) {
-		__u64 ip = instruction_pointer(regs);
+	if (ip) {
 		input[2] = ip;
 		input[3] = ip >> 32;
 	}
@@ -791,7 +790,11 @@
 	fast_pool->last = now;
 
 	r = nonblocking_pool.initialized ? &input_pool : &nonblocking_pool;
+#ifndef CONFIG_PREEMPT_RT_FULL
 	__mix_pool_bytes(r, &fast_pool->pool, sizeof(fast_pool->pool), NULL);
+#else
+	mix_pool_bytes(r, &fast_pool->pool, sizeof(fast_pool->pool), NULL);
+#endif
 	/*
 	 * If we don't have a valid cycle counter, and we see
 	 * back-to-back timer interrupts, then skip giving credit for
diff --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c
index 79c47e8..8976b3d 100644
--- a/drivers/clocksource/tcb_clksrc.c
+++ b/drivers/clocksource/tcb_clksrc.c
@@ -21,8 +21,7 @@
  *     resolution better than 200 nsec).
  *
  *   - 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
@@ -68,6 +67,7 @@
 struct tc_clkevt_device {
 	struct clock_event_device	clkevt;
 	struct clk			*clk;
+	u32				freq;
 	void __iomem			*regs;
 };
 
@@ -76,13 +76,6 @@
 	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_mode(enum clock_event_mode m, struct clock_event_device *d)
@@ -105,11 +98,12 @@
 	case CLOCK_EVT_MODE_PERIODIC:
 		clk_enable(tcd->clk);
 
-		/* 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));
@@ -122,7 +116,7 @@
 	case CLOCK_EVT_MODE_ONESHOT:
 		clk_enable(tcd->clk);
 
-		/* 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));
@@ -152,8 +146,12 @@
 		.features	= CLOCK_EVT_FEAT_PERIODIC
 					| CLOCK_EVT_FEAT_ONESHOT,
 		.shift		= 32,
+#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK
 		/* Should be lower than at91rm9200's system timer */
 		.rating		= 125,
+#else
+		.rating		= 200,
+#endif
 		.set_next_event	= tc_next_event,
 		.set_mode	= tc_mode,
 	},
@@ -179,8 +177,9 @@
 	.handler	= ch2_irq,
 };
 
-static void __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx)
+static void __init setup_clkevents(struct atmel_tc *tc, int divisor_idx)
 {
+	unsigned divisor = atmel_tc_divisors[divisor_idx];
 	struct clk *t2_clk = tc->clk[2];
 	int irq = tc->irq[2];
 
@@ -188,11 +187,17 @@
 	clkevt.clk = t2_clk;
 	tc_irqaction.dev_id = &clkevt;
 
-	timer_clock = clk32k_divisor_idx;
+	timer_clock = divisor_idx;
 
-	clkevt.clkevt.mult = div_sc(32768, NSEC_PER_SEC, clkevt.clkevt.shift);
-	clkevt.clkevt.max_delta_ns
-		= clockevent_delta2ns(0xffff, &clkevt.clkevt);
+	if (!divisor)
+		clkevt.freq = 32768;
+	else
+		clkevt.freq = clk_get_rate(t2_clk)/divisor;
+
+	clkevt.clkevt.mult = div_sc(clkevt.freq, NSEC_PER_SEC,
+				    clkevt.clkevt.shift);
+	clkevt.clkevt.max_delta_ns =
+		clockevent_delta2ns(0xffff, &clkevt.clkevt);
 	clkevt.clkevt.min_delta_ns = clockevent_delta2ns(1, &clkevt.clkevt) + 1;
 	clkevt.clkevt.cpumask = cpumask_of(0);
 
@@ -295,8 +300,11 @@
 	clocksource_register(&clksrc);
 
 	/* channel 2:  periodic and oneshot timer support */
+#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK
 	setup_clkevents(tc, clk32k_divisor_idx);
-
+#else
+	setup_clkevents(tc, best_divisor_idx);
+#endif
 	return 0;
 }
 arch_initcall(tcb_clksrc_init);
diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index a6c10e8..e4d11e4 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -46,7 +46,7 @@
 	u32 saved_risingdetect;
 	u32 level_mask;
 	u32 toggle_mask;
-	spinlock_t lock;
+	raw_spinlock_t lock;
 	struct gpio_chip chip;
 	struct clk *dbck;
 	u32 mod_usage;
@@ -418,9 +418,9 @@
 		return -EINVAL;
 
 	bank = irq_data_get_irq_chip_data(d);
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	retval = _set_gpio_triggering(bank, GPIO_INDEX(bank, gpio), type);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 
 	if (type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
 		__irq_set_handler_locked(d->irq, handle_level_irq);
@@ -533,13 +533,13 @@
 		return -EINVAL;
 	}
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	if (enable)
 		bank->suspend_wakeup |= gpio_bit;
 	else
 		bank->suspend_wakeup &= ~gpio_bit;
 
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 
 	return 0;
 }
@@ -570,7 +570,7 @@
 	struct gpio_bank *bank = container_of(chip, struct gpio_bank, chip);
 	unsigned long flags;
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 
 	/* Set trigger to none. You need to enable the desired trigger with
 	 * request_irq() or set_irq_type().
@@ -602,7 +602,7 @@
 		}
 		bank->mod_usage |= 1 << offset;
 	}
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 
 	return 0;
 }
@@ -612,7 +612,7 @@
 	struct gpio_bank *bank = container_of(chip, struct gpio_bank, chip);
 	unsigned long flags;
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 #ifdef CONFIG_ARCH_OMAP16XX
 	if (bank->method == METHOD_GPIO_1610) {
 		/* Disable wake-up during idle for dynamic tick */
@@ -651,7 +651,7 @@
 		}
 	}
 	_reset_gpio(bank, bank->chip.base + offset);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 }
 
 /*
@@ -751,9 +751,9 @@
 	struct gpio_bank *bank = irq_data_get_irq_chip_data(d);
 	unsigned long flags;
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	_reset_gpio(bank, gpio);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 }
 
 static void gpio_ack_irq(struct irq_data *d)
@@ -770,10 +770,10 @@
 	struct gpio_bank *bank = irq_data_get_irq_chip_data(d);
 	unsigned long flags;
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	_set_gpio_irqenable(bank, gpio, 0);
 	_set_gpio_triggering(bank, GPIO_INDEX(bank, gpio), IRQ_TYPE_NONE);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 }
 
 static void gpio_unmask_irq(struct irq_data *d)
@@ -784,7 +784,7 @@
 	u32 trigger = irqd_get_trigger_type(d);
 	unsigned long flags;
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	if (trigger)
 		_set_gpio_triggering(bank, GPIO_INDEX(bank, gpio), trigger);
 
@@ -796,7 +796,7 @@
 	}
 
 	_set_gpio_irqenable(bank, gpio, 1);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 }
 
 static struct irq_chip gpio_irq_chip = {
@@ -827,10 +827,10 @@
 					OMAP_MPUIO_GPIO_MASKIT / bank->stride;
 	unsigned long		flags;
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	bank->saved_wakeup = __raw_readl(mask_reg);
 	__raw_writel(0xffff & ~bank->suspend_wakeup, mask_reg);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 
 	return 0;
 }
@@ -843,9 +843,9 @@
 					OMAP_MPUIO_GPIO_MASKIT / bank->stride;
 	unsigned long		flags;
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	__raw_writel(bank->saved_wakeup, mask_reg);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 
 	return 0;
 }
@@ -904,9 +904,9 @@
 	unsigned long flags;
 
 	bank = container_of(chip, struct gpio_bank, chip);
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	_set_gpio_direction(bank, offset, 1);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 	return 0;
 }
 
@@ -941,10 +941,10 @@
 	unsigned long flags;
 
 	bank = container_of(chip, struct gpio_bank, chip);
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	bank->set_dataout(bank, offset, value);
 	_set_gpio_direction(bank, offset, 0);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 	return 0;
 }
 
@@ -962,9 +962,9 @@
 			dev_err(bank->dev, "Could not get gpio dbck\n");
 	}
 
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	_set_gpio_debounce(bank, offset, debounce);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 
 	return 0;
 }
@@ -975,9 +975,9 @@
 	unsigned long flags;
 
 	bank = container_of(chip, struct gpio_bank, chip);
-	spin_lock_irqsave(&bank->lock, flags);
+	raw_spin_lock_irqsave(&bank->lock, flags);
 	bank->set_dataout(bank, offset, value);
-	spin_unlock_irqrestore(&bank->lock, flags);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
 }
 
 static int gpio_2irq(struct gpio_chip *chip, unsigned offset)
@@ -1207,7 +1207,7 @@
 	else
 		bank->set_dataout = _set_gpio_dataout_mask;
 
-	spin_lock_init(&bank->lock);
+	raw_spin_lock_init(&bank->lock);
 
 	/* Static mapping, never released */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -1276,11 +1276,11 @@
 			continue;
 		}
 
-		spin_lock_irqsave(&bank->lock, flags);
+		raw_spin_lock_irqsave(&bank->lock, flags);
 		bank->saved_wakeup = __raw_readl(wake_status);
 		__raw_writel(0xffffffff, wake_clear);
 		__raw_writel(bank->suspend_wakeup, wake_set);
-		spin_unlock_irqrestore(&bank->lock, flags);
+		raw_spin_unlock_irqrestore(&bank->lock, flags);
 	}
 
 	return 0;
@@ -1322,10 +1322,10 @@
 			continue;
 		}
 
-		spin_lock_irqsave(&bank->lock, flags);
+		raw_spin_lock_irqsave(&bank->lock, flags);
 		__raw_writel(0xffffffff, wake_clear);
 		__raw_writel(bank->saved_wakeup, wake_set);
-		spin_unlock_irqrestore(&bank->lock, flags);
+		raw_spin_unlock_irqrestore(&bank->lock, flags);
 	}
 }
 
diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index 73af885..2b13224 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -619,11 +619,6 @@
 	 * code gets preempted or delayed for some reason.
 	 */
 	for (i = 0; i < DRM_TIMESTAMP_MAXRETRIES; i++) {
-		/* Disable preemption to make it very likely to
-		 * succeed in the first iteration even on PREEMPT_RT kernel.
-		 */
-		preempt_disable();
-
 		/* Get system timestamp before query. */
 		do_gettimeofday(&stime);
 
@@ -633,8 +628,6 @@
 		/* Get system timestamp after query. */
 		do_gettimeofday(&raw_time);
 
-		preempt_enable();
-
 		/* Return as no-op if scanout query unsupported or failed. */
 		if (!(vbl_status & DRM_SCANOUTPOS_VALID)) {
 			DRM_DEBUG("crtc %d : scanoutpos query failed [%d].\n",
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index a0b69ae0..c550529 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1216,7 +1216,9 @@
 		dev_priv->relative_constants_mode = mode;
 	}
 
+#ifndef CONFIG_PREEMPT_RT_BASE
 	trace_i915_gem_ring_dispatch(ring, seqno);
+#endif
 
 	exec_start = batch_obj->gtt_offset + args->batch_start_offset;
 	exec_len = args->batch_len;
diff --git a/drivers/ide/alim15x3.c b/drivers/ide/alim15x3.c
index 2c8016a..6fd6037 100644
--- a/drivers/ide/alim15x3.c
+++ b/drivers/ide/alim15x3.c
@@ -234,7 +234,7 @@
 
 	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 @@
 	}
 	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 58c51cd..d2a4059 100644
--- a/drivers/ide/hpt366.c
+++ b/drivers/ide/hpt366.c
@@ -1241,7 +1241,7 @@
 
 	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 @@
 	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 1976397..4169433 100644
--- a/drivers/ide/ide-io-std.c
+++ b/drivers/ide/ide-io-std.c
@@ -175,7 +175,7 @@
 		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 @@
 			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 @@
 		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 @@
 			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 177db6d..079ae6b 100644
--- a/drivers/ide/ide-io.c
+++ b/drivers/ide/ide-io.c
@@ -659,7 +659,7 @@
 		/* 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 376f2dc..f014dd1 100644
--- a/drivers/ide/ide-iops.c
+++ b/drivers/ide/ide-iops.c
@@ -129,12 +129,12 @@
 				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 068cef0..38e69e1 100644
--- a/drivers/ide/ide-probe.c
+++ b/drivers/ide/ide-probe.c
@@ -196,10 +196,10 @@
 	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 5bc2839..da861a6 100644
--- a/drivers/ide/ide-taskfile.c
+++ b/drivers/ide/ide-taskfile.c
@@ -251,7 +251,7 @@
 
 		page_is_high = PageHighMem(page);
 		if (page_is_high)
-			local_irq_save(flags);
+			local_irq_save_nort(flags);
 
 		buf = kmap_atomic(page, KM_BIO_SRC_IRQ) + offset;
 
@@ -272,7 +272,7 @@
 		kunmap_atomic(buf, KM_BIO_SRC_IRQ);
 
 		if (page_is_high)
-			local_irq_restore(flags);
+			local_irq_restore_nort(flags);
 
 		len -= nr_bytes;
 	}
@@ -415,7 +415,7 @@
 	}
 
 	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/idle/i7300_idle.c b/drivers/idle/i7300_idle.c
index c976285..5537d7c 100644
--- a/drivers/idle/i7300_idle.c
+++ b/drivers/idle/i7300_idle.c
@@ -75,7 +75,7 @@
 
 static struct pci_dev *fbd_dev;
 
-static spinlock_t i7300_idle_lock;
+static raw_spinlock_t i7300_idle_lock;
 static int i7300_idle_active;
 
 static u8 i7300_idle_thrtctl_saved;
@@ -457,7 +457,7 @@
 		idle_begin_time = ktime_get();
 	}
 
-	spin_lock_irqsave(&i7300_idle_lock, flags);
+	raw_spin_lock_irqsave(&i7300_idle_lock, flags);
 	if (val == IDLE_START) {
 
 		cpumask_set_cpu(smp_processor_id(), idle_cpumask);
@@ -506,7 +506,7 @@
 		}
 	}
 end:
-	spin_unlock_irqrestore(&i7300_idle_lock, flags);
+	raw_spin_unlock_irqrestore(&i7300_idle_lock, flags);
 	return 0;
 }
 
@@ -554,7 +554,7 @@
 
 static int __init i7300_idle_init(void)
 {
-	spin_lock_init(&i7300_idle_lock);
+	raw_spin_lock_init(&i7300_idle_lock);
 	total_us = 0;
 
 	if (i7300_idle_platform_probe(&fbd_dev, &ioat_dev, forceload))
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 80799c0..014589a8 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -800,7 +800,7 @@
 
 	ipoib_mcast_stop_thread(dev, 0);
 
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 	netif_addr_lock(dev);
 	spin_lock(&priv->lock);
 
@@ -882,7 +882,7 @@
 
 	spin_unlock(&priv->lock);
 	netif_addr_unlock(dev);
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 
 	/* We have to cancel outside of the spinlock */
 	list_for_each_entry_safe(mcast, tmcast, &remove_list, list) {
diff --git a/drivers/input/gameport/gameport.c b/drivers/input/gameport/gameport.c
index c351aa4..1ecaf60 100644
--- a/drivers/input/gameport/gameport.c
+++ b/drivers/input/gameport/gameport.c
@@ -87,12 +87,12 @@
 	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;
 	}
@@ -111,11 +111,11 @@
 	tx = 1 << 30;
 
 	for(i = 0; i < 50; i++) {
-		local_irq_save(flags);
+		local_irq_save_nort(flags);
 		rdtscl(t1);
 		for (t = 0; t < 50; t++) gameport_read(gameport);
 		rdtscl(t2);
-		local_irq_restore(flags);
+		local_irq_restore_nort(flags);
 		udelay(i * 10);
 		if (t2 - t1 < tx) tx = t2 - t1;
 	}
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index c00bcdc..7a5c0a2 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1676,14 +1676,14 @@
 		if (map_request(ti, clone, md))
 			goto requeued;
 
-		BUG_ON(!irqs_disabled());
+		BUG_ON_NONRT(!irqs_disabled());
 		spin_lock(q->queue_lock);
 	}
 
 	goto out;
 
 requeued:
-	BUG_ON(!irqs_disabled());
+	BUG_ON_NONRT(!irqs_disabled());
 	spin_lock(q->queue_lock);
 
 delay_and_out:
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 6056ee7..10fbba8 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -1253,8 +1253,9 @@
 	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++;
@@ -1306,7 +1307,8 @@
 			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();
 }
 
 #ifdef CONFIG_MULTICORE_RAID456
@@ -4465,8 +4467,10 @@
 {
 	if (conf->level == 6 && !percpu->spare_page)
 		percpu->spare_page = alloc_page(GFP_KERNEL);
-	if (!percpu->scribble)
+	if (!percpu->scribble) {
 		percpu->scribble = kmalloc(conf->scribble_len, GFP_KERNEL);
+		spin_lock_init(&percpu->lock);
+	}
 
 	if (!percpu->scribble || (conf->level == 6 && !percpu->spare_page)) {
 		free_scratch_buffer(conf, percpu);
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index e10c553..010a969 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -405,6 +405,7 @@
 	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 */
 		void		*scribble;   /* space for constructing buffer
 					      * lists and performing address
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index 5664696..951ae6c 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -82,6 +82,7 @@
 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
@@ -97,8 +98,7 @@
 	  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
@@ -112,6 +112,14 @@
 	  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 IBM_ASM
 	tristate "Device driver for IBM RSA service processor"
 	depends on X86 && PCI && INPUT && EXPERIMENTAL
@@ -133,6 +141,35 @@
 	  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 b26495a..84c4554 100644
--- a/drivers/misc/Makefile
+++ b/drivers/misc/Makefile
@@ -48,3 +48,4 @@
 obj-y				+= carma/
 obj-$(CONFIG_USB_SWITCH_FSA9480) += fsa9480.o
 obj-$(CONFIG_ALTERA_STAPL)	+=altera-stapl/
+obj-$(CONFIG_HWLAT_DETECTOR)	+= hwlat_detector.o
diff --git a/drivers/misc/hwlat_detector.c b/drivers/misc/hwlat_detector.c
new file mode 100644
index 0000000..d2676b8
--- /dev/null
+++ b/drivers/misc/hwlat_detector.c
@@ -0,0 +1,1239 @@
+/*
+ * 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 the outer loop (t2 to next t1) */
+			diff = time_to_us(time_sub(t1, last_t2));
+			/* This shouldn't happen */
+			if (diff < 0) {
+				printk(KERN_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) {
+			printk(KERN_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)) {
+		printk(KERN_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 = strict_strtoull(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 = strict_strtoul(buf, 10, &val);
+	if (0 != 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) {
+			printk(KERN_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 = strict_strtoull(buf, 10, &val);
+	if (0 != 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 = strict_strtoull(buf, 10, &val);
+	if (0 != 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;
+
+	printk(KERN_INFO BANNER "version %s\n", VERSION);
+
+	ret = init_stats();
+	if (0 != ret)
+		goto out;
+
+	ret = init_debugfs();
+	if (0 != 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)
+			printk(KERN_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 0726e59..5d7bf83 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -859,15 +859,12 @@
 	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;
@@ -907,8 +904,6 @@
 
 	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/Kconfig b/drivers/net/Kconfig
index 61d3d1f..226e40d 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -155,6 +155,7 @@
 
 config NETCONSOLE
 	tristate "Network console logging support"
+	depends on !PREEMPT_RT_FULL
 	---help---
 	If you want to log kernel messages over the network, enable this.
 	See <file:Documentation/networking/netconsole.txt> for details.
diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c
index efc9dee..2500aa4 100644
--- a/drivers/net/ethernet/3com/3c59x.c
+++ b/drivers/net/ethernet/3com/3c59x.c
@@ -842,9 +842,9 @@
 {
 	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
 
@@ -1921,12 +1921,12 @@
 			 * 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 5ae7df7..9500316 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -2235,11 +2235,7 @@
 	}
 
 	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 87851f0..9704ef6 100644
--- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
+++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c
@@ -1858,8 +1858,7 @@
 		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/cadence/at91_ether.c b/drivers/net/ethernet/cadence/at91_ether.c
index 56624d3..ad4dbea 100644
--- a/drivers/net/ethernet/cadence/at91_ether.c
+++ b/drivers/net/ethernet/cadence/at91_ether.c
@@ -200,7 +200,9 @@
 	struct net_device *dev = (struct net_device *) dev_id;
 	struct at91_private *lp = netdev_priv(dev);
 	unsigned int phy;
+	unsigned long flags;
 
+	spin_lock_irqsave(&lp->lock, flags);
 	/*
 	 * This hander is triggered on both edges, but the PHY chips expect
 	 * level-triggering.  We therefore have to check if the PHY actually has
@@ -242,6 +244,7 @@
 
 done:
 	disable_mdi();
+	spin_unlock_irqrestore(&lp->lock, flags);
 
 	return IRQ_HANDLED;
 }
@@ -398,9 +401,11 @@
 	struct net_device *dev = (struct net_device *) dev_id;
 	struct at91_private *lp = netdev_priv(dev);
 
+	spin_lock_irq(&lp->lock);
 	enable_mdi();
 	update_linkspeed(dev, 1);
 	disable_mdi();
+	spin_unlock_irq(&lp->lock);
 
 	mod_timer(&lp->check_timer, jiffies + LINK_POLL_INTERVAL);
 }
diff --git a/drivers/net/ethernet/chelsio/cxgb/sge.c b/drivers/net/ethernet/chelsio/cxgb/sge.c
index f9b6023..6d7412a 100644
--- a/drivers/net/ethernet/chelsio/cxgb/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb/sge.c
@@ -1678,8 +1678,7 @@
 	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/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c
index 9656dd0..ef7df09 100644
--- a/drivers/net/ethernet/dec/tulip/tulip_core.c
+++ b/drivers/net/ethernet/dec/tulip/tulip_core.c
@@ -1949,6 +1949,7 @@
 	pci_iounmap(pdev, tp->base_addr);
 	free_netdev (dev);
 	pci_release_regions (pdev);
+	pci_disable_device (pdev);
 	pci_set_drvdata (pdev, NULL);
 
 	/* pci_power_off (pdev, -1); */
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index b167e38..704b8e0e 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -1285,7 +1285,7 @@
 
 	if (netif_running(ndev)) {
 
-		local_irq_save(flags);
+		local_irq_save_nort(flags);
 		lock_tx_qs(priv);
 		lock_rx_qs(priv);
 
@@ -1303,7 +1303,7 @@
 
 		unlock_rx_qs(priv);
 		unlock_tx_qs(priv);
-		local_irq_restore(flags);
+		local_irq_restore_nort(flags);
 
 		disable_napi(priv);
 
@@ -1344,7 +1344,7 @@
 	/* Disable Magic Packet mode, in case something
 	 * else woke us up.
 	 */
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 	lock_tx_qs(priv);
 	lock_rx_qs(priv);
 
@@ -1356,7 +1356,7 @@
 
 	unlock_rx_qs(priv);
 	unlock_tx_qs(priv);
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 
 	netif_device_attach(ndev);
 
@@ -1680,7 +1680,7 @@
 
 
 	/* Lock it down */
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 	lock_tx_qs(priv);
 	lock_rx_qs(priv);
 
@@ -1688,7 +1688,7 @@
 
 	unlock_rx_qs(priv);
 	unlock_tx_qs(priv);
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 
 	/* Free the IRQs */
 	if (priv->device_flags & FSL_GIANFAR_DEV_HAS_MULTI_INTR) {
@@ -2323,7 +2323,7 @@
 	u32 tempval;
 
 	regs = priv->gfargrp[0].regs;
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 	lock_rx_qs(priv);
 
 	if (features & NETIF_F_HW_VLAN_TX) {
@@ -2355,7 +2355,7 @@
 	gfar_change_mtu(dev, dev->mtu);
 
 	unlock_rx_qs(priv);
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 }
 
 static int gfar_change_mtu(struct net_device *dev, int new_mtu)
@@ -2958,7 +2958,7 @@
 	struct phy_device *phydev = priv->phydev;
 	int new_state = 0;
 
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 	lock_tx_qs(priv);
 
 	if (phydev->link) {
@@ -3025,7 +3025,7 @@
 	if (new_state && netif_msg_link(priv))
 		phy_print_status(phydev);
 	unlock_tx_qs(priv);
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 }
 
 /* Update the hash table based on the current list of multicast
@@ -3225,14 +3225,14 @@
 			dev->stats.tx_dropped++;
 			priv->extra_stats.tx_underrun++;
 
-			local_irq_save(flags);
+			local_irq_save_nort(flags);
 			lock_tx_qs(priv);
 
 			/* Reactivate the Tx Queues */
 			gfar_write(&regs->tstat, gfargrp->tstat);
 
 			unlock_tx_qs(priv);
-			local_irq_restore(flags);
+			local_irq_restore_nort(flags);
 		}
 		netif_dbg(priv, tx_err, dev, "Transmit Error\n");
 	}
diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c
index 212736b..1fe331f 100644
--- a/drivers/net/ethernet/freescale/gianfar_ethtool.c
+++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c
@@ -486,7 +486,7 @@
 
 		/* Halt TX and RX, and process the frames which
 		 * have already been received */
-		local_irq_save(flags);
+		local_irq_save_nort(flags);
 		lock_tx_qs(priv);
 		lock_rx_qs(priv);
 
@@ -494,7 +494,7 @@
 
 		unlock_rx_qs(priv);
 		unlock_tx_qs(priv);
-		local_irq_restore(flags);
+		local_irq_restore_nort(flags);
 
 		for (i = 0; i < priv->num_rx_queues; i++)
 			gfar_clean_rx_ring(priv->rx_queue[i],
@@ -535,7 +535,7 @@
 	if (dev->flags & IFF_UP) {
 		/* Halt TX and RX, and process the frames which
 		 * have already been received */
-		local_irq_save(flags);
+		local_irq_save_nort(flags);
 		lock_tx_qs(priv);
 		lock_rx_qs(priv);
 
@@ -543,7 +543,7 @@
 
 		unlock_tx_qs(priv);
 		unlock_rx_qs(priv);
-		local_irq_restore(flags);
+		local_irq_restore_nort(flags);
 
 		for (i = 0; i < priv->num_rx_queues; i++)
 			gfar_clean_rx_ring(priv->rx_queue[i],
diff --git a/drivers/net/ethernet/freescale/gianfar_sysfs.c b/drivers/net/ethernet/freescale/gianfar_sysfs.c
index 64f4094..9f6fb3a 100644
--- a/drivers/net/ethernet/freescale/gianfar_sysfs.c
+++ b/drivers/net/ethernet/freescale/gianfar_sysfs.c
@@ -68,7 +68,7 @@
 		return count;
 
 
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 	lock_rx_qs(priv);
 
 	/* Set the new stashing value */
@@ -84,7 +84,7 @@
 	gfar_write(&regs->attr, temp);
 
 	unlock_rx_qs(priv);
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 
 	return count;
 }
@@ -112,7 +112,7 @@
 	if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_BUF_STASHING))
 		return count;
 
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 	lock_rx_qs(priv);
 
 	if (length > priv->rx_buffer_size)
@@ -140,7 +140,7 @@
 
 out:
 	unlock_rx_qs(priv);
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 
 	return count;
 }
@@ -171,7 +171,7 @@
 	if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_BUF_STASHING))
 		return count;
 
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 	lock_rx_qs(priv);
 
 	if (index > priv->rx_stash_size)
@@ -189,7 +189,7 @@
 
 out:
 	unlock_rx_qs(priv);
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 
 	return count;
 }
@@ -219,7 +219,7 @@
 	if (length > GFAR_MAX_FIFO_THRESHOLD)
 		return count;
 
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 	lock_tx_qs(priv);
 
 	priv->fifo_threshold = length;
@@ -230,7 +230,7 @@
 	gfar_write(&regs->fifo_tx_thr, temp);
 
 	unlock_tx_qs(priv);
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 
 	return count;
 }
@@ -259,7 +259,7 @@
 	if (num > GFAR_MAX_FIFO_STARVE)
 		return count;
 
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 	lock_tx_qs(priv);
 
 	priv->fifo_starve = num;
@@ -270,7 +270,7 @@
 	gfar_write(&regs->fifo_tx_starve, temp);
 
 	unlock_tx_qs(priv);
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 
 	return count;
 }
@@ -300,7 +300,7 @@
 	if (num > GFAR_MAX_FIFO_STARVE_OFF)
 		return count;
 
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 	lock_tx_qs(priv);
 
 	priv->fifo_starve_off = num;
@@ -311,7 +311,7 @@
 	gfar_write(&regs->fifo_tx_starve_shutoff, temp);
 
 	unlock_tx_qs(priv);
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 
 	return count;
 }
diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c
index 297f0b6..114bee9 100644
--- a/drivers/net/ethernet/ibm/ehea/ehea_main.c
+++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c
@@ -1304,7 +1304,7 @@
 			 "%s-queue%d", dev->name, i);
 		ret = ibmebus_request_irq(pr->eq->attr.ist1,
 					  ehea_recv_irq_handler,
-					  IRQF_DISABLED, pr->int_send_name,
+					  IRQF_NO_THREAD, pr->int_send_name,
 					  pr);
 		if (ret) {
 			netdev_err(dev, "failed registering irq for ehea_queue port_res_nr:%d, ist=%X\n",
diff --git a/drivers/net/ethernet/neterion/s2io.c b/drivers/net/ethernet/neterion/s2io.c
index c27fb3d..4624278 100644
--- a/drivers/net/ethernet/neterion/s2io.c
+++ b/drivers/net/ethernet/neterion/s2io.c
@@ -4090,12 +4090,7 @@
 			[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 495d65c..6b2a684 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
@@ -1937,10 +1937,9 @@
 		adapter->stats.tx_length_errors++;
 		return NETDEV_TX_OK;
 	}
-	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 728805f..274cb0a 100644
--- a/drivers/net/ethernet/realtek/8139too.c
+++ b/drivers/net/ethernet/realtek/8139too.c
@@ -2174,7 +2174,7 @@
  */
 static void rtl8139_poll_controller(struct net_device *dev)
 {
-	disable_irq(dev->irq);
+	disable_irq_nosync(dev->irq);
 	rtl8139_interrupt(dev->irq, dev);
 	enable_irq(dev->irq);
 }
diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c
index cc7e7de..900f6f4 100644
--- a/drivers/net/ethernet/tehuti/tehuti.c
+++ b/drivers/net/ethernet/tehuti/tehuti.c
@@ -1605,13 +1605,8 @@
 	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 c0f097b..3e914bd 100644
--- a/drivers/net/rionet.c
+++ b/drivers/net/rionet.c
@@ -178,11 +178,7 @@
 	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 = nact;
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 21935580..ee59362 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -54,7 +54,7 @@
 /* use when traversing tree through the allnext, child, sibling,
  * or parent members of struct device_node.
  */
-DEFINE_RWLOCK(devtree_lock);
+DEFINE_RAW_SPINLOCK(devtree_lock);
 
 int of_n_addr_cells(struct device_node *np)
 {
@@ -163,16 +163,14 @@
 EXPORT_SYMBOL(of_node_put);
 #endif /* !CONFIG_SPARC */
 
-struct property *of_find_property(const struct device_node *np,
-				  const char *name,
-				  int *lenp)
+static struct property *__of_find_property(const struct device_node *np,
+					   const char *name, int *lenp)
 {
 	struct property *pp;
 
 	if (!np)
 		return NULL;
 
-	read_lock(&devtree_lock);
 	for (pp = np->properties; pp != 0; pp = pp->next) {
 		if (of_prop_cmp(pp->name, name) == 0) {
 			if (lenp != 0)
@@ -180,7 +178,20 @@
 			break;
 		}
 	}
-	read_unlock(&devtree_lock);
+
+	return pp;
+}
+
+struct property *of_find_property(const struct device_node *np,
+				  const char *name,
+				  int *lenp)
+{
+	struct property *pp;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&devtree_lock, flags);
+	pp = __of_find_property(np, name, lenp);
+	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 
 	return pp;
 }
@@ -198,13 +209,13 @@
 {
 	struct device_node *np;
 
-	read_lock(&devtree_lock);
+	raw_spin_lock(&devtree_lock);
 	np = prev ? prev->allnext : allnodes;
 	for (; np != NULL; np = np->allnext)
 		if (of_node_get(np))
 			break;
 	of_node_put(prev);
-	read_unlock(&devtree_lock);
+	raw_spin_unlock(&devtree_lock);
 	return np;
 }
 EXPORT_SYMBOL(of_find_all_nodes);
@@ -213,8 +224,20 @@
  * Find a property with a given name for a given node
  * and return the value.
  */
+static const void *__of_get_property(const struct device_node *np,
+				     const char *name, int *lenp)
+{
+	struct property *pp = __of_find_property(np, name, lenp);
+
+	return pp ? pp->value : NULL;
+}
+
+/*
+ * Find a property with a given name for a given node
+ * and return the value.
+ */
 const void *of_get_property(const struct device_node *np, const char *name,
-			 int *lenp)
+			    int *lenp)
 {
 	struct property *pp = of_find_property(np, name, lenp);
 
@@ -225,13 +248,13 @@
 /** Checks if the given "compat" string matches one of the strings in
  * the device's "compatible" property
  */
-int of_device_is_compatible(const struct device_node *device,
-		const char *compat)
+static int __of_device_is_compatible(const struct device_node *device,
+				     const char *compat)
 {
 	const char* cp;
-	int cplen, l;
+	int uninitialized_var(cplen), l;
 
-	cp = of_get_property(device, "compatible", &cplen);
+	cp = __of_get_property(device, "compatible", &cplen);
 	if (cp == NULL)
 		return 0;
 	while (cplen > 0) {
@@ -244,6 +267,21 @@
 
 	return 0;
 }
+
+/** Checks if the given "compat" string matches one of the strings in
+ * the device's "compatible" property
+ */
+int of_device_is_compatible(const struct device_node *device,
+		const char *compat)
+{
+	unsigned long flags;
+	int res;
+
+	raw_spin_lock_irqsave(&devtree_lock, flags);
+	res = __of_device_is_compatible(device, compat);
+	raw_spin_unlock_irqrestore(&devtree_lock, flags);
+	return res;
+}
 EXPORT_SYMBOL(of_device_is_compatible);
 
 /**
@@ -303,13 +341,14 @@
 struct device_node *of_get_parent(const struct device_node *node)
 {
 	struct device_node *np;
+	unsigned long flags;
 
 	if (!node)
 		return NULL;
 
-	read_lock(&devtree_lock);
+	raw_spin_lock_irqsave(&devtree_lock, flags);
 	np = of_node_get(node->parent);
-	read_unlock(&devtree_lock);
+	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 	return np;
 }
 EXPORT_SYMBOL(of_get_parent);
@@ -328,14 +367,15 @@
 struct device_node *of_get_next_parent(struct device_node *node)
 {
 	struct device_node *parent;
+	unsigned long flags;
 
 	if (!node)
 		return NULL;
 
-	read_lock(&devtree_lock);
+	raw_spin_lock_irqsave(&devtree_lock, flags);
 	parent = of_node_get(node->parent);
 	of_node_put(node);
-	read_unlock(&devtree_lock);
+	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 	return parent;
 }
 
@@ -351,14 +391,15 @@
 	struct device_node *prev)
 {
 	struct device_node *next;
+	unsigned long flags;
 
-	read_lock(&devtree_lock);
+	raw_spin_lock_irqsave(&devtree_lock, flags);
 	next = prev ? prev->sibling : node->child;
 	for (; next; next = next->sibling)
 		if (of_node_get(next))
 			break;
 	of_node_put(prev);
-	read_unlock(&devtree_lock);
+	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 	return next;
 }
 EXPORT_SYMBOL(of_get_next_child);
@@ -373,14 +414,15 @@
 struct device_node *of_find_node_by_path(const char *path)
 {
 	struct device_node *np = allnodes;
+	unsigned long flags;
 
-	read_lock(&devtree_lock);
+	raw_spin_lock_irqsave(&devtree_lock, flags);
 	for (; np; np = np->allnext) {
 		if (np->full_name && (of_node_cmp(np->full_name, path) == 0)
 		    && of_node_get(np))
 			break;
 	}
-	read_unlock(&devtree_lock);
+	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 	return np;
 }
 EXPORT_SYMBOL(of_find_node_by_path);
@@ -400,15 +442,16 @@
 	const char *name)
 {
 	struct device_node *np;
+	unsigned long flags;
 
-	read_lock(&devtree_lock);
+	raw_spin_lock_irqsave(&devtree_lock, flags);
 	np = from ? from->allnext : allnodes;
 	for (; np; np = np->allnext)
 		if (np->name && (of_node_cmp(np->name, name) == 0)
 		    && of_node_get(np))
 			break;
 	of_node_put(from);
-	read_unlock(&devtree_lock);
+	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 	return np;
 }
 EXPORT_SYMBOL(of_find_node_by_name);
@@ -429,15 +472,16 @@
 	const char *type)
 {
 	struct device_node *np;
+	unsigned long flags;
 
-	read_lock(&devtree_lock);
+	raw_spin_lock_irqsave(&devtree_lock, flags);
 	np = from ? from->allnext : allnodes;
 	for (; np; np = np->allnext)
 		if (np->type && (of_node_cmp(np->type, type) == 0)
 		    && of_node_get(np))
 			break;
 	of_node_put(from);
-	read_unlock(&devtree_lock);
+	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 	return np;
 }
 EXPORT_SYMBOL(of_find_node_by_type);
@@ -460,18 +504,20 @@
 	const char *type, const char *compatible)
 {
 	struct device_node *np;
+	unsigned long flags;
 
-	read_lock(&devtree_lock);
+	raw_spin_lock_irqsave(&devtree_lock, flags);
 	np = from ? from->allnext : allnodes;
 	for (; np; np = np->allnext) {
 		if (type
 		    && !(np->type && (of_node_cmp(np->type, type) == 0)))
 			continue;
-		if (of_device_is_compatible(np, compatible) && of_node_get(np))
+		if (__of_device_is_compatible(np, compatible) &&
+		    of_node_get(np))
 			break;
 	}
 	of_node_put(from);
-	read_unlock(&devtree_lock);
+	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 	return np;
 }
 EXPORT_SYMBOL(of_find_compatible_node);
@@ -493,8 +539,9 @@
 {
 	struct device_node *np;
 	struct property *pp;
+	unsigned long flags;
 
-	read_lock(&devtree_lock);
+	raw_spin_lock_irqsave(&devtree_lock, flags);
 	np = from ? from->allnext : allnodes;
 	for (; np; np = np->allnext) {
 		for (pp = np->properties; pp != 0; pp = pp->next) {
@@ -506,20 +553,14 @@
 	}
 out:
 	of_node_put(from);
-	read_unlock(&devtree_lock);
+	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 	return np;
 }
 EXPORT_SYMBOL(of_find_node_with_property);
 
-/**
- * of_match_node - Tell if an device_node has a matching of_match structure
- *	@matches:	array of of device match structures to search in
- *	@node:		the of device structure to match against
- *
- *	Low level utility function used by device matching.
- */
-const struct of_device_id *of_match_node(const struct of_device_id *matches,
-					 const struct device_node *node)
+static
+const struct of_device_id *__of_match_node(const struct of_device_id *matches,
+					   const struct device_node *node)
 {
 	if (!matches)
 		return NULL;
@@ -533,14 +574,33 @@
 			match &= node->type
 				&& !strcmp(matches->type, node->type);
 		if (matches->compatible[0])
-			match &= of_device_is_compatible(node,
-						matches->compatible);
+			match &= __of_device_is_compatible(node,
+							   matches->compatible);
 		if (match)
 			return matches;
 		matches++;
 	}
 	return NULL;
 }
+
+/**
+ * of_match_node - Tell if an device_node has a matching of_match structure
+ *	@matches:	array of of device match structures to search in
+ *	@node:		the of device structure to match against
+ *
+ *	Low level utility function used by device matching.
+ */
+const struct of_device_id *of_match_node(const struct of_device_id *matches,
+					 const struct device_node *node)
+{
+	const struct of_device_id *match;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&devtree_lock, flags);
+	match = __of_match_node(matches, node);
+	raw_spin_unlock_irqrestore(&devtree_lock, flags);
+	return match;
+}
 EXPORT_SYMBOL(of_match_node);
 
 /**
@@ -559,15 +619,16 @@
 					  const struct of_device_id *matches)
 {
 	struct device_node *np;
+	unsigned long flags;
 
-	read_lock(&devtree_lock);
+	raw_spin_lock_irqsave(&devtree_lock, flags);
 	np = from ? from->allnext : allnodes;
 	for (; np; np = np->allnext) {
-		if (of_match_node(matches, np) && of_node_get(np))
+		if (__of_match_node(matches, np) && of_node_get(np))
 			break;
 	}
 	of_node_put(from);
-	read_unlock(&devtree_lock);
+	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 	return np;
 }
 EXPORT_SYMBOL(of_find_matching_node);
@@ -610,12 +671,12 @@
 {
 	struct device_node *np;
 
-	read_lock(&devtree_lock);
+	raw_spin_lock(&devtree_lock);
 	for (np = allnodes; np; np = np->allnext)
 		if (np->phandle == handle)
 			break;
 	of_node_get(np);
-	read_unlock(&devtree_lock);
+	raw_spin_unlock(&devtree_lock);
 	return np;
 }
 EXPORT_SYMBOL(of_find_node_by_phandle);
@@ -985,18 +1046,18 @@
 	unsigned long flags;
 
 	prop->next = NULL;
-	write_lock_irqsave(&devtree_lock, flags);
+	raw_spin_lock_irqsave(&devtree_lock, flags);
 	next = &np->properties;
 	while (*next) {
 		if (strcmp(prop->name, (*next)->name) == 0) {
 			/* duplicate ! don't insert it */
-			write_unlock_irqrestore(&devtree_lock, flags);
+			raw_spin_unlock_irqrestore(&devtree_lock, flags);
 			return -1;
 		}
 		next = &(*next)->next;
 	}
 	*next = prop;
-	write_unlock_irqrestore(&devtree_lock, flags);
+	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 
 #ifdef CONFIG_PROC_DEVICETREE
 	/* try to add to proc as well if it was initialized */
@@ -1021,7 +1082,7 @@
 	unsigned long flags;
 	int found = 0;
 
-	write_lock_irqsave(&devtree_lock, flags);
+	raw_spin_lock_irqsave(&devtree_lock, flags);
 	next = &np->properties;
 	while (*next) {
 		if (*next == prop) {
@@ -1034,7 +1095,7 @@
 		}
 		next = &(*next)->next;
 	}
-	write_unlock_irqrestore(&devtree_lock, flags);
+	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 
 	if (!found)
 		return -ENODEV;
@@ -1064,7 +1125,7 @@
 	unsigned long flags;
 	int found = 0;
 
-	write_lock_irqsave(&devtree_lock, flags);
+	raw_spin_lock_irqsave(&devtree_lock, flags);
 	next = &np->properties;
 	while (*next) {
 		if (*next == oldprop) {
@@ -1078,7 +1139,7 @@
 		}
 		next = &(*next)->next;
 	}
-	write_unlock_irqrestore(&devtree_lock, flags);
+	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 
 	if (!found)
 		return -ENODEV;
@@ -1108,12 +1169,12 @@
 {
 	unsigned long flags;
 
-	write_lock_irqsave(&devtree_lock, flags);
+	raw_spin_lock_irqsave(&devtree_lock, flags);
 	np->sibling = np->parent->child;
 	np->allnext = allnodes;
 	np->parent->child = np;
 	allnodes = np;
-	write_unlock_irqrestore(&devtree_lock, flags);
+	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 }
 
 /**
@@ -1127,7 +1188,7 @@
 	struct device_node *parent;
 	unsigned long flags;
 
-	write_lock_irqsave(&devtree_lock, flags);
+	raw_spin_lock_irqsave(&devtree_lock, flags);
 
 	parent = np->parent;
 	if (!parent)
@@ -1158,7 +1219,7 @@
 	of_node_set_flag(np, OF_DETACHED);
 
 out_unlock:
-	write_unlock_irqrestore(&devtree_lock, flags);
+	raw_spin_unlock_irqrestore(&devtree_lock, flags);
 }
 #endif /* defined(CONFIG_OF_DYNAMIC) */
 
diff --git a/drivers/pci/access.c b/drivers/pci/access.c
index fdaa42a..1a6cc67 100644
--- a/drivers/pci/access.c
+++ b/drivers/pci/access.c
@@ -441,7 +441,7 @@
 	WARN_ON(!dev->block_ucfg_access);
 
 	dev->block_ucfg_access = 0;
-	wake_up_all(&pci_ucfg_wait);
+	wake_up_all_locked(&pci_ucfg_wait);
 	raw_spin_unlock_irqrestore(&pci_lock, flags);
 }
 EXPORT_SYMBOL_GPL(pci_unblock_user_cfg_access);
diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
index 8d67467..4085187 100644
--- a/drivers/scsi/fcoe/fcoe.c
+++ b/drivers/scsi/fcoe/fcoe.c
@@ -1156,7 +1156,7 @@
 	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);
@@ -1212,7 +1212,7 @@
 			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
@@ -1435,11 +1435,11 @@
 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;
 }
@@ -1680,7 +1680,7 @@
 	 */
 	hp = (struct fcoe_hdr *) skb_network_header(skb);
 
-	stats = per_cpu_ptr(lport->dev_stats, get_cpu());
+	stats = per_cpu_ptr(lport->dev_stats, get_cpu_light());
 	if (unlikely(FC_FCOE_DECAPS_VER(hp) != FC_FCOE_VER)) {
 		if (stats->ErrorFrames < 5)
 			printk(KERN_WARNING "fcoe: FCoE version "
@@ -1712,13 +1712,13 @@
 		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 e7522dc..bfb83c0 100644
--- a/drivers/scsi/fcoe/fcoe_ctlr.c
+++ b/drivers/scsi/fcoe/fcoe_ctlr.c
@@ -719,7 +719,7 @@
 	unsigned long sel_time = 0;
 	struct fcoe_dev_stats *stats;
 
-	stats = per_cpu_ptr(fip->lp->dev_stats, get_cpu());
+	stats = per_cpu_ptr(fip->lp->dev_stats, get_cpu_light());
 
 	list_for_each_entry_safe(fcf, next, &fip->fcfs, list) {
 		deadline = fcf->time + fcf->fka_period + fcf->fka_period / 2;
@@ -752,7 +752,7 @@
 				sel_time = fcf->time;
 		}
 	}
-	put_cpu();
+	put_cpu_light();
 	if (sel_time && !fip->sel_fcf && !fip->sel_time) {
 		sel_time += msecs_to_jiffies(FCOE_CTLR_START_DELAY);
 		fip->sel_time = sel_time;
diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c
index 9de9db2..340998f 100644
--- a/drivers/scsi/libfc/fc_exch.c
+++ b/drivers/scsi/libfc/fc_exch.c
@@ -724,10 +724,10 @@
 	}
 	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/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h
index 9902834..6d01db6 100644
--- a/drivers/scsi/qla2xxx/qla_inline.h
+++ b/drivers/scsi/qla2xxx/qla_inline.h
@@ -36,12 +36,12 @@
 {
 	unsigned long flags;
 	struct qla_hw_data *ha = rsp->hw;
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 	if (IS_QLA82XX(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/tty/serial/8250.c b/drivers/tty/serial/8250.c
index 33601f8..b713a36 100644
--- a/drivers/tty/serial/8250.c
+++ b/drivers/tty/serial/8250.c
@@ -38,6 +38,7 @@
 #include <linux/nmi.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
+#include <linux/kdb.h>
 
 #include <asm/io.h>
 #include <asm/irq.h>
@@ -81,7 +82,16 @@
 #define DEBUG_INTR(fmt...)	do { } while (0)
 #endif
 
-#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
 
 #define BOTH_EMPTY 	(UART_LSR_TEMT | UART_LSR_THRE)
 
@@ -2883,14 +2893,14 @@
 
 	touch_nmi_watchdog();
 
-	local_irq_save(flags);
-	if (up->port.sysrq) {
-		/* serial8250_handle_port() already took the lock */
+	if (unlikely(in_kdb_printk())) {
 		locked = 0;
-	} else if (oops_in_progress) {
-		locked = spin_trylock(&up->port.lock);
-	} else
-		spin_lock(&up->port.lock);
+	} else {
+		if (up->port.sysrq || oops_in_progress)
+			locked = spin_trylock_irqsave(&up->port.lock, flags);
+		else
+			spin_lock_irqsave(&up->port.lock, flags);
+	}
 
 	/*
 	 *	First save the IER then disable the interrupts
@@ -2922,8 +2932,7 @@
 		check_modem_status(up);
 
 	if (locked)
-		spin_unlock(&up->port.lock);
-	local_irq_restore(flags);
+		spin_unlock_irqrestore(&up->port.lock, flags);
 }
 
 static int __init serial8250_console_setup(struct console *co, char *options)
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index fe9f111..1fbaf66 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -1761,13 +1761,19 @@
 
 	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
@@ -1789,8 +1795,7 @@
 	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/imx.c b/drivers/tty/serial/imx.c
index 8e68f79..5f5c214 100644
--- a/drivers/tty/serial/imx.c
+++ b/drivers/tty/serial/imx.c
@@ -1115,8 +1115,14 @@
 	struct imx_port *sport = imx_ports[co->index];
 	unsigned int old_ucr1, old_ucr2, ucr1;
 	unsigned long flags;
+	int locked = 1;
 
-	spin_lock_irqsave(&sport->port.lock, flags);
+	if (sport->port.sysrq)
+		locked = 0;
+	else if (oops_in_progress)
+		locked = spin_trylock_irqsave(&sport->port.lock, flags);
+	else
+		spin_lock_irqsave(&sport->port.lock, flags);
 
 	/*
 	 *	First, save UCR1/2 and then disable interrupts
@@ -1144,7 +1150,8 @@
 	writel(old_ucr1, sport->port.membase + UCR1);
 	writel(old_ucr2, sport->port.membase + UCR2);
 
-	spin_unlock_irqrestore(&sport->port.lock, flags);
+	if (locked)
+		spin_unlock_irqrestore(&sport->port.lock, flags);
 }
 
 /*
diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c
index 5e713d3..93cdb92 100644
--- a/drivers/tty/serial/omap-serial.c
+++ b/drivers/tty/serial/omap-serial.c
@@ -946,13 +946,12 @@
 	unsigned int ier;
 	int locked = 1;
 
-	local_irq_save(flags);
 	if (up->port.sysrq)
 		locked = 0;
 	else if (oops_in_progress)
-		locked = spin_trylock(&up->port.lock);
+		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
@@ -979,8 +978,7 @@
 		check_modem_status(up);
 
 	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/tty_buffer.c b/drivers/tty/tty_buffer.c
index 4f02f9c..7c8fe9b 100644
--- a/drivers/tty/tty_buffer.c
+++ b/drivers/tty/tty_buffer.c
@@ -496,10 +496,14 @@
 		tty->buf.tail->commit = tty->buf.tail->used;
 	spin_unlock_irqrestore(&tty->buf.lock, flags);
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 	if (tty->low_latency)
 		flush_to_ldisc(&tty->buf.work);
 	else
 		schedule_work(&tty->buf.work);
+#else
+	flush_to_ldisc(&tty->buf.work);
+#endif
 }
 EXPORT_SYMBOL(tty_flip_buffer_push);
 
diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c
index 8e0924f..820f7dc 100644
--- a/drivers/tty/tty_ldisc.c
+++ b/drivers/tty/tty_ldisc.c
@@ -71,7 +71,7 @@
 	 * We really want an "atomic_dec_and_lock_irqsave()",
 	 * but we don't have it, so this does it by hand.
 	 */
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 	if (atomic_dec_and_lock(&ld->users, &tty_ldisc_lock)) {
 		struct tty_ldisc_ops *ldo = ld->ops;
 
@@ -82,7 +82,7 @@
 		kfree(ld);
 		return;
 	}
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 	wake_up(&tty_ldisc_idle);
 }
 
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index eb2c3bd..9e9fc4e 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -2145,7 +2145,7 @@
 	 * when the first handler doesn't use it.  So let's just
 	 * assume it's never used.
 	 */
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 
 	if (unlikely(HCD_DEAD(hcd) || !HCD_HW_ACCESSIBLE(hcd))) {
 		rc = IRQ_NONE;
@@ -2158,7 +2158,7 @@
 		rc = IRQ_HANDLED;
 	}
 
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(usb_hcd_irq);
diff --git a/drivers/usb/gadget/ci13xxx_udc.c b/drivers/usb/gadget/ci13xxx_udc.c
index 9a0c397..f526873 100644
--- a/drivers/usb/gadget/ci13xxx_udc.c
+++ b/drivers/usb/gadget/ci13xxx_udc.c
@@ -819,7 +819,7 @@
 } dbg_data = {
 	.idx = 0,
 	.tty = 0,
-	.lck = __RW_LOCK_UNLOCKED(lck)
+	.lck = __RW_LOCK_UNLOCKED(dbg_data.lck)
 };
 
 /**
diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c
index b263919..d4b05d1 100644
--- a/drivers/usb/host/ohci-hcd.c
+++ b/drivers/usb/host/ohci-hcd.c
@@ -830,9 +830,13 @@
 	}
 
 	if (ints & OHCI_INTR_WDH) {
-		spin_lock (&ohci->lock);
-		dl_done_list (ohci);
-		spin_unlock (&ohci->lock);
+		if (ohci->hcca->done_head == 0) {
+			ints &= ~OHCI_INTR_WDH;
+		} else {
+			spin_lock (&ohci->lock);
+			dl_done_list (ohci);
+			spin_unlock (&ohci->lock);
+		}
 	}
 
 	if (quirk_zfmicro(ohci) && (ints & OHCI_INTR_SF)) {
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index 650d520..fb77639 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 7fc0371..eb63fb7 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -161,7 +161,7 @@
 			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/btrfs/ctree.c b/fs/btrfs/ctree.c
index dede441..980adc0 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -77,7 +77,7 @@
 {
 	int i;
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
+#if (defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_PREEMPT_RT_BASE))
 	/* lockdep really cares that we take all of these spinlocks
 	 * in the right order.  If any of the locks in the path are not
 	 * currently blocking, it is going to complain.  So, make really
@@ -104,7 +104,7 @@
 		}
 	}
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
+#if (defined(CONFIG_DEBUG_LOCK_ALLOC) || defined(CONFIG_PREEMPT_RT_BASE))
 	if (held)
 		btrfs_clear_lock_blocking_rw(held, held_rw);
 #endif
diff --git a/fs/buffer.c b/fs/buffer.c
index 7eb4da4..896adf2 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -331,8 +331,7 @@
 	 * 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;
@@ -345,8 +344,7 @@
 		}
 		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
@@ -358,9 +356,7 @@
 	return;
 
 still_busy:
-	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
-	local_irq_restore(flags);
-	return;
+	bh_uptodate_unlock_irqrestore(first, flags);
 }
 
 /*
@@ -394,8 +390,7 @@
 	}
 
 	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);
@@ -407,15 +402,12 @@
 		}
 		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);
 
@@ -1444,10 +1436,23 @@
 	}
 	put_cpu_var(bh_lrus);
 }
+
+static bool has_bh_in_lru(int cpu, void *dummy)
+{
+	struct bh_lru *b = per_cpu_ptr(&bh_lrus, cpu);
+	int i;
 	
+	for (i = 0; i < BH_LRU_SIZE; i++) {
+		if (b->bhs[i])
+			return 1;
+	}
+
+	return 0;
+}
+
 void invalidate_bh_lrus(void)
 {
-	on_each_cpu(invalidate_bh_lru, NULL, 1);
+	on_each_cpu_cond(has_bh_in_lru, invalidate_bh_lru, NULL, 1, GFP_KERNEL);
 }
 EXPORT_SYMBOL_GPL(invalidate_bh_lrus);
 
@@ -3241,6 +3246,7 @@
 	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 8a35300..41c6d35 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -37,6 +37,7 @@
 #include <linux/rculist_bl.h>
 #include <linux/prefetch.h>
 #include <linux/ratelimit.h>
+#include <linux/delay.h>
 #include "internal.h"
 
 /*
@@ -410,7 +411,7 @@
 	if (inode && !spin_trylock(&inode->i_lock)) {
 relock:
 		spin_unlock(&dentry->d_lock);
-		cpu_relax();
+		cpu_chill();
 		return dentry; /* try again with same dentry */
 	}
 	if (IS_ROOT(dentry))
@@ -796,7 +797,7 @@
 
 		if (!spin_trylock(&dentry->d_lock)) {
 			spin_unlock(&dcache_lru_lock);
-			cpu_relax();
+			cpu_chill();
 			goto relock;
 		}
 
@@ -1989,7 +1990,7 @@
 	if (dentry->d_count == 1) {
 		if (inode && !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 451b9b8..3ed4aca 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -464,12 +464,12 @@
  */
 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 7adb43f..da515d7 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -837,10 +837,12 @@
 		}
 	}
 	task_lock(tsk);
+	local_irq_disable_rt();
 	active_mm = tsk->active_mm;
 	tsk->mm = mm;
 	tsk->active_mm = mm;
 	activate_mm(active_mm, mm);
+	local_irq_enable_rt();
 	task_unlock(tsk);
 	arch_pick_mmap_layout(mm);
 	if (old_mm) {
diff --git a/fs/file.c b/fs/file.c
index 30bfc99..9161ecc 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -105,14 +105,14 @@
 		kfree(fdt->open_fds);
 		kfree(fdt);
 	} else {
-		fddef = &get_cpu_var(fdtable_defer_list);
+		fddef = &per_cpu(fdtable_defer_list, get_cpu_light());
 		spin_lock(&fddef->lock);
 		fdt->next = fddef->next;
 		fddef->next = fdt;
 		/* vmallocs are handled from the workqueue context */
 		schedule_work(&fddef->wq);
 		spin_unlock(&fddef->lock);
-		put_cpu_var(fdtable_defer_list);
+		put_cpu_light();
 	}
 }
 
@@ -422,7 +422,7 @@
 		.close_on_exec	= (fd_set *)&init_files.close_on_exec_init,
 		.open_fds	= (fd_set *)&init_files.open_fds_init,
 	},
-	.file_lock	= __SPIN_LOCK_UNLOCKED(init_task.file_lock),
+	.file_lock	= __SPIN_LOCK_UNLOCKED(init_files.file_lock),
 };
 
 /*
diff --git a/fs/fs_struct.c b/fs/fs_struct.c
index 78b519c..f5818c4 100644
--- a/fs/fs_struct.c
+++ b/fs/fs_struct.c
@@ -26,11 +26,11 @@
 {
 	struct path old_root;
 
+	path_get_longterm(path);
 	spin_lock(&fs->lock);
 	write_seqcount_begin(&fs->seq);
 	old_root = fs->root;
 	fs->root = *path;
-	path_get_longterm(path);
 	write_seqcount_end(&fs->seq);
 	spin_unlock(&fs->lock);
 	if (old_root.dentry)
@@ -45,11 +45,11 @@
 {
 	struct path old_pwd;
 
+	path_get_longterm(path);
 	spin_lock(&fs->lock);
 	write_seqcount_begin(&fs->seq);
 	old_pwd = fs->pwd;
 	fs->pwd = *path;
-	path_get_longterm(path);
 	write_seqcount_end(&fs->seq);
 	spin_unlock(&fs->lock);
 
@@ -57,6 +57,14 @@
 		path_put_longterm(&old_pwd);
 }
 
+static inline int replace_path(struct path *p, const struct path *old, const struct path *new)
+{
+	if (likely(p->dentry != old->dentry || p->mnt != old->mnt))
+		return 0;
+	*p = *new;
+	return 1;
+}
+
 void chroot_fs_refs(struct path *old_root, struct path *new_root)
 {
 	struct task_struct *g, *p;
@@ -68,21 +76,16 @@
 		task_lock(p);
 		fs = p->fs;
 		if (fs) {
+			int hits = 0;
 			spin_lock(&fs->lock);
 			write_seqcount_begin(&fs->seq);
-			if (fs->root.dentry == old_root->dentry
-			    && fs->root.mnt == old_root->mnt) {
-				path_get_longterm(new_root);
-				fs->root = *new_root;
-				count++;
-			}
-			if (fs->pwd.dentry == old_root->dentry
-			    && fs->pwd.mnt == old_root->mnt) {
-				path_get_longterm(new_root);
-				fs->pwd = *new_root;
-				count++;
-			}
+			hits += replace_path(&fs->root, old_root, new_root);
+			hits += replace_path(&fs->pwd, old_root, new_root);
 			write_seqcount_end(&fs->seq);
+			while (hits--) {
+				count++;
+				path_get_longterm(new_root);
+			}
 			spin_unlock(&fs->lock);
 		}
 		task_unlock(p);
diff --git a/fs/jbd/checkpoint.c b/fs/jbd/checkpoint.c
index 5c93ffc..ddbd223 100644
--- a/fs/jbd/checkpoint.c
+++ b/fs/jbd/checkpoint.c
@@ -129,6 +129,8 @@
 		if (journal->j_flags & JFS_ABORT)
 			return;
 		spin_unlock(&journal->j_state_lock);
+		if (current->plug)
+			io_schedule();
 		mutex_lock(&journal->j_checkpoint_mutex);
 
 		/*
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 39c7059..7b195af 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -129,6 +129,8 @@
 		if (journal->j_flags & JBD2_ABORT)
 			return;
 		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 a1e663d..060c0a0 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -31,6 +31,7 @@
 #include <linux/idr.h>
 #include <linux/fs_struct.h>
 #include <linux/fsnotify.h>
+#include <linux/delay.h>
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
 #include "pnode.h"
@@ -341,8 +342,14 @@
 	 * incremented count after it has set MNT_WRITE_HOLD.
 	 */
 	smp_mb();
-	while (mnt->mnt_flags & MNT_WRITE_HOLD)
-		cpu_relax();
+	/*
+	 * No need to keep preemption disabled accross the spin loop.
+	 */
+	while (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
@@ -352,9 +359,7 @@
 	if (__mnt_is_readonly(mnt)) {
 		mnt_dec_writers(mnt);
 		ret = -EROFS;
-		goto out;
 	}
-out:
 	preempt_enable();
 	return ret;
 }
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index 0b1e885b..4c8095c 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -108,8 +108,7 @@
 				"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;
@@ -124,8 +123,7 @@
 		}
 		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
@@ -146,13 +144,13 @@
 		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, KM_BIO_SRC_IRQ);
 		for (i = 0; i < recs; i++)
 			post_read_mst_fixup((NTFS_RECORD*)(kaddr +
 					i * rec_size), rec_size);
 		kunmap_atomic(kaddr, KM_BIO_SRC_IRQ);
-		local_irq_restore(flags);
+		local_irq_restore_nort(flags);
 		flush_dcache_page(page);
 		if (likely(page_uptodate && !PageError(page)))
 			SetPageUptodate(page);
@@ -160,9 +158,7 @@
 	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 dffeb37..57f0e4e 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -313,7 +313,7 @@
 		if (hrtimer_try_to_cancel(&ctx->tmr) >= 0)
 			break;
 		spin_unlock_irq(&ctx->wqh.lock);
-		cpu_relax();
+		hrtimer_wait_for_timer(&ctx->tmr);
 	}
 
 	/*
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index 828662f..13d86a8 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -97,7 +97,7 @@
 /*
  * Feature macros (disable/enable)
  */
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) && !defined(CONFIG_PREEMPT_RT_FULL)
 #define HAVE_PERCPU_SB	/* per cpu superblock counters are a 2.6 feature */
 #else
 #undef  HAVE_PERCPU_SB	/* per cpu superblock counters are a 2.6 feature */
diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h
index f4b2eff..0e70789 100644
--- a/include/acpi/platform/aclinux.h
+++ b/include/acpi/platform/aclinux.h
@@ -73,6 +73,7 @@
 
 #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
 
 #else /* !__KERNEL__ */
@@ -176,6 +177,19 @@
 	lock ? AE_OK : AE_NO_MEMORY;				\
 })
 
+#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)
+
 #endif /* __KERNEL__ */
 
 #endif /* __ACLINUX_H__ */
diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index 84458b0..97c1eaf 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -3,6 +3,10 @@
 
 #include <linux/compiler.h>
 
+#ifndef __ASSEMBLY__
+extern void __WARN_ON(const char *func, const char *file, const int line);
+#endif /* __ASSEMBLY__ */
+
 #ifdef CONFIG_BUG
 
 #ifdef CONFIG_GENERIC_BUG
@@ -202,4 +206,18 @@
 # 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
diff --git a/include/asm-generic/cmpxchg-local.h b/include/asm-generic/cmpxchg-local.h
index 2533fdd..d8d4c89 100644
--- a/include/asm-generic/cmpxchg-local.h
+++ b/include/asm-generic/cmpxchg-local.h
@@ -21,7 +21,7 @@
 	if (size == 8 && sizeof(unsigned long) != 8)
 		wrong_size_cmpxchg(ptr);
 
-	local_irq_save(flags);
+	raw_local_irq_save(flags);
 	switch (size) {
 	case 1: prev = *(u8 *)ptr;
 		if (prev == old)
@@ -42,7 +42,7 @@
 	default:
 		wrong_size_cmpxchg(ptr);
 	}
-	local_irq_restore(flags);
+	raw_local_irq_restore(flags);
 	return prev;
 }
 
@@ -55,11 +55,11 @@
 	u64 prev;
 	unsigned long flags;
 
-	local_irq_save(flags);
+	raw_local_irq_save(flags);
 	prev = *(u64 *)ptr;
 	if (prev == old)
 		*(u64 *)ptr = new;
-	local_irq_restore(flags);
+	raw_local_irq_restore(flags);
 	return prev;
 }
 
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index fed3f3a..7a0f7d2 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -72,8 +72,52 @@
 	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 defined(CONFIG_JBD) || defined(CONFIG_JBD_MODULE) || \
+    defined(CONFIG_JBD2) || defined(CONFIG_JBD2_MODULE)
+	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 defined(CONFIG_JBD) || defined(CONFIG_JBD_MODULE) || \
+    defined(CONFIG_JBD2) || defined(CONFIG_JBD2_MODULE)
+	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/console.h b/include/linux/console.h
index 6ae6a15..5695804 100644
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -135,6 +135,7 @@
 	for (con = console_drivers; con != NULL; con = con->next)
 
 extern int console_set_on_cmdline;
+extern struct console *early_console;
 
 extern int add_preferred_console(char *name, int idx, char *options);
 extern int update_console_cmdline(char *name, int idx, char *name_new, int idx_new, char *options);
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 9c3e071..ff0a0ec 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -168,6 +168,8 @@
 
 extern void get_online_cpus(void);
 extern void put_online_cpus(void);
+extern void pin_current_cpu(void);
+extern void unpin_current_cpu(void);
 extern void cpu_hotplug_disable(void);
 extern void cpu_hotplug_enable(void);
 #define hotcpu_notifier(fn, pri)	cpu_notifier(fn, pri)
@@ -192,6 +194,8 @@
 
 #define get_online_cpus()	do { } while (0)
 #define put_online_cpus()	do { } while (0)
+static inline void pin_current_cpu(void) { }
+static inline void unpin_current_cpu(void) { }
 #define cpu_hotplug_disable()	do { } while (0)
 #define cpu_hotplug_enable()	do { } while (0)
 #define hotcpu_notifier(fn, pri)	do { (void)(fn); } while (0)
diff --git a/include/linux/delay.h b/include/linux/delay.h
index a6ecb34..37caab3 100644
--- a/include/linux/delay.h
+++ b/include/linux/delay.h
@@ -52,4 +52,10 @@
 	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_event.h b/include/linux/ftrace_event.h
index 82924bf..11877b0 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -49,7 +49,8 @@
 	unsigned char		flags;
 	unsigned char		preempt_count;
 	int			pid;
-	int			padding;
+	unsigned short		migrate_disable;
+	unsigned short		padding;
 };
 
 #define FTRACE_MAX_EVENT						\
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index f743883..7059ce2 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -60,7 +60,11 @@
 #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
 
 #ifndef PREEMPT_ACTIVE
 #define PREEMPT_ACTIVE_BITS	1
@@ -73,10 +77,17 @@
 #endif
 
 #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?
  * Are we in a softirq context? Interrupt context?
@@ -86,7 +97,6 @@
 #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?
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index cc07d27..7259cd3 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -111,6 +111,11 @@
 	enum hrtimer_restart		(*function)(struct hrtimer *);
 	struct hrtimer_clock_base	*base;
 	unsigned long			state;
+	struct list_head		cb_entry;
+	int				irqsafe;
+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
+	ktime_t 			praecox;
+#endif
 #ifdef CONFIG_TIMER_STATS
 	int				start_pid;
 	void				*start_site;
@@ -147,6 +152,7 @@
 	int			index;
 	clockid_t		clockid;
 	struct timerqueue_head	active;
+	struct list_head	expired;
 	ktime_t			resolution;
 	ktime_t			(*get_time)(void);
 	ktime_t			softirq_time;
@@ -189,6 +195,9 @@
 	unsigned long			nr_hangs;
 	ktime_t				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];
 };
 
@@ -382,6 +391,13 @@
 	return 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);
 extern int hrtimer_get_res(const clockid_t which_clock, struct timespec *tp);
diff --git a/include/linux/idr.h b/include/linux/idr.h
index 52a9da2..dffed8f 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -136,7 +136,7 @@
 	struct ida_bitmap	*free_bitmap;
 };
 
-#define IDA_INIT(name)		{ .idr = IDR_INIT(name), .free_bitmap = NULL, }
+#define IDA_INIT(name)		{ .idr = IDR_INIT((name).idr), .free_bitmap = NULL, }
 #define DEFINE_IDA(name)	struct ida name = IDA_INIT(name)
 
 int ida_pre_get(struct ida *ida, gfp_t gfp_mask);
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index cdde2b37..3202e80 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -142,6 +142,12 @@
 # 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
+
 #define INIT_TASK_COMM "swapper"
 
 /*
@@ -197,6 +203,7 @@
 	.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 a64b00e..42f79fb 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -61,6 +61,7 @@
  * IRQF_NO_THREAD - Interrupt cannot be threaded
  * IRQF_EARLY_RESUME - Resume IRQ early during syscore instead of at device
  *                resume time.
+ * IRQF_NO_SOFTIRQ_CALL - Do not process softirqs in the irq thread context (RT)
  */
 #define IRQF_DISABLED		0x00000020
 #define IRQF_SAMPLE_RANDOM	0x00000040
@@ -75,6 +76,7 @@
 #define IRQF_FORCE_RESUME	0x00008000
 #define IRQF_NO_THREAD		0x00010000
 #define IRQF_EARLY_RESUME	0x00020000
+#define IRQF_NO_SOFTIRQ_CALL	0x00040000
 
 #define IRQF_TIMER		(__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD)
 
@@ -219,7 +221,7 @@
 #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);
@@ -269,6 +271,7 @@
 	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);
 };
@@ -396,9 +399,13 @@
 
 
 #ifdef CONFIG_IRQ_FORCED_THREADING
-extern bool force_irqthreads;
+# 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
@@ -452,8 +459,14 @@
 	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(); }
+#else
+extern void thread_do_softirq(void);
+#endif
+
 extern void open_softirq(int nr, void (*action)(struct softirq_action *));
 extern void softirq_init(void);
 static inline void __raise_softirq_irqoff(unsigned int nr)
@@ -465,6 +478,8 @@
 extern void raise_softirq_irqoff(unsigned int nr);
 extern void raise_softirq(unsigned int nr);
 
+extern void softirq_check_pending_idle(void);
+
 /* This is the worklist that queues up per-cpu softirq work.
  *
  * send_remote_sendirq() adds work to these lists, and
@@ -505,8 +520,9 @@
      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.
@@ -531,27 +547,36 @@
 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_clear_bit(); 
 	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
@@ -600,17 +625,8 @@
 	smp_mb();
 }
 
-static inline void tasklet_enable(struct tasklet_struct *t)
-{
-	smp_mb__before_atomic_dec();
-	atomic_dec(&t->count);
-}
-
-static inline void tasklet_hi_enable(struct tasklet_struct *t)
-{
-	smp_mb__before_atomic_dec();
-	atomic_dec(&t->count);
-}
+extern  void tasklet_enable(struct tasklet_struct *t);
+extern  void tasklet_hi_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);
@@ -642,6 +658,12 @@
 	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 bff29c5..3838b53 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -67,6 +67,7 @@
  * IRQ_MOVE_PCNTXT		- Interrupt can be migrated from process context
  * IRQ_NESTED_TRHEAD		- Interrupt nests into another thread
  * IRQ_PER_CPU_DEVID		- Dev_id is a per-cpu variable
+ * IRQ_NO_SOFTIRQ_CALL		- No softirq processing in the irq thread context (RT)
  */
 enum {
 	IRQ_TYPE_NONE		= 0x00000000,
@@ -90,12 +91,14 @@
 	IRQ_NESTED_THREAD	= (1 << 15),
 	IRQ_NOTHREAD		= (1 << 16),
 	IRQ_PER_CPU_DEVID	= (1 << 17),
+	IRQ_NO_SOFTIRQ_CALL	= (1 << 18),
 };
 
 #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_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID | \
+	 IRQ_NO_SOFTIRQ_CALL)
 
 #define IRQ_NO_BALANCING_MASK	(IRQ_PER_CPU | IRQ_NO_BALANCING)
 
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index e2e1ab5..7fa27c1 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -55,6 +55,7 @@
 	unsigned int		irq_count;	/* For detecting broken IRQs */
 	unsigned long		last_unhandled;	/* Aging timer for unhandled count */
 	unsigned int		irqs_unhandled;
+	u64			random_ip;
 	atomic_t		threads_handled;
 	int			threads_handled_last;
 	raw_spinlock_t		lock;
diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
index d176d65..a52b35d 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) || \
@@ -147,4 +151,23 @@
 
 #endif /* CONFIG_TRACE_IRQFLAGS_SUPPORT */
 
+/*
+ * 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)	do { local_save_flags(flags); } while (0)
+# define local_irq_restore_nort(flags)	do { (void)(flags); } while (0)
+# 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/jbd_common.h b/include/linux/jbd_common.h
index 6230f85..11c313e 100644
--- a/include/linux/jbd_common.h
+++ b/include/linux/jbd_common.h
@@ -37,32 +37,56 @@
 
 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
 }
 
 #endif
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 388b0d4..9cc8ed9 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -4,7 +4,7 @@
 #include <linux/types.h>
 #include <linux/compiler.h>
 
-#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL)
+#if defined(CC_HAVE_ASM_GOTO) && defined(CONFIG_JUMP_LABEL) && !defined(CONFIG_PREEMPT_BASE)
 
 struct jump_label_key {
 	atomic_t enabled;
diff --git a/include/linux/kdb.h b/include/linux/kdb.h
index 0647258..0d1ebfc 100644
--- a/include/linux/kdb.h
+++ b/include/linux/kdb.h
@@ -150,12 +150,14 @@
 extern int kdb_register_repeat(char *, kdb_func_t, char *, char *,
 			       short, kdb_repeat_t);
 extern int kdb_unregister(char *);
+#define in_kdb_printk() (kdb_trap_printk)
 #else /* ! CONFIG_KGDB_KDB */
 #define kdb_printf(...)
 #define kdb_init(x)
 #define kdb_register(...)
 #define kdb_register_repeat(...)
 #define kdb_uregister(x)
+#define in_kdb_printk() (0)
 #endif	/* CONFIG_KGDB_KDB */
 enum {
 	KDB_NOT_INITIALIZED,
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index dcf6a8b..7551546 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -370,7 +370,7 @@
 	SYSTEM_HALT,
 	SYSTEM_POWER_OFF,
 	SYSTEM_RESTART,
-	SYSTEM_SUSPEND_DISK,
+	SYSTEM_SUSPEND,
 } system_state;
 
 #define TAINT_PROPRIETARY_MODULE	0
diff --git a/include/linux/lglock.h b/include/linux/lglock.h
index 87f402c..cdfcef3 100644
--- a/include/linux/lglock.h
+++ b/include/linux/lglock.h
@@ -71,6 +71,8 @@
  extern void name##_global_lock_online(void);				\
  extern void name##_global_unlock_online(void);				\
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+
 #define DEFINE_LGLOCK(name)						\
 									\
  DEFINE_SPINLOCK(name##_cpu_lock);					\
@@ -197,4 +199,130 @@
 	preempt_enable();						\
  }									\
  EXPORT_SYMBOL(name##_global_unlock);
+
+#else /* !PREEMPT_RT_FULL */
+#define DEFINE_LGLOCK(name)						\
+									\
+ DEFINE_PER_CPU(struct rt_mutex, name##_lock);				\
+ DEFINE_SPINLOCK(name##_cpu_lock);					\
+ cpumask_t name##_cpus __read_mostly;					\
+ DEFINE_LGLOCK_LOCKDEP(name);						\
+									\
+ static int								\
+ name##_lg_cpu_callback(struct notifier_block *nb,			\
+				unsigned long action, void *hcpu)	\
+ {									\
+	switch (action & ~CPU_TASKS_FROZEN) {				\
+	case CPU_UP_PREPARE:						\
+		spin_lock(&name##_cpu_lock);				\
+		cpu_set((unsigned long)hcpu, name##_cpus);		\
+		spin_unlock(&name##_cpu_lock);				\
+		break;							\
+	case CPU_UP_CANCELED: case CPU_DEAD:				\
+		spin_lock(&name##_cpu_lock);				\
+		cpu_clear((unsigned long)hcpu, name##_cpus);		\
+		spin_unlock(&name##_cpu_lock);				\
+	}								\
+	return NOTIFY_OK;						\
+ }									\
+ static struct notifier_block name##_lg_cpu_notifier = {		\
+	.notifier_call = name##_lg_cpu_callback,			\
+ };									\
+ void name##_lock_init(void) {						\
+	int i;								\
+	LOCKDEP_INIT_MAP(&name##_lock_dep_map, #name, &name##_lock_key, 0); \
+	for_each_possible_cpu(i) {					\
+		struct rt_mutex *lock;					\
+		lock = &per_cpu(name##_lock, i);			\
+		rt_mutex_init(lock);					\
+	}								\
+	register_hotcpu_notifier(&name##_lg_cpu_notifier);		\
+	get_online_cpus();						\
+	for_each_online_cpu(i)						\
+		cpu_set(i, name##_cpus);				\
+	put_online_cpus();						\
+ }									\
+ EXPORT_SYMBOL(name##_lock_init);					\
+									\
+ void name##_local_lock(void) {						\
+	struct rt_mutex *lock;						\
+	migrate_disable();						\
+	rwlock_acquire_read(&name##_lock_dep_map, 0, 0, _THIS_IP_);	\
+	lock = &__get_cpu_var(name##_lock);				\
+	__rt_spin_lock(lock);						\
+ }									\
+ EXPORT_SYMBOL(name##_local_lock);					\
+									\
+ void name##_local_unlock(void) {					\
+	struct rt_mutex *lock;						\
+	rwlock_release(&name##_lock_dep_map, 1, _THIS_IP_);		\
+	lock = &__get_cpu_var(name##_lock);				\
+	__rt_spin_unlock(lock);						\
+	migrate_enable();						\
+ }									\
+ EXPORT_SYMBOL(name##_local_unlock);					\
+									\
+ void name##_local_lock_cpu(int cpu) {					\
+	struct rt_mutex *lock;						\
+	rwlock_acquire_read(&name##_lock_dep_map, 0, 0, _THIS_IP_);	\
+	lock = &per_cpu(name##_lock, cpu);				\
+	__rt_spin_lock(lock);						\
+ }									\
+ EXPORT_SYMBOL(name##_local_lock_cpu);					\
+									\
+ void name##_local_unlock_cpu(int cpu) {				\
+	struct rt_mutex *lock;						\
+	rwlock_release(&name##_lock_dep_map, 1, _THIS_IP_);		\
+	lock = &per_cpu(name##_lock, cpu);				\
+	__rt_spin_unlock(lock);						\
+ }									\
+ EXPORT_SYMBOL(name##_local_unlock_cpu);				\
+									\
+ void name##_global_lock_online(void) {					\
+	int i;								\
+	rwlock_acquire(&name##_lock_dep_map, 0, 0, _RET_IP_);		\
+	spin_lock(&name##_cpu_lock);					\
+	for_each_cpu(i, &name##_cpus) {					\
+		struct rt_mutex *lock;					\
+		lock = &per_cpu(name##_lock, i);			\
+		__rt_spin_lock(lock);					\
+	}								\
+ }									\
+ EXPORT_SYMBOL(name##_global_lock_online);				\
+									\
+ void name##_global_unlock_online(void) {				\
+	int i;								\
+	rwlock_release(&name##_lock_dep_map, 1, _RET_IP_);		\
+	for_each_cpu(i, &name##_cpus) {					\
+		struct rt_mutex *lock;					\
+		lock = &per_cpu(name##_lock, i);			\
+		__rt_spin_unlock(lock);					\
+	}								\
+	spin_unlock(&name##_cpu_lock);					\
+ }									\
+ EXPORT_SYMBOL(name##_global_unlock_online);				\
+									\
+ void name##_global_lock(void) {					\
+	int i;								\
+	rwlock_acquire(&name##_lock_dep_map, 0, 0, _RET_IP_);		\
+	for_each_possible_cpu(i) {					\
+		struct rt_mutex *lock;					\
+		lock = &per_cpu(name##_lock, i);			\
+		__rt_spin_lock(lock);					\
+	}								\
+ }									\
+ EXPORT_SYMBOL(name##_global_lock);					\
+									\
+ void name##_global_unlock(void) {					\
+	int i;								\
+	rwlock_release(&name##_lock_dep_map, 1, _RET_IP_);		\
+	for_each_possible_cpu(i) {					\
+		struct rt_mutex *lock;					\
+		lock = &per_cpu(name##_lock, i);			\
+		__rt_spin_unlock(lock);					\
+	}								\
+ }									\
+ EXPORT_SYMBOL(name##_global_unlock);
+#endif /* PRREMPT_RT_FULL */
+
 #endif
diff --git a/include/linux/list.h b/include/linux/list.h
index cc6d2aa..7a9851b 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -362,6 +362,17 @@
 	list_entry((ptr)->next, type, member)
 
 /**
+ * list_last_entry - get the last element from a list
+ * @ptr:	the list head to take the element from.
+ * @type:	the type of the struct this is embedded in.
+ * @member:	the name of the list_struct within the struct.
+ *
+ * Note, that list is expected to be not empty.
+ */
+#define list_last_entry(ptr, type, member) \
+	list_entry((ptr)->prev, type, member)
+
+/**
  * list_for_each	-	iterate over a list
  * @pos:	the &struct list_head to use as a loop cursor.
  * @head:	the head for your list.
diff --git a/include/linux/list_bl.h b/include/linux/list_bl.h
index 31f9d75..becd7a6 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 +33,22 @@
 
 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)
+
+static inline void INIT_HLIST_BL_HEAD(struct hlist_bl_head *h)
+{
+	h->first = NULL;
+#ifdef CONFIG_PREEMPT_RT_BASE
+	raw_spin_lock_init(&h->lock);
+#endif
+}
 
 static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h)
 {
@@ -117,12 +127,26 @@
 
 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
 }
 
 /**
diff --git a/include/linux/locallock.h b/include/linux/locallock.h
new file mode 100644
index 0000000..a5eea5d
--- /dev/null
+++ b/include/linux/locallock.h
@@ -0,0 +1,253 @@
+#ifndef _LINUX_LOCALLOCK_H
+#define _LINUX_LOCALLOCK_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)
+
+static inline void __local_lock(struct local_irq_lock *lv)
+{
+	if (lv->owner != current) {
+		spin_lock(&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)
+
+static inline int __local_trylock(struct local_irq_lock *lv)
+{
+	if (lv->owner != current && spin_trylock(&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(&lv->lock);
+}
+
+#define local_unlock(lvar)					\
+	do {							\
+		__local_unlock(&__get_cpu_var(lvar));		\
+		put_local_var(lvar);				\
+	} 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(&__get_cpu_var(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 = __get_cpu_var(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(&__get_cpu_var(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);					\
+		&__get_cpu_var(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.h b/include/linux/mm.h
index e5ee683..82a8112 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1198,27 +1198,59 @@
  * overflow into the next struct page (as it might with DEBUG_SPINLOCK).
  * When freeing, reset page->mapping so free_pages_check won't complain.
  */
+#ifndef CONFIG_PREEMPT_RT_FULL
+
 #define __pte_lockptr(page)	&((page)->ptl)
-#define pte_lock_init(_page)	do {					\
-	spin_lock_init(__pte_lockptr(_page));				\
-} while (0)
+
+static inline struct page *pte_lock_init(struct page *page)
+{
+	spin_lock_init(__pte_lockptr(page));
+	return page;
+}
+
 #define pte_lock_deinit(page)	((page)->mapping = NULL)
+
+#else /* !PREEMPT_RT_FULL */
+
+/*
+ * On PREEMPT_RT_FULL the spinlock_t's are too large to embed in the
+ * page frame, hence it only has a pointer and we need to dynamically
+ * allocate the lock when we allocate PTE-pages.
+ *
+ * This is an overall win, since only a small fraction of the pages
+ * will be PTE pages under normal circumstances.
+ */
+
+#define __pte_lockptr(page)	((page)->ptl)
+
+extern struct page *pte_lock_init(struct page *page);
+extern void pte_lock_deinit(struct page *page);
+
+#endif /* PREEMPT_RT_FULL */
+
 #define pte_lockptr(mm, pmd)	({(void)(mm); __pte_lockptr(pmd_page(*(pmd)));})
 #else	/* !USE_SPLIT_PTLOCKS */
 /*
  * We use mm->page_table_lock to guard all pagetable pages of the mm.
  */
-#define pte_lock_init(page)	do {} while (0)
+static inline struct page *pte_lock_init(struct page *page) { return page; }
 #define pte_lock_deinit(page)	do {} while (0)
 #define pte_lockptr(mm, pmd)	({(void)(pmd); &(mm)->page_table_lock;})
 #endif /* USE_SPLIT_PTLOCKS */
 
-static inline void pgtable_page_ctor(struct page *page)
+static inline struct page *__pgtable_page_ctor(struct page *page)
 {
-	pte_lock_init(page);
-	inc_zone_page_state(page, NR_PAGETABLE);
+	page = pte_lock_init(page);
+	if (page)
+		inc_zone_page_state(page, NR_PAGETABLE);
+	return page;
 }
 
+#define pgtable_page_ctor(page)				\
+do {							\
+	page = __pgtable_page_ctor(page);		\
+} while (0)
+
 static inline void pgtable_page_dtor(struct page *page)
 {
 	pte_lock_deinit(page);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index de3a321..d61475b 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -12,6 +12,7 @@
 #include <linux/completion.h>
 #include <linux/cpumask.h>
 #include <linux/page-debug-flags.h>
+#include <linux/rcupdate.h>
 #include <asm/page.h>
 #include <asm/mmu.h>
 
@@ -118,7 +119,11 @@
 						 * system if PG_buddy is set.
 						 */
 #if USE_SPLIT_PTLOCKS
-		spinlock_t ptl;
+# ifndef CONFIG_PREEMPT_RT_FULL
+	    spinlock_t ptl;
+# else
+	    spinlock_t *ptl;
+# endif
 #endif
 		struct kmem_cache *slab;	/* SLUB: Pointer to slab */
 		struct page *first_page;	/* Compound tail pages */
@@ -390,6 +395,9 @@
 #ifdef CONFIG_CPUMASK_OFFSTACK
 	struct cpumask cpumask_allocation;
 #endif
+#ifdef CONFIG_PREEMPT_RT_BASE
+	struct rcu_head delayed_drop;
+#endif
 };
 
 static inline void mm_init_cpumask(struct mm_struct *mm)
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index 9121595..bdf1da2 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -17,6 +17,17 @@
 
 #include <linux/atomic.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:
  *
@@ -95,13 +106,6 @@
 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) \
@@ -167,6 +171,9 @@
  */
 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);
 
 #ifndef CONFIG_HAVE_ARCH_MUTEX_CPU_RELAX
diff --git a/include/linux/mutex_rt.h b/include/linux/mutex_rt.h
new file mode 100644
index 0000000..c38a44b
--- /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 4b04097..aa44bb5 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1764,6 +1764,7 @@
 	unsigned		dropped;
 	struct sk_buff_head	input_pkt_queue;
 	struct napi_struct	backlog;
+	struct sk_buff_head	tofree_queue;
 };
 
 static inline void input_queue_head_incr(struct softnet_data *sd)
diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 32cddf7..bed90da2 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -186,6 +186,7 @@
 #ifdef __KERNEL__
 
 #include <linux/netdevice.h>
+#include <linux/locallock.h>
 
 /**
  * struct xt_action_param - parameters for matches/targets
@@ -466,6 +467,8 @@
  */
 DECLARE_PER_CPU(seqcount_t, xt_recseq);
 
+DECLARE_LOCAL_IRQ_LOCK(xt_write_lock);
+
 /**
  * xt_write_recseq_begin - start of a write section
  *
@@ -480,6 +483,9 @@
 {
 	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().
@@ -510,6 +516,7 @@
 	/* 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/of.h b/include/linux/of.h
index c81ef31..ea21881 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -71,7 +71,7 @@
 extern struct device_node *allnodes;
 extern struct device_node *of_chosen;
 extern struct device_node *of_aliases;
-extern rwlock_t devtree_lock;
+extern raw_spinlock_t devtree_lock;
 
 static inline bool of_have_populated_dt(void)
 {
diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h
index 961ecc7..2927c08 100644
--- a/include/linux/page_cgroup.h
+++ b/include/linux/page_cgroup.h
@@ -30,6 +30,10 @@
  */
 struct page_cgroup {
 	unsigned long flags;
+#ifdef CONFIG_PREEMPT_RT_BASE
+	spinlock_t pcg_lock;
+	spinlock_t pcm_lock;
+#endif
 	struct mem_cgroup *mem_cgroup;
 	struct list_head lru;		/* per cgroup LRU list */
 };
@@ -96,30 +100,54 @@
 	 * Don't take this lock in IRQ context.
 	 * This lock is for pc->mem_cgroup, USED, CACHE, MIGRATION
 	 */
+#ifndef CONFIG_PREEMPT_RT_BASE
 	bit_spin_lock(PCG_LOCK, &pc->flags);
+#else
+	spin_lock(&pc->pcg_lock);
+#endif
 }
 
 static inline void unlock_page_cgroup(struct page_cgroup *pc)
 {
+#ifndef CONFIG_PREEMPT_RT_BASE
 	bit_spin_unlock(PCG_LOCK, &pc->flags);
+#else
+	spin_unlock(&pc->pcg_lock);
+#endif
 }
 
 static inline void move_lock_page_cgroup(struct page_cgroup *pc,
 	unsigned long *flags)
 {
+#ifndef CONFIG_PREEMPT_RT_BASE
 	/*
 	 * We know updates to pc->flags of page cache's stats are from both of
 	 * usual context or IRQ context. Disable IRQ to avoid deadlock.
 	 */
 	local_irq_save(*flags);
 	bit_spin_lock(PCG_MOVE_LOCK, &pc->flags);
+#else
+	spin_lock_irqsave(&pc->pcm_lock, *flags);
+#endif
 }
 
 static inline void move_unlock_page_cgroup(struct page_cgroup *pc,
 	unsigned long *flags)
 {
+#ifndef CONFIG_PREEMPT_RT_BASE
 	bit_spin_unlock(PCG_MOVE_LOCK, &pc->flags);
 	local_irq_restore(*flags);
+#else
+	spin_unlock_irqrestore(&pc->pcm_lock, *flags);
+#endif
+}
+
+static inline void page_cgroup_lock_init(struct page_cgroup *pc)
+{
+#ifdef CONFIG_PREEMPT_RT_BASE
+	spin_lock_init(&pc->pcg_lock);
+	spin_lock_init(&pc->pcm_lock);
+#endif
 }
 
 #ifdef CONFIG_SPARSEMEM
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 9ca008f..58163cd 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -48,6 +48,31 @@
 	preempt_enable();				\
 } while (0)
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+# 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)
+#else
+# define get_local_var(var) (*({			\
+	migrate_disable();				\
+	&__get_cpu_var(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)
+#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 b152d44..7f33683 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 e86bf01..53c9382 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -48,15 +48,23 @@
 	barrier(); \
 } while (0)
 
-#define preempt_enable_no_resched() \
+#define __preempt_enable_no_resched() \
 do { \
 	barrier(); \
 	dec_preempt_count(); \
 } while (0)
 
+#ifndef CONFIG_PREEMPT_RT_BASE
+# define preempt_enable_no_resched()	__preempt_enable_no_resched()
+# define preempt_check_resched_rt()	do { } while (0)
+#else
+# define preempt_enable_no_resched()	preempt_enable()
+# define preempt_check_resched_rt()	preempt_check_resched()
+#endif
+
 #define preempt_enable() \
 do { \
-	preempt_enable_no_resched(); \
+	__preempt_enable_no_resched(); \
 	barrier(); \
 	preempt_check_resched(); \
 } while (0)
@@ -98,15 +106,38 @@
  * region.
  */
 #define preempt_disable()		barrier()
+#define __preempt_enable_no_resched()	barrier()
 #define preempt_enable_no_resched()	barrier()
 #define preempt_enable()		barrier()
 
 #define preempt_disable_notrace()		barrier()
 #define preempt_enable_no_resched_notrace()	barrier()
 #define preempt_enable_notrace()		barrier()
+#define preempt_check_resched_rt()	do { } while (0)
 
 #endif /* CONFIG_PREEMPT_COUNT */
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+# define preempt_disable_rt()		preempt_disable()
+# define preempt_enable_rt()		preempt_enable()
+# define preempt_disable_nort()		do { } while (0)
+# define preempt_enable_nort()		do { } while (0)
+# ifdef CONFIG_SMP
+   extern void migrate_disable(void);
+   extern void migrate_enable(void);
+# else /* CONFIG_SMP */
+#  define migrate_disable()		do { } while (0)
+#  define migrate_enable()		do { } while (0)
+# endif /* CONFIG_SMP */
+#else
+# define preempt_disable_rt()		do { } while (0)
+# define preempt_enable_rt()		do { } while (0)
+# 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 f0e22f7..a53adf6 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -88,8 +88,15 @@
 	return 0;
 }
 
+#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
 
 extern int printk_needs_cpu(int cpu);
 extern void printk_tick(void);
@@ -109,7 +116,6 @@
 #define printk_ratelimit() __printk_ratelimit(__func__)
 extern bool printk_timed_ratelimit(unsigned long *caller_jiffies,
 				   unsigned int interval_msec);
-
 extern int printk_delay_msec;
 extern int dmesg_restrict;
 extern int kptr_restrict;
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 9d4539c..6b4bdf2 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -231,7 +231,13 @@
 				unsigned long index, unsigned long max_scan);
 unsigned long radix_tree_prev_hole(struct radix_tree_root *root,
 				unsigned long index, unsigned long max_scan);
+
+#ifndef CONFIG_PREEMPT_RT_FULL
 int radix_tree_preload(gfp_t gfp_mask);
+#else
+static inline int radix_tree_preload(gfp_t gm) { return 0; }
+#endif
+
 void radix_tree_init(void);
 void *radix_tree_tag_set(struct radix_tree_root *root,
 			unsigned long index, unsigned int tag);
@@ -256,7 +262,7 @@
 
 static inline void radix_tree_preload_end(void)
 {
-	preempt_enable();
+	preempt_enable_nort();
 }
 
 #endif /* _LINUX_RADIX_TREE_H */
diff --git a/include/linux/random.h b/include/linux/random.h
index f5e1311..1622993 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -53,7 +53,7 @@
 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 void get_random_bytes_arch(void *buf, int nbytes);
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 2cf4226..0e6fb5c 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -92,6 +92,9 @@
 
 #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.
@@ -112,6 +115,7 @@
  */
 extern void call_rcu_bh(struct rcu_head *head,
 			void (*func)(struct rcu_head *head));
+#endif
 
 /**
  * call_rcu_sched() - Queue an RCU for invocation after sched grace period.
@@ -147,6 +151,11 @@
  * 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 */
 
@@ -170,6 +179,8 @@
 	return 0;
 }
 
+#define sched_rcu_preempt_depth()	rcu_preempt_depth()
+
 #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
 
 /* Internal to kernel */
@@ -274,7 +285,14 @@
  * rcu_read_lock_bh_held() is defined out of line to avoid #include-file
  * hell.
  */
+#ifdef CONFIG_PREEMPT_RT_FULL
+static inline int rcu_read_lock_bh_held(void)
+{
+	return rcu_read_lock_held();
+}
+#else
 extern int rcu_read_lock_bh_held(void);
+#endif
 
 /**
  * rcu_read_lock_sched_held() - might we be in RCU-sched read-side critical section?
@@ -677,8 +695,12 @@
 static inline void rcu_read_lock_bh(void)
 {
 	local_bh_disable();
+#ifdef CONFIG_PREEMPT_RT_FULL
+	rcu_read_lock();
+#else
 	__acquire(RCU_BH);
 	rcu_read_acquire_bh();
+#endif
 }
 
 /*
@@ -688,8 +710,12 @@
  */
 static inline void rcu_read_unlock_bh(void)
 {
+#ifdef CONFIG_PREEMPT_RT_FULL
+	rcu_read_unlock();
+#else
 	rcu_read_release_bh();
 	__release(RCU_BH);
+#endif
 	local_bh_enable();
 }
 
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 6745846..6e503a3 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -57,7 +57,11 @@
 
 #endif /* #else #ifdef CONFIG_TREE_PREEMPT_RCU */
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 extern void synchronize_rcu_bh(void);
+#else
+# define synchronize_rcu_bh	synchronize_rcu
+#endif
 extern void synchronize_sched_expedited(void);
 extern void synchronize_rcu_expedited(void);
 
@@ -67,19 +71,29 @@
 }
 
 extern void rcu_barrier(void);
+#ifdef CONFIG_PREEMPT_RT_FULL
+# define rcu_barrier_bh		rcu_barrier
+#else
 extern void rcu_barrier_bh(void);
+#endif
 extern void rcu_barrier_sched(void);
 
 extern unsigned long rcutorture_testseq;
 extern unsigned long rcutorture_vernum;
 extern long rcu_batches_completed(void);
-extern long rcu_batches_completed_bh(void);
 extern long rcu_batches_completed_sched(void);
 
 extern void rcu_force_quiescent_state(void);
-extern void rcu_bh_force_quiescent_state(void);
 extern void rcu_sched_force_quiescent_state(void);
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+extern void rcu_bh_force_quiescent_state(void);
+extern 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
+
 /* A context switch is a grace period for RCU-sched and RCU-bh. */
 static inline int rcu_blocking_is_gp(void)
 {
diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h
index de17134..9340b86 100644
--- a/include/linux/rtmutex.h
+++ b/include/linux/rtmutex.h
@@ -14,7 +14,7 @@
 
 #include <linux/linkage.h>
 #include <linux/plist.h>
-#include <linux/spinlock_types.h>
+#include <linux/spinlock_types_raw.h>
 
 extern int max_lock_depth; /* for sysctl */
 
@@ -29,9 +29,10 @@
 	raw_spinlock_t		wait_lock;
 	struct plist_head	wait_list;
 	struct task_struct	*owner;
-#ifdef CONFIG_DEBUG_RT_MUTEXES
 	int			save_state;
-	const char 		*name, *file;
+#ifdef CONFIG_DEBUG_RT_MUTEXES
+	const char		*file;
+	const char		*name;
 	int			line;
 	void			*magic;
 #endif
@@ -56,19 +57,39 @@
 #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__)
+
+# define rt_mutex_init(mutex)					\
+	do {							\
+		raw_spin_lock_init(&(mutex)->wait_lock);	\
+		__rt_mutex_init(mutex, #mutex);			\
+	} while (0)
+
  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_init(mutex)					\
+	do {							\
+		raw_spin_lock_init(&(mutex)->wait_lock);	\
+		__rt_mutex_init(mutex, #mutex);			\
+	} while (0)
+
 # 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) \
 	, .wait_list = PLIST_HEAD_INIT(mutexname.wait_list) \
 	, .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)
@@ -88,11 +109,10 @@
 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,
-						int detect_deadlock);
+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,
-					int detect_deadlock);
+			       struct hrtimer_sleeper *timeout);
 
 extern int rt_mutex_trylock(struct rt_mutex *lock);
 
diff --git a/include/linux/rwlock_rt.h b/include/linux/rwlock_rt.h
new file mode 100644
index 0000000..853ee36
--- /dev/null
+++ b/include/linux/rwlock_rt.h
@@ -0,0 +1,123 @@
+#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);	\
+		migrate_disable();			\
+		flags = rt_read_lock_irqsave(lock);	\
+	} while (0)
+
+#define write_lock_irqsave(lock, flags)			\
+	do {						\
+		typecheck(unsigned long, flags);	\
+		migrate_disable();			\
+		flags = rt_write_lock_irqsave(lock);	\
+	} while (0)
+
+#define read_lock(lock)					\
+	do {						\
+		migrate_disable();			\
+		rt_read_lock(lock);			\
+	} while (0)
+
+#define read_lock_bh(lock)				\
+	do {						\
+		local_bh_disable();			\
+		migrate_disable();			\
+		rt_read_lock(lock);			\
+	} while (0)
+
+#define read_lock_irq(lock)	read_lock(lock)
+
+#define write_lock(lock)				\
+	do {						\
+		migrate_disable();			\
+		rt_write_lock(lock);			\
+	} while (0)
+
+#define write_lock_bh(lock)				\
+	do {						\
+		local_bh_disable();			\
+		migrate_disable();			\
+		rt_write_lock(lock);			\
+	} while (0)
+
+#define write_lock_irq(lock)	write_lock(lock)
+
+#define read_unlock(lock)				\
+	do {						\
+		rt_read_unlock(lock);			\
+		migrate_enable();			\
+	} while (0)
+
+#define read_unlock_bh(lock)				\
+	do {						\
+		rt_read_unlock(lock);			\
+		migrate_enable();			\
+		local_bh_enable();			\
+	} while (0)
+
+#define read_unlock_irq(lock)	read_unlock(lock)
+
+#define write_unlock(lock)				\
+	do {						\
+		rt_write_unlock(lock);			\
+		migrate_enable();			\
+	} while (0)
+
+#define write_unlock_bh(lock)				\
+	do {						\
+		rt_write_unlock(lock);			\
+		migrate_enable();			\
+		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);			\
+		migrate_enable();			\
+	} while (0)
+
+#define write_unlock_irqrestore(lock, flags) \
+	do {						\
+		typecheck(unsigned long, flags);	\
+		(void) flags;				\
+		rt_write_unlock(lock);			\
+		migrate_enable();			\
+	} while (0)
+
+#endif
diff --git a/include/linux/rwlock_types.h b/include/linux/rwlock_types.h
index cc0072e..d0da966 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 @@
 				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 0000000..b138321
--- /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 63d4065..209be4b 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -17,6 +17,10 @@
 #include <asm/system.h>
 #include <linux/atomic.h>
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+#include <linux/rwsem_rt.h>
+#else /* PREEMPT_RT_FULL */
+
 struct rw_semaphore;
 
 #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK
@@ -131,4 +135,6 @@
 # define down_write_nested(sem, subclass)	down_write(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 0000000..802c690
--- /dev/null
+++ b/include/linux/rwsem_rt.h
@@ -0,0 +1,105 @@
+#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, char *name,
+				     struct lock_class_key *key);
+
+# define rt_init_rwsem(sem)				\
+do {							\
+	static struct lock_class_key __key;		\
+							\
+	rt_mutex_init(&(sem)->lock);			\
+	__rt_rwsem_init((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_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 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 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 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_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);
+}
+
+#endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 44e5f47..232390a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -63,6 +63,7 @@
 #include <linux/nodemask.h>
 #include <linux/mm_types.h>
 
+#include <asm/kmap_types.h>
 #include <asm/system.h>
 #include <asm/page.h>
 #include <asm/ptrace.h>
@@ -91,6 +92,7 @@
 #include <linux/latencytop.h>
 #include <linux/cred.h>
 #include <linux/llist.h>
+#include <linux/hardirq.h>
 
 #include <asm/processor.h>
 
@@ -360,6 +362,7 @@
 extern signed long schedule_timeout_killable(signed long timeout);
 extern signed long schedule_timeout_uninterruptible(signed long timeout);
 asmlinkage void schedule(void);
+extern void schedule_preempt_disabled(void);
 extern int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner);
 
 struct nsproxy;
@@ -1075,6 +1078,7 @@
 #define WF_SYNC		0x01		/* waker goes to sleep after wakup */
 #define WF_FORK		0x02		/* child wakeup after fork */
 #define WF_MIGRATED	0x04		/* internal use, task got migrated */
+#define WF_LOCK_SLEEPER	0x08		/* wakeup spinlock "sleeper" */
 
 #define ENQUEUE_WAKEUP		1
 #define ENQUEUE_HEAD		2
@@ -1225,6 +1229,7 @@
 
 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 */
@@ -1264,6 +1269,12 @@
 #endif
 
 	unsigned int policy;
+#ifdef CONFIG_PREEMPT_RT_FULL
+	int migrate_disable;
+#ifdef CONFIG_SCHED_DEBUG
+	int migrate_disable_atomic;
+#endif
+#endif
 	cpumask_t cpus_allowed;
 
 #ifdef CONFIG_PREEMPT_RCU
@@ -1362,6 +1373,9 @@
 
 	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
@@ -1395,10 +1409,15 @@
 /* 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;
@@ -1438,6 +1457,9 @@
 	/* mutex deadlock detection */
 	struct mutex_waiter *blocked_on;
 #endif
+#ifdef CONFIG_PREEMPT_RT_FULL
+	int pagefault_disabled;
+#endif
 #ifdef CONFIG_TRACE_IRQFLAGS
 	unsigned int irq_events;
 	unsigned long hardirq_enable_ip;
@@ -1569,6 +1591,12 @@
 	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_CGROUP_MEM_RES_CTLR /* memcg uses this to do batch job */
 	struct memcg_batch_info {
@@ -1581,10 +1609,32 @@
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 	atomic_t ptrace_bp_refcnt;
 #endif
+#ifdef CONFIG_PREEMPT_RT_BASE
+	struct rcu_head put_rcu;
+	int softirq_nestcnt;
+#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_PREEMPT
+	unsigned long preempt_disable_ip;
+#endif
 };
 
-/* Future-safe accessor for struct task_struct's cpus_allowed. */
-#define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
+#ifdef CONFIG_PREEMPT_RT_FULL
+static inline bool cur_pf_disabled(void) { return current->pagefault_disabled; }
+#else
+static inline bool cur_pf_disabled(void) { return false; }
+#endif
+
+static inline bool pagefault_disabled(void)
+{
+	return in_atomic() || cur_pf_disabled();
+}
 
 /*
  * Priority of a process goes from 0..MAX_PRIO-1, valid RT
@@ -1772,6 +1822,15 @@
 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)
@@ -1779,6 +1838,7 @@
 	if (atomic_dec_and_test(&t->usage))
 		__put_task_struct(t);
 }
+#endif
 
 extern void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
 extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st);
@@ -1804,6 +1864,7 @@
 #define PF_FROZEN	0x00010000	/* frozen for system suspend */
 #define PF_FSTRANS	0x00020000	/* inside a filesystem transaction */
 #define PF_KSWAPD	0x00040000	/* I am kswapd */
+#define PF_STOMPER	0x00080000	/* I am a stomp machine thread */
 #define PF_LESS_THROTTLE 0x00100000	/* Throttle me less: I clean memory */
 #define PF_KTHREAD	0x00200000	/* I am a kernel thread */
 #define PF_RANDOMIZE	0x00400000	/* randomize virtual address space */
@@ -1905,6 +1966,10 @@
 
 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)
@@ -1917,6 +1982,9 @@
 		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
@@ -2084,13 +2152,26 @@
 #ifdef CONFIG_RT_MUTEXES
 extern int rt_mutex_getprio(struct task_struct *p);
 extern void rt_mutex_setprio(struct task_struct *p, int prio);
+extern int rt_mutex_check_prio(struct task_struct *task, int newprio);
 extern void rt_mutex_adjust_pi(struct task_struct *p);
+static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
+{
+	return tsk->pi_blocked_on != NULL;
+}
 #else
 static inline int rt_mutex_getprio(struct task_struct *p)
 {
 	return p->normal_prio;
 }
+static inline int rt_mutex_check_prio(struct task_struct *task, int newprio)
+{
+	return 0;
+}
 # define rt_mutex_adjust_pi(p)		do { } while (0)
+static inline bool tsk_is_pi_blocked(struct task_struct *tsk)
+{
+	return false;
+}
 #endif
 
 extern bool yield_to(struct task_struct *p, bool preempt);
@@ -2105,6 +2186,14 @@
 extern int sched_setscheduler_nocheck(struct task_struct *, int,
 				      const struct sched_param *);
 extern struct task_struct *idle_task(int cpu);
+/**
+ * is_idle_task - is the specified task an idle task?
+ * @tsk: the task in question.
+ */
+static inline bool is_idle_task(struct task_struct *p)
+{
+	return p->pid == 0;
+}
 extern struct task_struct *curr_task(int cpu);
 extern void set_curr_task(int cpu, struct task_struct *p);
 
@@ -2170,6 +2259,7 @@
 
 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);
@@ -2260,12 +2350,24 @@
 
 /* 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 */
@@ -2568,7 +2670,7 @@
 
 extern int __cond_resched_lock(spinlock_t *lock);
 
-#ifdef CONFIG_PREEMPT_COUNT
+#if defined(CONFIG_PREEMPT_COUNT) && !defined(CONFIG_PREEMPT_RT_FULL)
 #define PREEMPT_LOCK_OFFSET	PREEMPT_OFFSET
 #else
 #define PREEMPT_LOCK_OFFSET	0
@@ -2579,12 +2681,16 @@
 	__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
 
 /*
  * Does a critical section need to be broken due to another
@@ -2656,6 +2762,26 @@
 
 #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)
+{
+#ifdef CONFIG_PREEMPT_RT_FULL
+	if (p->migrate_disable)
+		return cpumask_of(task_cpu(p));
+#endif
+
+	return &p->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 bb1fac5..4ea1409 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -30,92 +30,12 @@
 #include <linux/preempt.h>
 #include <asm/processor.h>
 
-typedef struct {
-	unsigned sequence;
-	spinlock_t lock;
-} seqlock_t;
-
-/*
- * These macros triggered gcc-3.x compile-time problems.  We think these are
- * OK now.  Be cautious.
- */
-#define __SEQLOCK_UNLOCKED(lockname) \
-		 { 0, __SPIN_LOCK_UNLOCKED(lockname) }
-
-#define seqlock_init(x)					\
-	do {						\
-		(x)->sequence = 0;			\
-		spin_lock_init(&(x)->lock);		\
-	} while (0)
-
-#define DEFINE_SEQLOCK(x) \
-		seqlock_t x = __SEQLOCK_UNLOCKED(x)
-
-/* Lock out other writers and update the count.
- * Acts like a normal spin_lock/unlock.
- * Don't need preempt_disable() because that is in the spin_lock already.
- */
-static inline void write_seqlock(seqlock_t *sl)
-{
-	spin_lock(&sl->lock);
-	++sl->sequence;
-	smp_wmb();
-}
-
-static inline void write_sequnlock(seqlock_t *sl)
-{
-	smp_wmb();
-	sl->sequence++;
-	spin_unlock(&sl->lock);
-}
-
-static inline int write_tryseqlock(seqlock_t *sl)
-{
-	int ret = spin_trylock(&sl->lock);
-
-	if (ret) {
-		++sl->sequence;
-		smp_wmb();
-	}
-	return ret;
-}
-
-/* Start of read calculation -- fetch last complete writer token */
-static __always_inline unsigned read_seqbegin(const seqlock_t *sl)
-{
-	unsigned ret;
-
-repeat:
-	ret = ACCESS_ONCE(sl->sequence);
-	if (unlikely(ret & 1)) {
-		cpu_relax();
-		goto repeat;
-	}
-	smp_rmb();
-
-	return ret;
-}
-
-/*
- * Test if reader processed invalid data.
- *
- * If sequence value changed then writer changed data while in section.
- */
-static __always_inline int read_seqretry(const seqlock_t *sl, unsigned start)
-{
-	smp_rmb();
-
-	return unlikely(sl->sequence != start);
-}
-
-
 /*
  * Version using sequence counter only.
  * This can be used when code has its own mutex protecting the
  * updating starting before the write_seqcountbeqin() and ending
  * after the write_seqcount_end().
  */
-
 typedef struct seqcount {
 	unsigned sequence;
 } seqcount_t;
@@ -197,7 +117,6 @@
 static inline int read_seqcount_retry(const seqcount_t *s, unsigned start)
 {
 	smp_rmb();
-
 	return __read_seqcount_retry(s, start);
 }
 
@@ -206,18 +125,30 @@
  * Sequence counter only version assumes that callers are using their
  * own mutexing.
  */
-static inline void write_seqcount_begin(seqcount_t *s)
+static inline void __write_seqcount_begin(seqcount_t *s)
 {
 	s->sequence++;
 	smp_wmb();
 }
 
-static inline void write_seqcount_end(seqcount_t *s)
+static inline void write_seqcount_begin(seqcount_t *s)
+{
+	preempt_disable_rt();
+	__write_seqcount_begin(s);
+}
+
+static inline void __write_seqcount_end(seqcount_t *s)
 {
 	smp_wmb();
 	s->sequence++;
 }
 
+static inline void write_seqcount_end(seqcount_t *s)
+{
+	__write_seqcount_end(s);
+	preempt_enable_rt();
+}
+
 /**
  * write_seqcount_barrier - invalidate in-progress read-side seq operations
  * @s: pointer to seqcount_t
@@ -231,31 +162,124 @@
 	s->sequence+=2;
 }
 
+typedef struct {
+	struct seqcount seqcount;
+	spinlock_t lock;
+} seqlock_t;
+
 /*
- * Possible sw/hw IRQ protected versions of the interfaces.
+ * These macros triggered gcc-3.x compile-time problems.  We think these are
+ * OK now.  Be cautious.
  */
+#define __SEQLOCK_UNLOCKED(lockname)			\
+	{						\
+		.seqcount = SEQCNT_ZERO,		\
+		.lock =	__SPIN_LOCK_UNLOCKED(lockname)	\
+	}
+
+#define seqlock_init(x)					\
+	do {						\
+		seqcount_init(&(x)->seqcount);		\
+		spin_lock_init(&(x)->lock);		\
+	} while (0)
+
+#define DEFINE_SEQLOCK(x) \
+		seqlock_t x = __SEQLOCK_UNLOCKED(x)
+
+/*
+ * 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 = 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_lock(&sl->lock);
+		spin_unlock(&sl->lock);
+		goto repeat;
+	}
+	return ret;
+}
+#endif
+
+static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
+{
+	return read_seqcount_retry(&sl->seqcount, start);
+}
+
+/*
+ * Lock out other writers and update the count.
+ * Acts like a normal spin_lock/unlock.
+ * Don't need preempt_disable() because that is in the spin_lock already.
+ */
+static inline void write_seqlock(seqlock_t *sl)
+{
+	spin_lock(&sl->lock);
+	__write_seqcount_begin(&sl->seqcount);
+}
+
+static inline void write_sequnlock(seqlock_t *sl)
+{
+	__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);
+}
+
+static inline void write_sequnlock_bh(seqlock_t *sl)
+{
+	__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);
+}
+
+static inline void write_sequnlock_irq(seqlock_t *sl)
+{
+	__write_seqcount_end(&sl->seqcount);
+	spin_unlock_irq(&sl->lock);
+}
+
+static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&sl->lock, flags);
+	__write_seqcount_begin(&sl->seqcount);
+	return flags;
+}
+
 #define write_seqlock_irqsave(lock, flags)				\
-	do { local_irq_save(flags); write_seqlock(lock); } while (0)
-#define write_seqlock_irq(lock)						\
-	do { local_irq_disable();   write_seqlock(lock); } while (0)
-#define write_seqlock_bh(lock)						\
-        do { local_bh_disable();    write_seqlock(lock); } while (0)
+	do { flags = __write_seqlock_irqsave(lock); } while (0)
 
-#define write_sequnlock_irqrestore(lock, flags)				\
-	do { write_sequnlock(lock); local_irq_restore(flags); } while(0)
-#define write_sequnlock_irq(lock)					\
-	do { write_sequnlock(lock); local_irq_enable(); } while(0)
-#define write_sequnlock_bh(lock)					\
-	do { write_sequnlock(lock); local_bh_enable(); } while(0)
-
-#define read_seqbegin_irqsave(lock, flags)				\
-	({ local_irq_save(flags);   read_seqbegin(lock); })
-
-#define read_seqretry_irqrestore(lock, iv, flags)			\
-	({								\
-		int ret = read_seqretry(lock, iv);			\
-		local_irq_restore(flags);				\
-		ret;							\
-	})
+static inline void
+write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags)
+{
+	__write_seqcount_end(&sl->seqcount);
+	spin_unlock_irqrestore(&sl->lock, flags);
+}
 
 #endif /* __LINUX_SEQLOCK_H */
diff --git a/include/linux/signal.h b/include/linux/signal.h
index a822300..a448900 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -229,6 +229,7 @@
 }
 
 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 1b4ea29..4257e3a 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -124,6 +124,7 @@
 
 	__u32		qlen;
 	spinlock_t	lock;
+	raw_spinlock_t	raw_lock;
 };
 
 struct sk_buff;
@@ -943,6 +944,12 @@
 	__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 8cc38d3..3001ba5 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -80,7 +80,6 @@
 
 int smp_call_function_any(const struct cpumask *mask,
 			  smp_call_func_t func, void *info, int wait);
-
 /*
  * Generic and arch helpers
  */
@@ -102,6 +101,22 @@
 int on_each_cpu(smp_call_func_t func, void *info, int wait);
 
 /*
+ * Call a function on processors specified by mask, which might include
+ * the local one.
+ */
+void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func,
+		void *info, bool wait);
+
+/*
+ * Call a function on each processor for which the supplied function
+ * cond_func returns a positive value. This may include the local
+ * processor.
+ */
+void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
+		smp_call_func_t func, void *info, bool wait,
+		gfp_t gfp_flags);
+
+/*
  * Mark the boot cpu "online" so that it can call console drivers in
  * printk() and can access its per-cpu storage.
  */
@@ -132,6 +147,36 @@
 		local_irq_enable();		\
 		0;				\
 	})
+/*
+ * Note we still need to test the mask even for UP
+ * because we actually can get an empty mask from
+ * code that on SMP might call us without the local
+ * CPU in the mask.
+ */
+#define on_each_cpu_mask(mask, func, info, wait) \
+	do {						\
+		if (cpumask_test_cpu(0, (mask))) {	\
+			local_irq_disable();		\
+			(func)(info);			\
+			local_irq_enable();		\
+		}					\
+	} while (0)
+/*
+ * Preemption is disabled here to make sure the cond_func is called under the
+ * same condtions in UP and SMP.
+ */
+#define on_each_cpu_cond(cond_func, func, info, wait, gfp_flags)\
+	do {							\
+		void *__info = (info);				\
+		preempt_disable();				\
+		if ((cond_func)(0, __info)) {			\
+			local_irq_disable();			\
+			(func)(__info);				\
+			local_irq_enable();			\
+		}						\
+		preempt_enable();				\
+	} while (0)
+
 static inline void smp_send_reschedule(int cpu) { }
 #define num_booting_cpus()			1
 #define smp_prepare_boot_cpu()			do {} while (0)
@@ -173,6 +218,9 @@
 #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 7df6c17..5fe7e40 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -254,7 +254,11 @@
 #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:
@@ -265,6 +269,10 @@
 # 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
  */
@@ -397,4 +405,6 @@
 #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 e253ccd..2a5ba05 100644
--- a/include/linux/spinlock_api_smp.h
+++ b/include/linux/spinlock_api_smp.h
@@ -191,6 +191,8 @@
 	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 0000000..28edba7
--- /dev/null
+++ b/include/linux/spinlock_rt.h
@@ -0,0 +1,167 @@
+#ifndef __LINUX_SPINLOCK_RT_H
+#define __LINUX_SPINLOCK_RT_H
+
+#ifndef __LINUX_SPINLOCK_H
+#error Do not include directly. Use spinlock.h
+#endif
+
+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)
+
+extern void __lockfunc rt_spin_lock(spinlock_t *lock);
+extern unsigned long __lockfunc rt_spin_lock_trace_flags(spinlock_t *lock);
+extern void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass);
+extern void __lockfunc rt_spin_unlock(spinlock_t *lock);
+extern void __lockfunc rt_spin_unlock_after_trylock_in_irq(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(struct rt_mutex *lock);
+extern void __lockfunc __rt_spin_unlock(struct rt_mutex *lock);
+
+#define spin_lock_local(lock)			rt_spin_lock(lock)
+#define spin_unlock_local(lock)			rt_spin_unlock(lock)
+
+#define spin_lock(lock)				\
+	do {					\
+		migrate_disable();		\
+		rt_spin_lock(lock);		\
+	} while (0)
+
+#define spin_lock_bh(lock)			\
+	do {					\
+		local_bh_disable();		\
+		migrate_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;				\
+	migrate_disable();			\
+	__locked = spin_do_trylock(lock);	\
+	if (!__locked)				\
+		migrate_enable();		\
+	__locked;				\
+})
+
+#ifdef CONFIG_LOCKDEP
+# define spin_lock_nested(lock, subclass)		\
+	do {						\
+		migrate_disable();			\
+		rt_spin_lock_nested(lock, subclass);	\
+	} while (0)
+
+# define spin_lock_irqsave_nested(lock, flags, subclass) \
+	do {						 \
+		typecheck(unsigned long, flags);	 \
+		flags = 0;				 \
+		migrate_disable();			 \
+		rt_spin_lock_nested(lock, subclass);	 \
+	} while (0)
+#else
+# define spin_lock_nested(lock, subclass)	spin_lock(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)				\
+	do {						\
+		rt_spin_unlock(lock);			\
+		migrate_enable();			\
+	} while (0)
+
+#define spin_unlock_bh(lock)				\
+	do {						\
+		rt_spin_unlock(lock);			\
+		migrate_enable();			\
+		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 73548eb..10bac71 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>
+#include <linux/spinlock_types_raw.h>
+
+#ifndef CONFIG_PREEMPT_RT_FULL
+# include <linux/spinlock_types_nort.h>
+# include <linux/rwlock_types.h>
 #else
-# include <linux/spinlock_types_up.h>
+# include <linux/rtmutex.h>
+# include <linux/spinlock_types_rt.h>
+# include <linux/rwlock_types_rt.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)
-
-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 0000000..f1dac1f
--- /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 0000000..edffc4d
--- /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 0000000..1fe8fc0
--- /dev/null
+++ b/include/linux/spinlock_types_rt.h
@@ -0,0 +1,49 @@
+#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
+
+/*
+ * 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/sysctl.h b/include/linux/sysctl.h
index 703cfa3..b954c41 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -932,6 +932,7 @@
 #include <linux/list.h>
 #include <linux/rcupdate.h>
 #include <linux/wait.h>
+#include <linux/atomic.h>
 
 /* For the /proc/sys support */
 struct ctl_table;
diff --git a/include/linux/timer.h b/include/linux/timer.h
index 6abd913..b703477 100644
--- a/include/linux/timer.h
+++ b/include/linux/timer.h
@@ -276,7 +276,7 @@
 
 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/uaccess.h b/include/linux/uaccess.h
index 5ca0951..44b3751 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -6,37 +6,36 @@
 
 /*
  * These routines enable/disable the pagefault handler in that
- * it will not take any locks and go straight to the fixup table.
- *
- * They have great resemblance to the preempt_disable/enable calls
- * and in fact they are identical; this is because currently there is
- * no other way to make the pagefault handlers do this. So we do
- * disable preemption but we don't necessarily care about that.
+ * it will not take any MM locks and go straight to the fixup table.
  */
-static inline void pagefault_disable(void)
+static inline void raw_pagefault_disable(void)
 {
 	inc_preempt_count();
-	/*
-	 * make sure to have issued the store before a pagefault
-	 * can hit.
-	 */
 	barrier();
 }
 
+static inline void raw_pagefault_enable(void)
+{
+	barrier();
+	dec_preempt_count();
+	barrier();
+	preempt_check_resched();
+}
+
+#ifndef CONFIG_PREEMPT_RT_FULL
+static inline void pagefault_disable(void)
+{
+	raw_pagefault_disable();
+}
+
 static inline void pagefault_enable(void)
 {
-	/*
-	 * make sure to issue those last loads/stores before enabling
-	 * the pagefault handler again.
-	 */
-	barrier();
-	dec_preempt_count();
-	/*
-	 * make sure we do..
-	 */
-	barrier();
-	preempt_check_resched();
+	raw_pagefault_enable();
 }
+#else
+extern void pagefault_disable(void);
+extern void pagefault_enable(void);
+#endif
 
 #ifndef ARCH_HAS_NOCACHE_UACCESS
 
@@ -77,9 +76,9 @@
 		mm_segment_t old_fs = get_fs();		\
 							\
 		set_fs(KERNEL_DS);			\
-		pagefault_disable();			\
+		raw_pagefault_disable();		\
 		ret = __copy_from_user_inatomic(&(retval), (__force typeof(retval) __user *)(addr), sizeof(retval));		\
-		pagefault_enable();			\
+		raw_pagefault_enable();			\
 		set_fs(old_fs);				\
 		ret;					\
 	})
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 65efb92d..1b3f2ef 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -29,7 +29,9 @@
 
 static inline void __count_vm_event(enum vm_event_item item)
 {
+	preempt_disable_rt();
 	__this_cpu_inc(vm_event_states.event[item]);
+	preempt_enable_rt();
 }
 
 static inline void count_vm_event(enum vm_event_item item)
@@ -39,7 +41,9 @@
 
 static inline void __count_vm_events(enum vm_event_item item, long delta)
 {
+	preempt_disable_rt();
 	__this_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-simple.h b/include/linux/wait-simple.h
new file mode 100644
index 0000000..44fee60
--- /dev/null
+++ b/include/linux/wait-simple.h
@@ -0,0 +1,172 @@
+#ifndef _LINUX_WAIT_SIMPLE_H
+#define _LINUX_WAIT_SIMPLE_H
+
+#include <linux/spinlock.h>
+#include <linux/list.h>
+
+#include <asm/current.h>
+
+struct swaiter {
+	struct task_struct	*task;
+	struct list_head	node;
+};
+
+#define DEFINE_SWAITER(name)					\
+	struct swaiter name = {					\
+		.task	= current,				\
+		.node	= LIST_HEAD_INIT((name).node),		\
+	}
+
+struct swait_head {
+	raw_spinlock_t		lock;
+	struct list_head	list;
+};
+
+#define SWAIT_HEAD_INITIALIZER(name) {				\
+		.lock	= __RAW_SPIN_LOCK_UNLOCKED(name.lock),	\
+		.list	= LIST_HEAD_INIT((name).list),		\
+	}
+
+#define DEFINE_SWAIT_HEAD(name)					\
+	struct swait_head name = SWAIT_HEAD_INITIALIZER(name)
+
+extern void __init_swait_head(struct swait_head *h, struct lock_class_key *key);
+
+#define init_swait_head(swh)					\
+	do {							\
+		static struct lock_class_key __key;		\
+								\
+		__init_swait_head((swh), &__key);		\
+	} while (0)
+
+/*
+ * Waiter functions
+ */
+extern void swait_prepare_locked(struct swait_head *head, struct swaiter *w);
+extern void swait_prepare(struct swait_head *head, struct swaiter *w, int state);
+extern void swait_finish_locked(struct swait_head *head, struct swaiter *w);
+extern void swait_finish(struct swait_head *head, struct swaiter *w);
+
+/*
+ * Wakeup functions
+ */
+extern unsigned int __swait_wake(struct swait_head *head, unsigned int state, unsigned int num);
+extern unsigned int __swait_wake_locked(struct swait_head *head, unsigned int state, unsigned int num);
+
+#define swait_wake(head)			__swait_wake(head, TASK_NORMAL, 1)
+#define swait_wake_interruptible(head)		__swait_wake(head, TASK_INTERRUPTIBLE, 1)
+#define swait_wake_all(head)			__swait_wake(head, TASK_NORMAL, 0)
+#define swait_wake_all_interruptible(head)	__swait_wake(head, TASK_INTERRUPTIBLE, 0)
+
+/*
+ * Event API
+ */
+#define __swait_event(wq, condition)					\
+do {									\
+	DEFINE_SWAITER(__wait);						\
+									\
+	for (;;) {							\
+		swait_prepare(&wq, &__wait, TASK_UNINTERRUPTIBLE);	\
+		if (condition)						\
+			break;						\
+		schedule();						\
+	}								\
+	swait_finish(&wq, &__wait);					\
+} while (0)
+
+/**
+ * swait_event - sleep until a condition gets true
+ * @wq: the waitqueue to wait on
+ * @condition: a C expression for the event to wait for
+ *
+ * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
+ * @condition evaluates to true. The @condition is checked each time
+ * the waitqueue @wq is woken up.
+ *
+ * wake_up() has to be called after changing any variable that could
+ * change the result of the wait condition.
+ */
+#define swait_event(wq, condition)					\
+do {									\
+	if (condition)							\
+		break;							\
+	__swait_event(wq, condition);					\
+} while (0)
+
+#define __swait_event_interruptible(wq, condition, ret)			\
+do {									\
+	DEFINE_SWAITER(__wait);						\
+									\
+	for (;;) {							\
+		swait_prepare(&wq, &__wait, TASK_INTERRUPTIBLE);	\
+		if (condition)						\
+			break;						\
+		if (signal_pending(current)) {				\
+			ret = -ERESTARTSYS;				\
+			break;						\
+		}							\
+		schedule();						\
+	}								\
+	swait_finish(&wq, &__wait);					\
+} while (0)
+
+/**
+ * swait_event_interruptible - sleep until a condition gets true
+ * @wq: the waitqueue to wait on
+ * @condition: a C expression for the event to wait for
+ *
+ * The process is put to sleep (TASK_INTERRUPTIBLE) until the
+ * @condition evaluates to true. The @condition is checked each time
+ * the waitqueue @wq is woken up.
+ *
+ * wake_up() has to be called after changing any variable that could
+ * change the result of the wait condition.
+ */
+#define swait_event_interruptible(wq, condition)			\
+({									\
+	int __ret = 0;							\
+	if (!(condition))						\
+		__swait_event_interruptible(wq, condition, __ret);	\
+	__ret;								\
+})
+
+#define __swait_event_timeout(wq, condition, ret)			\
+do {									\
+	DEFINE_SWAITER(__wait);						\
+									\
+	for (;;) {							\
+		swait_prepare(&wq, &__wait, TASK_UNINTERRUPTIBLE);	\
+		if (condition)						\
+			break;						\
+		ret = schedule_timeout(ret);				\
+		if (!ret)						\
+			break;						\
+	}								\
+	swait_finish(&wq, &__wait);					\
+} while (0)
+
+/**
+ * swait_event_timeout - sleep until a condition gets true or a timeout elapses
+ * @wq: the waitqueue to wait on
+ * @condition: a C expression for the event to wait for
+ * @timeout: timeout, in jiffies
+ *
+ * The process is put to sleep (TASK_UNINTERRUPTIBLE) until the
+ * @condition evaluates to true. The @condition is checked each time
+ * the waitqueue @wq is woken up.
+ *
+ * wake_up() has to be called after changing any variable that could
+ * change the result of the wait condition.
+ *
+ * The function returns 0 if the @timeout elapsed, and the remaining
+ * jiffies if the condition evaluated to true before the timeout elapsed.
+ */
+#define swait_event_timeout(wq, condition, timeout)			\
+({									\
+	long __ret = timeout;						\
+	if (!(condition))						\
+		__swait_event_timeout(wq, condition, __ret);		\
+	__ret;								\
+})
+
+#endif
diff --git a/include/linux/wait.h b/include/linux/wait.h
index e007f76..497fa20 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -157,7 +157,7 @@
 void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key);
 void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr,
 			void *key);
-void __wake_up_locked(wait_queue_head_t *q, unsigned int mode);
+void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr);
 void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr);
 void __wake_up_bit(wait_queue_head_t *, void *, int);
 int __wait_on_bit(wait_queue_head_t *, struct wait_bit_queue *, int (*)(void *), unsigned);
@@ -170,7 +170,8 @@
 #define wake_up(x)			__wake_up(x, TASK_NORMAL, 1, NULL)
 #define wake_up_nr(x, nr)		__wake_up(x, TASK_NORMAL, nr, NULL)
 #define wake_up_all(x)			__wake_up(x, TASK_NORMAL, 0, NULL)
-#define wake_up_locked(x)		__wake_up_locked((x), TASK_NORMAL)
+#define wake_up_locked(x)		__wake_up_locked((x), TASK_NORMAL, 1)
+#define wake_up_all_locked(x)		__wake_up_locked((x), TASK_NORMAL, 0)
 
 #define wake_up_interruptible(x)	__wake_up(x, TASK_INTERRUPTIBLE, 1, NULL)
 #define wake_up_interruptible_nr(x, nr)	__wake_up(x, TASK_INTERRUPTIBLE, nr, NULL)
diff --git a/include/linux/work-simple.h b/include/linux/work-simple.h
new file mode 100644
index 0000000..f175fa9
--- /dev/null
+++ b/include/linux/work-simple.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/net/neighbour.h b/include/net/neighbour.h
index 2720884..6fda9fa 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -385,7 +385,7 @@
 
 #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 d786b4f..8cef1d1 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -47,6 +47,7 @@
 
 	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 0000000..28646db
--- /dev/null
+++ b/include/trace/events/hist.h
@@ -0,0 +1,69 @@
+#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)
+#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 0000000..d6b5d77
--- /dev/null
+++ b/include/trace/events/latency_hist.h
@@ -0,0 +1,30 @@
+#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/init/Kconfig b/init/Kconfig
index b8dc1de..5fb23d9 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -469,7 +469,7 @@
 
 config RCU_FAST_NO_HZ
 	bool "Accelerate last non-dyntick-idle CPU's grace periods"
-	depends on TREE_RCU && NO_HZ && SMP
+	depends on TREE_RCU && NO_HZ && SMP && !PREEMPT_RT_FULL
 	default n
 	help
 	  This option causes RCU to attempt to accelerate grace periods
@@ -494,7 +494,7 @@
 config RCU_BOOST
 	bool "Enable RCU priority boosting"
 	depends on RT_MUTEXES && PREEMPT_RCU
-	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.
@@ -732,6 +732,7 @@
 	bool "Group scheduling for SCHED_RR/FIFO"
 	depends on EXPERIMENTAL
 	depends on CGROUP_SCHED
+	depends on !PREEMPT_RT_FULL
 	default n
 	help
 	  This feature lets you explicitly allocate real CPU bandwidth
@@ -1240,6 +1241,7 @@
 
 config SLUB
 	bool "SLUB (Unqueued Allocator)"
+	depends on !PREEMPT_RT_FULL
 	help
 	   SLUB is a slab allocator that minimizes cache line usage
 	   instead of managing queues of cached objects (SLAB approach).
@@ -1251,6 +1253,7 @@
 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
diff --git a/init/Makefile b/init/Makefile
index 0bf677a..6b473cd 100644
--- a/init/Makefile
+++ b/init/Makefile
@@ -29,4 +29,4 @@
 include/generated/compile.h: FORCE
 	@$($(quiet)chk_compile.h)
 	$(Q)$(CONFIG_SHELL) $(srctree)/scripts/mkcompile_h $@ \
-	"$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CC) $(KBUILD_CFLAGS)"
+	"$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CONFIG_PREEMPT_RT_FULL)" "$(CC) $(KBUILD_CFLAGS)"
diff --git a/init/main.c b/init/main.c
index e937d9b..267e2c2 100644
--- a/init/main.c
+++ b/init/main.c
@@ -69,6 +69,7 @@
 #include <linux/slab.h>
 #include <linux/perf_event.h>
 #include <linux/random.h>
+#include <linux/posix-timers.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>
@@ -379,11 +380,8 @@
 	 * at least once to get things moving:
 	 */
 	init_idle_bootup_task(current);
-	preempt_enable_no_resched();
-	schedule();
-
+	schedule_preempt_disabled();
 	/* Call into cpu_idle with preempt disabled */
-	preempt_disable();
 	cpu_idle();
 }
 
@@ -503,6 +501,7 @@
 	setup_command_line(command_line);
 	setup_nr_cpu_ids();
 	setup_per_cpu_areas();
+	softirq_early_init();
 	smp_prepare_boot_cpu();	/* arch-specific boot-cpu hooks */
 
 	build_all_zonelists(NULL);
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 5b4293d..eec1d99 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -820,12 +820,17 @@
 				  struct msg_msg *message,
 				  struct ext_wait_queue *receiver)
 {
+	/*
+	 * Keep them in one critical section for PREEMPT_RT:
+	 */
+	preempt_disable_rt();
 	receiver->msg = message;
 	list_del(&receiver->list);
 	receiver->state = STATE_PENDING;
 	wake_up_process(receiver->task);
 	smp_wmb();
 	receiver->state = STATE_READY;
+	preempt_enable_rt();
 }
 
 /* pipelined_receive() - if there is task waiting in sys_mq_timedsend()
@@ -839,15 +844,19 @@
 		wake_up_interruptible(&info->wait_q);
 		return;
 	}
+	/*
+	 * Keep them in one critical section for PREEMPT_RT:
+	 */
+	preempt_disable_rt();
 	msg_insert(sender->msg, info);
 	list_del(&sender->list);
 	sender->state = STATE_PENDING;
 	wake_up_process(sender->task);
 	smp_wmb();
 	sender->state = STATE_READY;
+	preempt_enable_rt();
 }
-
-SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr,
+ SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr,
 		size_t, msg_len, unsigned int, msg_prio,
 		const struct timespec __user *, u_abs_timeout)
 {
diff --git a/ipc/msg.c b/ipc/msg.c
index 25f1a61..876b844 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -259,12 +259,20 @@
 	while (tmp != &msq->q_receivers) {
 		struct msg_receiver *msr;
 
+		/*
+		 * Make sure that the wakeup doesnt preempt
+		 * this CPU prematurely. (on PREEMPT_RT)
+		 */
+		preempt_disable_rt();
+
 		msr = list_entry(tmp, struct msg_receiver, r_list);
 		tmp = tmp->next;
 		msr->r_msg = NULL;
 		wake_up_process(msr->r_tsk);
 		smp_mb();
 		msr->r_msg = ERR_PTR(res);
+
+		preempt_enable_rt();
 	}
 }
 
@@ -613,6 +621,12 @@
 		    !security_msg_queue_msgrcv(msq, msg, msr->r_tsk,
 					       msr->r_msgtype, msr->r_mode)) {
 
+			/*
+			 * Make sure that the wakeup doesnt preempt
+			 * this CPU prematurely. (on PREEMPT_RT)
+			 */
+			preempt_disable_rt();
+
 			list_del(&msr->r_list);
 			if (msr->r_maxsize < msg->m_ts) {
 				msr->r_msg = NULL;
@@ -626,9 +640,11 @@
 				wake_up_process(msr->r_tsk);
 				smp_mb();
 				msr->r_msg = msg;
+				preempt_enable_rt();
 
 				return 1;
 			}
+			preempt_enable_rt();
 		}
 	}
 	return 0;
diff --git a/ipc/sem.c b/ipc/sem.c
index 5215a81..5eaf684 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -461,6 +461,13 @@
 static void wake_up_sem_queue_prepare(struct list_head *pt,
 				struct sem_queue *q, int error)
 {
+#ifdef CONFIG_PREEMPT_RT_BASE
+	struct task_struct *p = q->sleeper;
+	get_task_struct(p);
+	q->status = error;
+	wake_up_process(p);
+	put_task_struct(p);
+#else
 	if (list_empty(pt)) {
 		/*
 		 * Hold preempt off so that we don't get preempted and have the
@@ -472,6 +479,7 @@
 	q->pid = error;
 
 	list_add_tail(&q->simple_list, pt);
+#endif
 }
 
 /**
@@ -485,6 +493,7 @@
  */
 static void wake_up_sem_queue_do(struct list_head *pt)
 {
+#ifndef CONFIG_PREEMPT_RT_BASE
 	struct sem_queue *q, *t;
 	int did_something;
 
@@ -497,6 +506,7 @@
 	}
 	if (did_something)
 		preempt_enable();
+#endif
 }
 
 static void unlink_queue(struct sem_array *sma, struct sem_queue *q)
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
index 61ebb49..a163ed5 100644
--- a/kernel/Kconfig.locks
+++ b/kernel/Kconfig.locks
@@ -203,4 +203,4 @@
 
 config MUTEX_SPIN_ON_OWNER
 	def_bool y
-	depends on SMP && !DEBUG_MUTEXES && ARCH_SUPPORTS_ATOMIC_RMW
+	depends on SMP && !DEBUG_MUTEXES && ARCH_SUPPORTS_ATOMIC_RMW && !PREEMPT_RT_FULL
diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index 24e7cb0..d0e9372 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -1,3 +1,10 @@
+config PREEMPT
+	bool
+	select PREEMPT_COUNT
+
+config PREEMPT_RT_BASE
+	bool
+	select PREEMPT
 
 choice
 	prompt "Preemption Model"
@@ -33,9 +40,9 @@
 
 	  Select this if you are building a kernel for a desktop system.
 
-config PREEMPT
+config PREEMPT__LL
 	bool "Preemptible Kernel (Low-Latency Desktop)"
-	select PREEMPT_COUNT
+	select PREEMPT
 	help
 	  This option reduces the latency of the kernel by making
 	  all kernel code (that is not executing in a critical section)
@@ -51,6 +58,21 @@
 	  embedded system with latency requirements in the milliseconds
 	  range.
 
+config PREEMPT_RTB
+	bool "Preemptible Kernel (Basic RT)"
+	select PREEMPT_RT_BASE
+	help
+	  This option is basically the same as (Low-Latency Desktop) but
+	  enables changes which are preliminary for the full preemptiple
+	  RT kernel.
+
+config PREEMPT_RT_FULL
+	bool "Fully Preemptible Kernel (RT)"
+	depends on IRQ_FORCED_THREADING
+	select PREEMPT_RT_BASE
+	help
+	  All and everything
+
 endchoice
 
 config PREEMPT_COUNT
diff --git a/kernel/Makefile b/kernel/Makefile
index e898c5b..b34456e 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -7,11 +7,11 @@
 	    sysctl.o sysctl_binary.o capability.o ptrace.o timer.o user.o \
 	    signal.o sys.o kmod.o workqueue.o pid.o \
 	    rcupdate.o extable.o params.o posix-timers.o \
-	    kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
-	    hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
+	    kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o \
+	    hrtimer.o nsproxy.o srcu.o semaphore.o \
 	    notifier.o ksysfs.o sched_clock.o cred.o \
 	    async.o range.o
-obj-y += groups.o
+obj-y += groups.o wait-simple.o work-simple.o
 
 ifdef CONFIG_FUNCTION_TRACER
 # Do not trace debug files and internal ftrace files
@@ -29,7 +29,11 @@
 obj-$(CONFIG_SYSCTL_SYSCALL_CHECK) += sysctl_check.o
 obj-$(CONFIG_STACKTRACE) += stacktrace.o
 obj-y += time/
+ifneq ($(CONFIG_PREEMPT_RT_FULL),y)
+obj-y += mutex.o
 obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o
+obj-y += rwsem.o
+endif
 obj-$(CONFIG_LOCKDEP) += lockdep.o
 ifeq ($(CONFIG_PROC_FS),y)
 obj-$(CONFIG_LOCKDEP) += lockdep_proc.o
@@ -41,6 +45,7 @@
 obj-$(CONFIG_RT_MUTEXES) += rtmutex.o
 obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
 obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o
+obj-$(CONFIG_PREEMPT_RT_FULL) += rt.o
 obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o
 obj-$(CONFIG_SMP) += smp.o
 ifneq ($(CONFIG_SMP),y)
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 82c91f1..031c644 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -58,6 +58,284 @@
 	.refcount = 0,
 };
 
+/**
+ * hotplug_pcp - per cpu hotplug descriptor
+ * @unplug:	set when pin_current_cpu() needs to sync tasks
+ * @sync_tsk:	the task that waits for tasks to finish pinned sections
+ * @refcount:	counter of tasks in pinned sections
+ * @grab_lock:	set when the tasks entering pinned sections should wait
+ * @synced:	notifier for @sync_tsk to tell cpu_down it's finished
+ * @mutex:	the mutex to make tasks wait (used when @grab_lock is true)
+ * @mutex_init:	zero if the mutex hasn't been initialized yet.
+ *
+ * Although @unplug and @sync_tsk may point to the same task, the @unplug
+ * is used as a flag and still exists after @sync_tsk has exited and
+ * @sync_tsk set to NULL.
+ */
+struct hotplug_pcp {
+	struct task_struct *unplug;
+	struct task_struct *sync_tsk;
+	int refcount;
+	int grab_lock;
+	struct completion synced;
+	struct completion unplug_wait;
+#ifdef CONFIG_PREEMPT_RT_FULL
+	spinlock_t lock;
+#else
+	struct mutex mutex;
+#endif
+	int mutex_init;
+};
+
+#ifdef CONFIG_PREEMPT_RT_FULL
+# define hotplug_lock(hp) rt_spin_lock(&(hp)->lock)
+# define hotplug_unlock(hp) rt_spin_unlock(&(hp)->lock)
+#else
+# define hotplug_lock(hp) mutex_lock(&(hp)->mutex)
+# define hotplug_unlock(hp) mutex_unlock(&(hp)->mutex)
+#endif
+
+static DEFINE_PER_CPU(struct hotplug_pcp, hotplug_pcp);
+
+/**
+ * pin_current_cpu - Prevent the current cpu from being unplugged
+ *
+ * Lightweight version of get_online_cpus() to prevent cpu from being
+ * unplugged when code runs in a migration disabled region.
+ *
+ * Must be called with preemption disabled (preempt_count = 1)!
+ */
+void pin_current_cpu(void)
+{
+	struct hotplug_pcp *hp;
+	int force = 0;
+
+retry:
+	hp = &__get_cpu_var(hotplug_pcp);
+
+	if (!hp->unplug || hp->refcount || force || preempt_count() > 1 ||
+	    hp->unplug == current || (current->flags & PF_STOMPER)) {
+		hp->refcount++;
+		return;
+	}
+
+	if (hp->grab_lock) {
+		preempt_enable();
+		hotplug_lock(hp);
+		hotplug_unlock(hp);
+	} else {
+		preempt_enable();
+		/*
+		 * Try to push this task off of this CPU.
+		 */
+		if (!migrate_me()) {
+			preempt_disable();
+			hp = &__get_cpu_var(hotplug_pcp);
+			if (!hp->grab_lock) {
+				/*
+				 * Just let it continue it's already pinned
+				 * or about to sleep.
+				 */
+				force = 1;
+				goto retry;
+			}
+			preempt_enable();
+		}
+	}
+	preempt_disable();
+	goto retry;
+}
+
+/**
+ * unpin_current_cpu - Allow unplug of current cpu
+ *
+ * Must be called with preemption or interrupts disabled!
+ */
+void unpin_current_cpu(void)
+{
+	struct hotplug_pcp *hp = &__get_cpu_var(hotplug_pcp);
+
+	WARN_ON(hp->refcount <= 0);
+
+	/* This is safe. sync_unplug_thread is pinned to this cpu */
+	if (!--hp->refcount && hp->unplug && hp->unplug != current &&
+	    !(current->flags & PF_STOMPER))
+		wake_up_process(hp->unplug);
+}
+
+static void wait_for_pinned_cpus(struct hotplug_pcp *hp)
+{
+	set_current_state(TASK_UNINTERRUPTIBLE);
+	while (hp->refcount) {
+		schedule_preempt_disabled();
+		set_current_state(TASK_UNINTERRUPTIBLE);
+	}
+}
+
+static int sync_unplug_thread(void *data)
+{
+	struct hotplug_pcp *hp = data;
+
+	wait_for_completion(&hp->unplug_wait);
+	preempt_disable();
+	hp->unplug = current;
+	wait_for_pinned_cpus(hp);
+
+	/*
+	 * This thread will synchronize the cpu_down() with threads
+	 * that have pinned the CPU. When the pinned CPU count reaches
+	 * zero, we inform the cpu_down code to continue to the next step.
+	 */
+	set_current_state(TASK_UNINTERRUPTIBLE);
+	preempt_enable();
+	complete(&hp->synced);
+
+	/*
+	 * If all succeeds, the next step will need tasks to wait till
+	 * the CPU is offline before continuing. To do this, the grab_lock
+	 * is set and tasks going into pin_current_cpu() will block on the
+	 * mutex. But we still need to wait for those that are already in
+	 * pinned CPU sections. If the cpu_down() failed, the kthread_should_stop()
+	 * will kick this thread out.
+	 */
+	while (!hp->grab_lock && !kthread_should_stop()) {
+		schedule();
+		set_current_state(TASK_UNINTERRUPTIBLE);
+	}
+
+	/* Make sure grab_lock is seen before we see a stale completion */
+	smp_mb();
+
+	/*
+	 * Now just before cpu_down() enters stop machine, we need to make
+	 * sure all tasks that are in pinned CPU sections are out, and new
+	 * tasks will now grab the lock, keeping them from entering pinned
+	 * CPU sections.
+	 */
+	if (!kthread_should_stop()) {
+		preempt_disable();
+		wait_for_pinned_cpus(hp);
+		preempt_enable();
+		complete(&hp->synced);
+	}
+
+	set_current_state(TASK_UNINTERRUPTIBLE);
+	while (!kthread_should_stop()) {
+		schedule();
+		set_current_state(TASK_UNINTERRUPTIBLE);
+	}
+	set_current_state(TASK_RUNNING);
+
+	/*
+	 * Force this thread off this CPU as it's going down and
+	 * we don't want any more work on this CPU.
+	 */
+	current->flags &= ~PF_THREAD_BOUND;
+	do_set_cpus_allowed(current, cpu_present_mask);
+	migrate_me();
+	return 0;
+}
+
+static void __cpu_unplug_sync(struct hotplug_pcp *hp)
+{
+	wake_up_process(hp->sync_tsk);
+	wait_for_completion(&hp->synced);
+}
+
+static void __cpu_unplug_wait(unsigned int cpu)
+{
+	struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu);
+
+	complete(&hp->unplug_wait);
+	wait_for_completion(&hp->synced);
+}
+
+/*
+ * Start the sync_unplug_thread on the target cpu and wait for it to
+ * complete.
+ */
+static int cpu_unplug_begin(unsigned int cpu)
+{
+	struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu);
+	int err;
+
+	/* Protected by cpu_hotplug.lock */
+	if (!hp->mutex_init) {
+#ifdef CONFIG_PREEMPT_RT_FULL
+		spin_lock_init(&hp->lock);
+#else
+		mutex_init(&hp->mutex);
+#endif
+		hp->mutex_init = 1;
+	}
+
+	/* Inform the scheduler to migrate tasks off this CPU */
+	tell_sched_cpu_down_begin(cpu);
+
+	init_completion(&hp->synced);
+	init_completion(&hp->unplug_wait);
+
+	hp->sync_tsk = kthread_create(sync_unplug_thread, hp, "sync_unplug/%d", cpu);
+	if (IS_ERR(hp->sync_tsk)) {
+		err = PTR_ERR(hp->sync_tsk);
+		hp->sync_tsk = NULL;
+		return err;
+	}
+	kthread_bind(hp->sync_tsk, cpu);
+
+	/*
+	 * Wait for tasks to get out of the pinned sections,
+	 * it's still OK if new tasks enter. Some CPU notifiers will
+	 * wait for tasks that are going to enter these sections and
+	 * we must not have them block.
+	 */
+	wake_up_process(hp->sync_tsk);
+	return 0;
+}
+
+static void cpu_unplug_sync(unsigned int cpu)
+{
+	struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu);
+
+	init_completion(&hp->synced);
+	/* The completion needs to be initialzied before setting grab_lock */
+	smp_wmb();
+
+	/* Grab the mutex before setting grab_lock */
+	hotplug_lock(hp);
+	hp->grab_lock = 1;
+
+	/*
+	 * The CPU notifiers have been completed.
+	 * Wait for tasks to get out of pinned CPU sections and have new
+	 * tasks block until the CPU is completely down.
+	 */
+	__cpu_unplug_sync(hp);
+
+	/* All done with the sync thread */
+	kthread_stop(hp->sync_tsk);
+	hp->sync_tsk = NULL;
+}
+
+static void cpu_unplug_done(unsigned int cpu)
+{
+	struct hotplug_pcp *hp = &per_cpu(hotplug_pcp, cpu);
+
+	hp->unplug = NULL;
+	/* Let all tasks know cpu unplug is finished before cleaning up */
+	smp_wmb();
+
+	if (hp->sync_tsk)
+		kthread_stop(hp->sync_tsk);
+
+	if (hp->grab_lock) {
+		hotplug_unlock(hp);
+		/* protected by cpu_hotplug.lock */
+		hp->grab_lock = 0;
+	}
+	tell_sched_cpu_down_done(cpu);
+}
+
 void get_online_cpus(void)
 {
 	might_sleep();
@@ -232,13 +510,15 @@
 /* Requires cpu_add_remove_lock to be held */
 static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 {
-	int err, nr_calls = 0;
+	int mycpu, err, nr_calls = 0;
 	void *hcpu = (void *)(long)cpu;
 	unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
 	struct take_cpu_down_param tcd_param = {
 		.mod = mod,
 		.hcpu = hcpu,
 	};
+	cpumask_var_t cpumask;
+	cpumask_var_t cpumask_org;
 
 	if (num_online_cpus() == 1)
 		return -EBUSY;
@@ -246,7 +526,34 @@
 	if (!cpu_online(cpu))
 		return -EINVAL;
 
+	/* Move the downtaker off the unplug cpu */
+	if (!alloc_cpumask_var(&cpumask, GFP_KERNEL))
+		return -ENOMEM;
+	if (!alloc_cpumask_var(&cpumask_org, GFP_KERNEL))  {
+		free_cpumask_var(cpumask);
+		return -ENOMEM;
+	}
+
+	cpumask_copy(cpumask_org, tsk_cpus_allowed(current));
+	cpumask_andnot(cpumask, cpu_online_mask, cpumask_of(cpu));
+	set_cpus_allowed_ptr(current, cpumask);
+	free_cpumask_var(cpumask);
+	migrate_disable();
+	mycpu = smp_processor_id();
+	if (mycpu == cpu) {
+		printk(KERN_ERR "Yuck! Still on unplug CPU\n!");
+		migrate_enable();
+		err = -EBUSY;
+		goto restore_cpus;
+	}
+	migrate_enable();
+
 	cpu_hotplug_begin();
+	err = cpu_unplug_begin(cpu);
+	if (err) {
+		printk("cpu_unplug_begin(%d) failed\n", cpu);
+		goto out_cancel;
+	}
 
 	err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls);
 	if (err) {
@@ -257,6 +564,11 @@
 		goto out_release;
 	}
 
+	__cpu_unplug_wait(cpu);
+
+	/* Notifiers are done. Don't let any more tasks pin this CPU. */
+	cpu_unplug_sync(cpu);
+
 	err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
 	if (err) {
 		/* CPU didn't die: tell everyone.  Can't complain. */
@@ -285,9 +597,14 @@
 	check_for_tasks(cpu);
 
 out_release:
+	cpu_unplug_done(cpu);
+out_cancel:
 	cpu_hotplug_done();
 	if (!err)
 		cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu);
+restore_cpus:
+	set_cpus_allowed_ptr(current, cpumask_org);
+	free_cpumask_var(cpumask_org);
 	return err;
 }
 
diff --git a/kernel/cred.c b/kernel/cred.c
index 48c6fd3..482a0e3 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -35,7 +35,7 @@
 static struct thread_group_cred init_tgcred = {
 	.usage	= ATOMIC_INIT(2),
 	.tgid	= 0,
-	.lock	= __SPIN_LOCK_UNLOCKED(init_cred.tgcred.lock),
+	.lock	= __SPIN_LOCK_UNLOCKED(init_tgcred.lock),
 };
 #endif
 
diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c
index 4802eb5..5b7455f 100644
--- a/kernel/debug/kdb/kdb_io.c
+++ b/kernel/debug/kdb/kdb_io.c
@@ -553,7 +553,6 @@
 	int diag;
 	int linecount;
 	int logging, saved_loglevel = 0;
-	int saved_trap_printk;
 	int got_printf_lock = 0;
 	int retlen = 0;
 	int fnd, len;
@@ -564,8 +563,6 @@
 	unsigned long uninitialized_var(flags);
 
 	preempt_disable();
-	saved_trap_printk = kdb_trap_printk;
-	kdb_trap_printk = 0;
 
 	/* Serialize kdb_printf if multiple cpus try to write at once.
 	 * But if any cpu goes recursive in kdb, just print the output,
@@ -821,7 +818,6 @@
 	} else {
 		__release(kdb_printf_lock);
 	}
-	kdb_trap_printk = saved_trap_printk;
 	preempt_enable();
 	return retlen;
 }
@@ -831,9 +827,11 @@
 	va_list ap;
 	int r;
 
+	kdb_trap_printk++;
 	va_start(ap, fmt);
 	r = vkdb_printf(fmt, ap);
 	va_end(ap);
+	kdb_trap_printk--;
 
 	return r;
 }
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4277095..44d83fb 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5600,6 +5600,7 @@
 
 	hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	hwc->hrtimer.function = perf_swevent_hrtimer;
+	hwc->hrtimer.irqsafe = 1;
 
 	/*
 	 * Since hrtimers have a fixed rate, we can do a static freq->period
diff --git a/kernel/exit.c b/kernel/exit.c
index fde15f9..4176f80 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -141,7 +141,7 @@
 	 * Do this under ->siglock, we can race with another thread
 	 * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals.
 	 */
-	flush_sigqueue(&tsk->pending);
+	flush_task_sigqueue(tsk);
 	tsk->sighand = NULL;
 	spin_unlock(&sighand->siglock);
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 29b4604..ffcf1f6 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -88,7 +88,7 @@
 
 DEFINE_PER_CPU(unsigned long, process_counts) = 0;
 
-__cacheline_aligned DEFINE_RWLOCK(tasklist_lock);  /* outer */
+DEFINE_RWLOCK(tasklist_lock);  /* outer */
 
 #ifdef CONFIG_PROVE_RCU
 int lockdep_tasklist_lock_is_held(void)
@@ -198,7 +198,18 @@
 	if (!profile_handoff_task(tsk))
 		free_task(tsk);
 }
+#ifndef CONFIG_PREEMPT_RT_BASE
 EXPORT_SYMBOL_GPL(__put_task_struct);
+#else
+void __put_task_struct_cb(struct rcu_head *rhp)
+{
+	struct task_struct *tsk = container_of(rhp, struct task_struct, put_rcu);
+
+	__put_task_struct(tsk);
+
+}
+EXPORT_SYMBOL_GPL(__put_task_struct_cb);
+#endif
 
 /*
  * macro override instead of weak attribute alias, to workaround
@@ -544,6 +555,19 @@
 }
 EXPORT_SYMBOL_GPL(__mmdrop);
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+/*
+ * RCU callback for delayed mm drop. Not strictly rcu, but we don't
+ * want another facility to make this work.
+ */
+void __mmdrop_delayed(struct rcu_head *rhp)
+{
+	struct mm_struct *mm = container_of(rhp, struct mm_struct, delayed_drop);
+
+	__mmdrop(mm);
+}
+#endif
+
 /*
  * Decrement the use count and release all resources for an mm.
  */
@@ -1031,6 +1055,9 @@
  */
 static void posix_cpu_timers_init(struct task_struct *tsk)
 {
+#ifdef CONFIG_PREEMPT_RT_BASE
+	tsk->posix_timer_list = NULL;
+#endif
 	tsk->cputime_expires.prof_exp = cputime_zero;
 	tsk->cputime_expires.virt_exp = cputime_zero;
 	tsk->cputime_expires.sched_exp = 0;
@@ -1138,6 +1165,7 @@
 	spin_lock_init(&p->alloc_lock);
 
 	init_sigpending(&p->pending);
+	p->sigqueue_cache = NULL;
 
 	p->utime = cputime_zero;
 	p->stime = cputime_zero;
@@ -1199,6 +1227,9 @@
 	p->hardirq_context = 0;
 	p->softirq_context = 0;
 #endif
+#ifdef CONFIG_PREEMPT_RT_FULL
+	p->pagefault_disabled = 0;
+#endif
 #ifdef CONFIG_LOCKDEP
 	p->lockdep_depth = 0; /* no locks held yet */
 	p->curr_chain_key = 0;
diff --git a/kernel/futex.c b/kernel/futex.c
index 7481595..cd2b055 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -643,97 +643,91 @@
  * [10] There is no transient state which leaves owner and user space
  *	TID out of sync.
  */
-static int
-lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
-		union futex_key *key, struct futex_pi_state **ps)
+
+/*
+ * Validate that the existing waiter has a pi_state and sanity check
+ * the pi_state against the user space value. If correct, attach to
+ * it.
+ */
+static int attach_to_pi_state(u32 uval, struct futex_pi_state *pi_state,
+			      struct futex_pi_state **ps)
 {
-	struct futex_pi_state *pi_state = NULL;
-	struct futex_q *this, *next;
-	struct plist_head *head;
-	struct task_struct *p;
 	pid_t pid = uval & FUTEX_TID_MASK;
 
-	head = &hb->chain;
+	/*
+	 * Userspace might have messed up non-PI and PI futexes [3]
+	 */
+	if (unlikely(!pi_state))
+		return -EINVAL;
 
-	plist_for_each_entry_safe(this, next, head, list) {
-		if (match_futex(&this->key, key)) {
+	WARN_ON(!atomic_read(&pi_state->refcount));
+
+	/*
+	 * Handle the owner died case:
+	 */
+	if (uval & FUTEX_OWNER_DIED) {
+		/*
+		 * exit_pi_state_list sets owner to NULL and wakes the
+		 * topmost waiter. The task which acquires the
+		 * pi_state->rt_mutex will fixup owner.
+		 */
+		if (!pi_state->owner) {
 			/*
-			 * Sanity check the waiter before increasing
-			 * the refcount and attaching to it.
+			 * No pi state owner, but the user space TID
+			 * is not 0. Inconsistent state. [5]
 			 */
-			pi_state = this->pi_state;
-			/*
-			 * Userspace might have messed up non-PI and
-			 * PI futexes [3]
-			 */
-			if (unlikely(!pi_state))
+			if (pid)
 				return -EINVAL;
-
-			WARN_ON(!atomic_read(&pi_state->refcount));
-
 			/*
-			 * Handle the owner died case:
+			 * Take a ref on the state and return success. [4]
 			 */
-			if (uval & FUTEX_OWNER_DIED) {
-				/*
-				 * exit_pi_state_list sets owner to NULL and
-				 * wakes the topmost waiter. The task which
-				 * acquires the pi_state->rt_mutex will fixup
-				 * owner.
-				 */
-				if (!pi_state->owner) {
-					/*
-					 * No pi state owner, but the user
-					 * space TID is not 0. Inconsistent
-					 * state. [5]
-					 */
-					if (pid)
-						return -EINVAL;
-					/*
-					 * Take a ref on the state and
-					 * return. [4]
-					 */
-					goto out_state;
-				}
-
-				/*
-				 * If TID is 0, then either the dying owner
-				 * has not yet executed exit_pi_state_list()
-				 * or some waiter acquired the rtmutex in the
-				 * pi state, but did not yet fixup the TID in
-				 * user space.
-				 *
-				 * Take a ref on the state and return. [6]
-				 */
-				if (!pid)
-					goto out_state;
-			} else {
-				/*
-				 * If the owner died bit is not set,
-				 * then the pi_state must have an
-				 * owner. [7]
-				 */
-				if (!pi_state->owner)
-					return -EINVAL;
-			}
-
-			/*
-			 * Bail out if user space manipulated the
-			 * futex value. If pi state exists then the
-			 * owner TID must be the same as the user
-			 * space TID. [9/10]
-			 */
-			if (pid != task_pid_vnr(pi_state->owner))
-				return -EINVAL;
-
-		out_state:
-			atomic_inc(&pi_state->refcount);
-			*ps = pi_state;
-			return 0;
+			goto out_state;
 		}
+
+		/*
+		 * If TID is 0, then either the dying owner has not
+		 * yet executed exit_pi_state_list() or some waiter
+		 * acquired the rtmutex in the pi state, but did not
+		 * yet fixup the TID in user space.
+		 *
+		 * Take a ref on the state and return success. [6]
+		 */
+		if (!pid)
+			goto out_state;
+	} else {
+		/*
+		 * If the owner died bit is not set, then the pi_state
+		 * must have an owner. [7]
+		 */
+		if (!pi_state->owner)
+			return -EINVAL;
 	}
 
 	/*
+	 * Bail out if user space manipulated the futex value. If pi
+	 * state exists then the owner TID must be the same as the
+	 * user space TID. [9/10]
+	 */
+	if (pid != task_pid_vnr(pi_state->owner))
+		return -EINVAL;
+out_state:
+	atomic_inc(&pi_state->refcount);
+	*ps = pi_state;
+	return 0;
+}
+
+/*
+ * Lookup the task for the TID provided from user space and attach to
+ * it after doing proper sanity checks.
+ */
+static int attach_to_pi_owner(u32 uval, union futex_key *key,
+			      struct futex_pi_state **ps)
+{
+	pid_t pid = uval & FUTEX_TID_MASK;
+	struct futex_pi_state *pi_state;
+	struct task_struct *p;
+
+	/*
 	 * We are the first waiter - try to look up the real owner and attach
 	 * the new pi_state to it, but bail out when TID = 0 [1]
 	 */
@@ -774,7 +768,7 @@
 	pi_state = alloc_pi_state();
 
 	/*
-	 * Initialize the pi_mutex in locked state and make 'p'
+	 * Initialize the pi_mutex in locked state and make @p
 	 * the owner of it:
 	 */
 	rt_mutex_init_proxy_locked(&pi_state->pi_mutex, p);
@@ -794,6 +788,36 @@
 	return 0;
 }
 
+static int lookup_pi_state(u32 uval, struct futex_hash_bucket *hb,
+			   union futex_key *key, struct futex_pi_state **ps)
+{
+	struct futex_q *match = futex_top_waiter(hb, key);
+
+	/*
+	 * If there is a waiter on that futex, validate it and
+	 * attach to the pi_state when the validation succeeds.
+	 */
+	if (match)
+		return attach_to_pi_state(uval, match->pi_state, ps);
+
+	/*
+	 * We are the first waiter - try to look up the owner based on
+	 * @uval and attach to it.
+	 */
+	return attach_to_pi_owner(uval, key, ps);
+}
+
+static int lock_pi_update_atomic(u32 __user *uaddr, u32 uval, u32 newval)
+{
+	u32 uninitialized_var(curval);
+
+	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
+		return -EFAULT;
+
+	/*If user space value changed, let the caller retry */
+	return curval != uval ? -EAGAIN : 0;
+}
+
 /**
  * futex_lock_pi_atomic() - Atomic work required to acquire a pi aware futex
  * @uaddr:		the pi futex user address
@@ -817,113 +841,69 @@
 				struct futex_pi_state **ps,
 				struct task_struct *task, int set_waiters)
 {
-	int lock_taken, ret, force_take = 0;
-	u32 uval, newval, curval, vpid = task_pid_vnr(task);
-
-retry:
-	ret = lock_taken = 0;
+	u32 uval, newval, vpid = task_pid_vnr(task);
+	struct futex_q *match;
+	int ret;
 
 	/*
-	 * To avoid races, we attempt to take the lock here again
-	 * (by doing a 0 -> TID atomic cmpxchg), while holding all
-	 * the locks. It will most likely not succeed.
+	 * Read the user space value first so we can validate a few
+	 * things before proceeding further.
 	 */
-	newval = vpid;
-	if (set_waiters)
-		newval |= FUTEX_WAITERS;
-
-	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, 0, newval)))
+	if (get_futex_value_locked(&uval, uaddr))
 		return -EFAULT;
 
 	/*
 	 * Detect deadlocks.
 	 */
-	if ((unlikely((curval & FUTEX_TID_MASK) == vpid)))
+	if ((unlikely((uval & FUTEX_TID_MASK) == vpid)))
 		return -EDEADLK;
 
 	/*
-	 * Surprise - we got the lock, but we do not trust user space at all.
+	 * Lookup existing state first. If it exists, try to attach to
+	 * its pi_state.
 	 */
-	if (unlikely(!curval)) {
+	match = futex_top_waiter(hb, key);
+	if (match)
+		return attach_to_pi_state(uval, match->pi_state, ps);
+
+	/*
+	 * No waiter and user TID is 0. We are here because the
+	 * waiters or the owner died bit is set or called from
+	 * requeue_cmp_pi or for whatever reason something took the
+	 * syscall.
+	 */
+	if (!(uval & FUTEX_TID_MASK)) {
 		/*
-		 * We verify whether there is kernel state for this
-		 * futex. If not, we can safely assume, that the 0 ->
-		 * TID transition is correct. If state exists, we do
-		 * not bother to fixup the user space state as it was
-		 * corrupted already.
+		 * We take over the futex. No other waiters and the user space
+		 * TID is 0. We preserve the owner died bit.
 		 */
-		return futex_top_waiter(hb, key) ? -EINVAL : 1;
+		newval = uval & FUTEX_OWNER_DIED;
+		newval |= vpid;
+
+		/* The futex requeue_pi code can enforce the waiters bit */
+		if (set_waiters)
+			newval |= FUTEX_WAITERS;
+
+		ret = lock_pi_update_atomic(uaddr, uval, newval);
+		/* If the take over worked, return 1 */
+		return ret < 0 ? ret : 1;
 	}
 
-	uval = curval;
-
 	/*
-	 * Set the FUTEX_WAITERS flag, so the owner will know it has someone
-	 * to wake at the next unlock.
+	 * First waiter. Set the waiters bit before attaching ourself to
+	 * the owner. If owner tries to unlock, it will be forced into
+	 * the kernel and blocked on hb->lock.
 	 */
-	newval = curval | FUTEX_WAITERS;
-
+	newval = uval | FUTEX_WAITERS;
+	ret = lock_pi_update_atomic(uaddr, uval, newval);
+	if (ret)
+		return ret;
 	/*
-	 * Should we force take the futex? See below.
+	 * If the update of the user space value succeeded, we try to
+	 * attach to the owner. If that fails, no harm done, we only
+	 * set the FUTEX_WAITERS bit in the user space variable.
 	 */
-	if (unlikely(force_take)) {
-		/*
-		 * Keep the OWNER_DIED and the WAITERS bit and set the
-		 * new TID value.
-		 */
-		newval = (curval & ~FUTEX_TID_MASK) | vpid;
-		force_take = 0;
-		lock_taken = 1;
-	}
-
-	if (unlikely(cmpxchg_futex_value_locked(&curval, uaddr, uval, newval)))
-		return -EFAULT;
-	if (unlikely(curval != uval))
-		goto retry;
-
-	/*
-	 * We took the lock due to forced take over.
-	 */
-	if (unlikely(lock_taken))
-		return 1;
-
-	/*
-	 * We dont have the lock. Look up the PI state (or create it if
-	 * we are the first waiter):
-	 */
-	ret = lookup_pi_state(uval, hb, key, ps);
-
-	if (unlikely(ret)) {
-		switch (ret) {
-		case -ESRCH:
-			/*
-			 * We failed to find an owner for this
-			 * futex. So we have no pi_state to block
-			 * on. This can happen in two cases:
-			 *
-			 * 1) The owner died
-			 * 2) A stale FUTEX_WAITERS bit
-			 *
-			 * Re-read the futex value.
-			 */
-			if (get_futex_value_locked(&curval, uaddr))
-				return -EFAULT;
-
-			/*
-			 * If the owner died or we have a stale
-			 * WAITERS bit the owner TID in the user space
-			 * futex is 0.
-			 */
-			if (!(curval & FUTEX_TID_MASK)) {
-				force_take = 1;
-				goto retry;
-			}
-		default:
-			break;
-		}
-	}
-
-	return ret;
+	return attach_to_pi_owner(uval, key, ps);
 }
 
 /**
@@ -1039,22 +1019,6 @@
 	return 0;
 }
 
-static int unlock_futex_pi(u32 __user *uaddr, u32 uval)
-{
-	u32 uninitialized_var(oldval);
-
-	/*
-	 * There is no waiter, so we unlock the futex. The owner died
-	 * bit has not to be preserved here. We are the owner:
-	 */
-	if (cmpxchg_futex_value_locked(&oldval, uaddr, uval, 0))
-		return -EFAULT;
-	if (oldval != uval)
-		return -EAGAIN;
-
-	return 0;
-}
-
 /*
  * Express the locking dependencies for lockdep:
  */
@@ -1502,7 +1466,12 @@
 				goto retry;
 			goto out;
 		case -EAGAIN:
-			/* The owner was exiting, try again. */
+			/*
+			 * Two reasons for this:
+			 * - Owner is exiting and we just wait for the
+			 *   exit to complete.
+			 * - The user space value changed.
+			 */
 			free_pi_state(pi_state);
 			pi_state = NULL;
 			double_unlock_hb(hb1, hb2);
@@ -1563,12 +1532,22 @@
 			this->pi_state = pi_state;
 			ret = rt_mutex_start_proxy_lock(&pi_state->pi_mutex,
 							this->rt_waiter,
-							this->task, 1);
+							this->task);
 			if (ret == 1) {
 				/* We got the lock. */
 				requeue_pi_wake_futex(this, &key2, hb2);
 				drop_count++;
 				continue;
+			} else if (ret == -EAGAIN) {
+				/*
+				 * Waiter was woken by timeout or
+				 * signal and has set pi_blocked_on to
+				 * PI_WAKEUP_INPROGRESS before we
+				 * tried to enqueue it on the rtmutex.
+				 */
+				this->pi_state = NULL;
+				free_pi_state(pi_state);
+				continue;
 			} else if (ret) {
 				/* -EDEADLK */
 				this->pi_state = NULL;
@@ -2147,8 +2126,10 @@
 			goto uaddr_faulted;
 		case -EAGAIN:
 			/*
-			 * Task is exiting and we just wait for the
-			 * exit to complete.
+			 * Two reasons for this:
+			 * - Task is exiting and we just wait for the
+			 *   exit to complete.
+			 * - The user space value changed.
 			 */
 			queue_unlock(&q, hb);
 			put_futex_key(&q.key);
@@ -2168,9 +2149,9 @@
 	/*
 	 * Block on the PI mutex:
 	 */
-	if (!trylock)
-		ret = rt_mutex_timed_lock(&q.pi_state->pi_mutex, to, 1);
-	else {
+	if (!trylock) {
+		ret = rt_mutex_timed_futex_lock(&q.pi_state->pi_mutex, to);
+	} else {
 		ret = rt_mutex_trylock(&q.pi_state->pi_mutex);
 		/* Fixup the trylock return value: */
 		ret = ret ? 0 : -EWOULDBLOCK;
@@ -2232,11 +2213,10 @@
  */
 static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 {
-	struct futex_hash_bucket *hb;
-	struct futex_q *this, *next;
-	struct plist_head *head;
+	u32 uninitialized_var(curval), uval, vpid = task_pid_vnr(current);
 	union futex_key key = FUTEX_KEY_INIT;
-	u32 uval, vpid = task_pid_vnr(current);
+	struct futex_hash_bucket *hb;
+	struct futex_q *match;
 	int ret;
 
 retry:
@@ -2249,61 +2229,50 @@
 		return -EPERM;
 
 	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &key, VERIFY_WRITE);
-	if (unlikely(ret != 0))
-		goto out;
+	if (ret)
+		return ret;
 
 	hb = hash_futex(&key);
 	spin_lock(&hb->lock);
 
 	/*
-	 * To avoid races, try to do the TID -> 0 atomic transition
-	 * again. If it succeeds then we can return without waking
-	 * anyone else up. We only try this if neither the waiters nor
-	 * the owner died bit are set.
+	 * Check waiters first. We do not trust user space values at
+	 * all and we at least want to know if user space fiddled
+	 * with the futex value instead of blindly unlocking.
 	 */
-	if (!(uval & ~FUTEX_TID_MASK) &&
-	    cmpxchg_futex_value_locked(&uval, uaddr, vpid, 0))
-		goto pi_faulted;
-	/*
-	 * Rare case: we managed to release the lock atomically,
-	 * no need to wake anyone else up:
-	 */
-	if (unlikely(uval == vpid))
-		goto out_unlock;
-
-	/*
-	 * Ok, other tasks may need to be woken up - check waiters
-	 * and do the wakeup if necessary:
-	 */
-	head = &hb->chain;
-
-	plist_for_each_entry_safe(this, next, head, list) {
-		if (!match_futex (&this->key, &key))
-			continue;
-		ret = wake_futex_pi(uaddr, uval, this);
+	match = futex_top_waiter(hb, &key);
+	if (match) {
+		ret = wake_futex_pi(uaddr, uval, match);
 		/*
-		 * The atomic access to the futex value
-		 * generated a pagefault, so retry the
-		 * user-access and the wakeup:
+		 * The atomic access to the futex value generated a
+		 * pagefault, so retry the user-access and the wakeup:
 		 */
 		if (ret == -EFAULT)
 			goto pi_faulted;
 		goto out_unlock;
 	}
+
 	/*
-	 * No waiters - kernel unlocks the futex:
+	 * We have no kernel internal state, i.e. no waiters in the
+	 * kernel. Waiters which are about to queue themselves are stuck
+	 * on hb->lock. So we can safely ignore them. We do neither
+	 * preserve the WAITERS bit not the OWNER_DIED one. We are the
+	 * owner.
 	 */
-	ret = unlock_futex_pi(uaddr, uval);
-	if (ret == -EFAULT)
+	if (cmpxchg_futex_value_locked(&curval, uaddr, uval, 0))
 		goto pi_faulted;
 
+	/*
+	 * If uval has changed, let user space handle it.
+	 */
+	ret = (curval == uval) ? 0 : -EAGAIN;
+
 out_unlock:
 	spin_unlock(&hb->lock);
 	put_futex_key(&key);
-
-out:
 	return ret;
 
+
 pi_faulted:
 	spin_unlock(&hb->lock);
 	put_futex_key(&key);
@@ -2411,7 +2380,7 @@
 	struct hrtimer_sleeper timeout, *to = NULL;
 	struct rt_mutex_waiter rt_waiter;
 	struct rt_mutex *pi_mutex = NULL;
-	struct futex_hash_bucket *hb;
+	struct futex_hash_bucket *hb, *hb2;
 	union futex_key key2 = FUTEX_KEY_INIT;
 	struct futex_q q = futex_q_init;
 	int res, ret;
@@ -2436,8 +2405,7 @@
 	 * The waiter is allocated on our stack, manipulated by the requeue
 	 * code while we sleep on uaddr.
 	 */
-	debug_rt_mutex_init_waiter(&rt_waiter);
-	rt_waiter.task = NULL;
+	rt_mutex_init_waiter(&rt_waiter, false);
 
 	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE);
 	if (unlikely(ret != 0))
@@ -2468,20 +2436,55 @@
 	/* Queue the futex_q, drop the hb lock, wait for wakeup. */
 	futex_wait_queue_me(hb, &q, to);
 
-	spin_lock(&hb->lock);
-	ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to);
-	spin_unlock(&hb->lock);
-	if (ret)
-		goto out_put_keys;
+	/*
+	 * On RT we must avoid races with requeue and trying to block
+	 * on two mutexes (hb->lock and uaddr2's rtmutex) by
+	 * serializing access to pi_blocked_on with pi_lock.
+	 */
+	raw_spin_lock_irq(&current->pi_lock);
+	if (current->pi_blocked_on) {
+		/*
+		 * We have been requeued or are in the process of
+		 * being requeued.
+		 */
+		raw_spin_unlock_irq(&current->pi_lock);
+	} else {
+		/*
+		 * Setting pi_blocked_on to PI_WAKEUP_INPROGRESS
+		 * prevents a concurrent requeue from moving us to the
+		 * uaddr2 rtmutex. After that we can safely acquire
+		 * (and possibly block on) hb->lock.
+		 */
+		current->pi_blocked_on = PI_WAKEUP_INPROGRESS;
+		raw_spin_unlock_irq(&current->pi_lock);
+
+		spin_lock(&hb->lock);
+
+		/*
+		 * Clean up pi_blocked_on. We might leak it otherwise
+		 * when we succeeded with the hb->lock in the fast
+		 * path.
+		 */
+		raw_spin_lock_irq(&current->pi_lock);
+		current->pi_blocked_on = NULL;
+		raw_spin_unlock_irq(&current->pi_lock);
+
+		ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to);
+		spin_unlock(&hb->lock);
+		if (ret)
+			goto out_put_keys;
+	}
 
 	/*
-	 * In order for us to be here, we know our q.key == key2, and since
-	 * we took the hb->lock above, we also know that futex_requeue() has
-	 * completed and we no longer have to concern ourselves with a wakeup
-	 * race with the atomic proxy lock acquisition by the requeue code. The
-	 * futex_requeue dropped our key1 reference and incremented our key2
-	 * reference count.
+	 * In order to be here, we have either been requeued, are in
+	 * the process of being requeued, or requeue successfully
+	 * acquired uaddr2 on our behalf.  If pi_blocked_on was
+	 * non-null above, we may be racing with a requeue.  Do not
+	 * rely on q->lock_ptr to be hb2->lock until after blocking on
+	 * hb->lock or hb2->lock. The futex_requeue dropped our key1
+	 * reference and incremented our key2 reference count.
 	 */
+	hb2 = hash_futex(&key2);
 
 	/* Check if the requeue code acquired the second futex for us. */
 	if (!q.rt_waiter) {
@@ -2490,9 +2493,10 @@
 		 * did a lock-steal - fix up the PI-state in that case.
 		 */
 		if (q.pi_state && (q.pi_state->owner != current)) {
-			spin_lock(q.lock_ptr);
+			spin_lock(&hb2->lock);
+			BUG_ON(&hb2->lock != q.lock_ptr);
 			ret = fixup_pi_state_owner(uaddr2, &q, current);
-			spin_unlock(q.lock_ptr);
+			spin_unlock(&hb2->lock);
 		}
 	} else {
 		/*
@@ -2502,10 +2506,11 @@
 		 */
 		WARN_ON(!q.pi_state);
 		pi_mutex = &q.pi_state->pi_mutex;
-		ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter, 1);
+		ret = rt_mutex_finish_proxy_lock(pi_mutex, to, &rt_waiter);
 		debug_rt_mutex_free_waiter(&rt_waiter);
 
-		spin_lock(q.lock_ptr);
+		spin_lock(&hb2->lock);
+		BUG_ON(&hb2->lock != q.lock_ptr);
 		/*
 		 * Fixup the pi_state owner and possibly acquire the lock if we
 		 * haven't already.
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index d9ce3d4..c4c5257 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -49,6 +49,7 @@
 #include <asm/uaccess.h>
 
 #include <trace/events/timer.h>
+#include <trace/events/hist.h>
 
 /*
  * The timer bases:
@@ -615,8 +616,7 @@
 	 * When the callback is running, we do not reprogram the clock event
 	 * device. The timer callback is either running on a different CPU or
 	 * the callback is executed in the hrtimer_interrupt context. The
-	 * reprogramming is handled either by the softirq, which called the
-	 * callback or at the end of the hrtimer_interrupt.
+	 * reprogramming is handled at the end of the hrtimer_interrupt.
 	 */
 	if (hrtimer_callback_running(timer))
 		return 0;
@@ -651,6 +651,9 @@
 	return res;
 }
 
+static void __run_hrtimer(struct hrtimer *timer, ktime_t *now);
+static int hrtimer_rt_defer(struct hrtimer *timer);
+
 /*
  * Initialize the high resolution related parts of cpu_base
  */
@@ -756,6 +759,11 @@
 }
 static inline void hrtimer_init_hres(struct hrtimer_cpu_base *base) { }
 static inline void retrigger_next_event(void *arg) { }
+static inline int hrtimer_reprogram(struct hrtimer *timer,
+				    struct hrtimer_clock_base *base)
+{
+	return 0;
+}
 
 #endif /* CONFIG_HIGH_RES_TIMERS */
 
@@ -873,6 +881,32 @@
 }
 EXPORT_SYMBOL_GPL(hrtimer_forward);
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+# define wake_up_timer_waiters(b)	wake_up(&(b)->wait)
+
+/**
+ * hrtimer_wait_for_timer - Wait for a running timer
+ *
+ * @timer:	timer to wait for
+ *
+ * The function waits in case the timers callback function is
+ * currently executed on the waitqueue of the timer base. The
+ * waitqueue is woken up after the timer callback function has
+ * finished execution.
+ */
+void hrtimer_wait_for_timer(const struct hrtimer *timer)
+{
+	struct hrtimer_clock_base *base = timer->base;
+
+	if (base && base->cpu_base && !timer->irqsafe)
+		wait_event(base->cpu_base->wait,
+			   !(timer->state & HRTIMER_STATE_CALLBACK));
+}
+
+#else
+# define wake_up_timer_waiters(b)	do { } while (0)
+#endif
+
 /*
  * enqueue_hrtimer - internal function to (re)start a timer
  *
@@ -916,6 +950,11 @@
 	if (!(timer->state & HRTIMER_STATE_ENQUEUED))
 		goto out;
 
+	if (unlikely(!list_empty(&timer->cb_entry))) {
+		list_del_init(&timer->cb_entry);
+		goto out;
+	}
+
 	next_timer = timerqueue_getnext(&base->active);
 	timerqueue_del(&base->active, &timer->node);
 	if (&timer->node == next_timer) {
@@ -1002,6 +1041,17 @@
 	/* Switch the timer base, if necessary: */
 	new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED);
 
+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
+	{
+		ktime_t now = new_base->get_time();
+
+		if (ktime_to_ns(tim) < ktime_to_ns(now))
+			timer->praecox = now;
+		else
+			timer->praecox = ktime_set(0, 0);
+	}
+#endif
+
 	timer_stats_hrtimer_set_start_info(timer);
 
 	leftmost = enqueue_hrtimer(timer, new_base);
@@ -1014,7 +1064,17 @@
 	 */
 	if (leftmost && new_base->cpu_base == &__get_cpu_var(hrtimer_bases)
 		&& hrtimer_enqueue_reprogram(timer, new_base)) {
-		if (wakeup) {
+
+		if (wakeup
+#ifdef CONFIG_PREEMPT_RT_BASE
+		    /*
+		     * Move softirq based timers away from the rbtree in
+		     * case it expired already. Otherwise we would have a
+		     * stale base->first entry until the softirq runs.
+		     */
+		    && hrtimer_rt_defer(timer)
+#endif
+			) {
 			/*
 			 * We need to drop cpu_base->lock to avoid a
 			 * lock ordering issue vs. rq->lock.
@@ -1023,9 +1083,18 @@
 			raise_softirq_irqoff(HRTIMER_SOFTIRQ);
 			local_irq_restore(flags);
 			return ret;
-		} else {
-			__raise_softirq_irqoff(HRTIMER_SOFTIRQ);
 		}
+
+		/*
+		 * In case we failed to reprogram the timer (mostly
+		 * because out current timer is already elapsed),
+		 * remove it again and report a failure. This avoids
+		 * stale base->first entries.
+		 */
+		debug_deactivate(timer);
+		__remove_hrtimer(timer, new_base,
+				 timer->state & HRTIMER_STATE_CALLBACK, 0);
+		ret = -ETIME;
 	}
 
 	unlock_hrtimer_base(timer, &flags);
@@ -1112,7 +1181,7 @@
 
 		if (ret >= 0)
 			return ret;
-		cpu_relax();
+		hrtimer_wait_for_timer(timer);
 	}
 }
 EXPORT_SYMBOL_GPL(hrtimer_cancel);
@@ -1191,6 +1260,7 @@
 
 	base = hrtimer_clockid_to_base(clock_id);
 	timer->base = &cpu_base->clock_base[base];
+	INIT_LIST_HEAD(&timer->cb_entry);
 	timerqueue_init(&timer->node);
 
 #ifdef CONFIG_TIMER_STATS
@@ -1277,6 +1347,126 @@
 	timer->state &= ~HRTIMER_STATE_CALLBACK;
 }
 
+static enum hrtimer_restart hrtimer_wakeup(struct hrtimer *timer);
+
+#ifdef CONFIG_PREEMPT_RT_BASE
+static void hrtimer_rt_reprogram(int restart, struct hrtimer *timer,
+				 struct hrtimer_clock_base *base)
+{
+	/*
+	 * Note, we clear the callback flag before we requeue the
+	 * timer otherwise we trigger the callback_running() check
+	 * in hrtimer_reprogram().
+	 */
+	timer->state &= ~HRTIMER_STATE_CALLBACK;
+
+	if (restart != HRTIMER_NORESTART) {
+		BUG_ON(hrtimer_active(timer));
+		/*
+		 * Enqueue the timer, if it's the leftmost timer then
+		 * we need to reprogram it.
+		 */
+		if (!enqueue_hrtimer(timer, base))
+			return;
+
+#ifndef CONFIG_HIGH_RES_TIMERS
+	}
+#else
+		if (base->cpu_base->hres_active &&
+		    hrtimer_reprogram(timer, base))
+			goto requeue;
+
+	} else if (hrtimer_active(timer)) {
+		/*
+		 * If the timer was rearmed on another CPU, reprogram
+		 * the event device.
+		 */
+		if (&timer->node == base->active.next &&
+		    base->cpu_base->hres_active &&
+		    hrtimer_reprogram(timer, base))
+			goto requeue;
+	}
+	return;
+
+requeue:
+	/*
+	 * Timer is expired. Thus move it from tree to pending list
+	 * again.
+	 */
+	__remove_hrtimer(timer, base, timer->state, 0);
+	list_add_tail(&timer->cb_entry, &base->expired);
+#endif
+}
+
+/*
+ * The changes in mainline which removed the callback modes from
+ * hrtimer are not yet working with -rt. The non wakeup_process()
+ * based callbacks which involve sleeping locks need to be treated
+ * seperately.
+ */
+static void hrtimer_rt_run_pending(void)
+{
+	enum hrtimer_restart (*fn)(struct hrtimer *);
+	struct hrtimer_cpu_base *cpu_base;
+	struct hrtimer_clock_base *base;
+	struct hrtimer *timer;
+	int index, restart;
+
+	local_irq_disable();
+	cpu_base = &per_cpu(hrtimer_bases, smp_processor_id());
+
+	raw_spin_lock(&cpu_base->lock);
+
+	for (index = 0; index < HRTIMER_MAX_CLOCK_BASES; index++) {
+		base = &cpu_base->clock_base[index];
+
+		while (!list_empty(&base->expired)) {
+			timer = list_first_entry(&base->expired,
+						 struct hrtimer, cb_entry);
+
+			/*
+			 * Same as the above __run_hrtimer function
+			 * just we run with interrupts enabled.
+			 */
+			debug_hrtimer_deactivate(timer);
+			__remove_hrtimer(timer, base, HRTIMER_STATE_CALLBACK, 0);
+			timer_stats_account_hrtimer(timer);
+			fn = timer->function;
+
+			raw_spin_unlock_irq(&cpu_base->lock);
+			restart = fn(timer);
+			raw_spin_lock_irq(&cpu_base->lock);
+
+			hrtimer_rt_reprogram(restart, timer, base);
+		}
+	}
+
+	raw_spin_unlock_irq(&cpu_base->lock);
+
+	wake_up_timer_waiters(cpu_base);
+}
+
+static int hrtimer_rt_defer(struct hrtimer *timer)
+{
+	if (timer->irqsafe)
+		return 0;
+
+	__remove_hrtimer(timer, timer->base, timer->state, 0);
+	list_add_tail(&timer->cb_entry, &timer->base->expired);
+	return 1;
+}
+
+#else
+
+static inline void hrtimer_rt_run_pending(void)
+{
+	hrtimer_peek_ahead_timers();
+}
+
+static inline int hrtimer_rt_defer(struct hrtimer *timer) { return 0; }
+
+#endif
+
 #ifdef CONFIG_HIGH_RES_TIMERS
 
 /*
@@ -1287,7 +1477,7 @@
 {
 	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
 	ktime_t expires_next, now, entry_time, delta;
-	int i, retries = 0;
+	int i, retries = 0, raise = 0;
 
 	BUG_ON(!cpu_base->hres_active);
 	cpu_base->nr_events++;
@@ -1322,6 +1512,15 @@
 
 			timer = container_of(node, struct hrtimer, node);
 
+			trace_hrtimer_interrupt(raw_smp_processor_id(),
+			    ktime_to_ns(ktime_sub(ktime_to_ns(timer->praecox) ?
+				timer->praecox : hrtimer_get_expires(timer),
+				basenow)),
+			    current,
+			    timer->function == hrtimer_wakeup ?
+			    container_of(timer, struct hrtimer_sleeper,
+				timer)->task : NULL);
+
 			/*
 			 * The immediate goal for using the softexpires is
 			 * minimizing wakeups, not running timers at the
@@ -1347,7 +1546,10 @@
 				break;
 			}
 
-			__run_hrtimer(timer, &basenow);
+			if (!hrtimer_rt_defer(timer))
+				__run_hrtimer(timer, &basenow);
+			else
+				raise = 1;
 		}
 	}
 
@@ -1362,7 +1564,7 @@
 	if (expires_next.tv64 == KTIME_MAX ||
 	    !tick_program_event(expires_next, 0)) {
 		cpu_base->hang_detected = 0;
-		return;
+		goto out;
 	}
 
 	/*
@@ -1406,6 +1608,9 @@
 	tick_program_event(expires_next, 1);
 	printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n",
 		    ktime_to_ns(delta));
+out:
+	if (raise)
+		raise_softirq_irqoff(HRTIMER_SOFTIRQ);
 }
 
 /*
@@ -1442,6 +1647,12 @@
 	local_irq_restore(flags);
 }
 
+#else /* CONFIG_HIGH_RES_TIMERS */
+
+static inline void __hrtimer_peek_ahead_timers(void) { }
+
+#endif	/* !CONFIG_HIGH_RES_TIMERS */
+
 static void run_hrtimer_softirq(struct softirq_action *h)
 {
 	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
@@ -1451,15 +1662,9 @@
 		clock_was_set();
 	}
 
-	hrtimer_peek_ahead_timers();
+	hrtimer_rt_run_pending();
 }
 
-#else /* CONFIG_HIGH_RES_TIMERS */
-
-static inline void __hrtimer_peek_ahead_timers(void) { }
-
-#endif	/* !CONFIG_HIGH_RES_TIMERS */
-
 /*
  * Called from timer softirq every jiffy, expire hrtimers:
  *
@@ -1492,7 +1697,7 @@
 	struct timerqueue_node *node;
 	struct hrtimer_cpu_base *cpu_base = &__get_cpu_var(hrtimer_bases);
 	struct hrtimer_clock_base *base;
-	int index, gettime = 1;
+	int index, gettime = 1, raise = 0;
 
 	if (hrtimer_hres_active())
 		return;
@@ -1517,10 +1722,16 @@
 					hrtimer_get_expires_tv64(timer))
 				break;
 
-			__run_hrtimer(timer, &base->softirq_time);
+			if (!hrtimer_rt_defer(timer))
+				__run_hrtimer(timer, &base->softirq_time);
+			else
+				raise = 1;
 		}
 		raw_spin_unlock(&cpu_base->lock);
 	}
+
+	if (raise)
+		raise_softirq_irqoff(HRTIMER_SOFTIRQ);
 }
 
 /*
@@ -1542,16 +1753,18 @@
 void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task)
 {
 	sl->timer.function = hrtimer_wakeup;
+	sl->timer.irqsafe = 1;
 	sl->task = task;
 }
 EXPORT_SYMBOL_GPL(hrtimer_init_sleeper);
 
-static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode)
+static int __sched do_nanosleep(struct hrtimer_sleeper *t, enum hrtimer_mode mode,
+				unsigned long state)
 {
 	hrtimer_init_sleeper(t, current);
 
 	do {
-		set_current_state(TASK_INTERRUPTIBLE);
+		set_current_state(state);
 		hrtimer_start_expires(&t->timer, mode);
 		if (!hrtimer_active(&t->timer))
 			t->task = NULL;
@@ -1595,7 +1808,8 @@
 				HRTIMER_MODE_ABS);
 	hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires);
 
-	if (do_nanosleep(&t, HRTIMER_MODE_ABS))
+	/* cpu_chill() does not care about restart state. */
+	if (do_nanosleep(&t, HRTIMER_MODE_ABS, TASK_INTERRUPTIBLE))
 		goto out;
 
 	rmtp = restart->nanosleep.rmtp;
@@ -1612,8 +1826,10 @@
 	return ret;
 }
 
-long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
-		       const enum hrtimer_mode mode, const clockid_t clockid)
+static long
+__hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
+		    const enum hrtimer_mode mode, const clockid_t clockid,
+		    unsigned long state)
 {
 	struct restart_block *restart;
 	struct hrtimer_sleeper t;
@@ -1626,7 +1842,7 @@
 
 	hrtimer_init_on_stack(&t.timer, clockid, mode);
 	hrtimer_set_expires_range_ns(&t.timer, timespec_to_ktime(*rqtp), slack);
-	if (do_nanosleep(&t, mode))
+	if (do_nanosleep(&t, mode, state))
 		goto out;
 
 	/* Absolute timers do not update the rmtp value and restart: */
@@ -1653,6 +1869,12 @@
 	return ret;
 }
 
+long hrtimer_nanosleep(struct timespec *rqtp, struct timespec __user *rmtp,
+		       const enum hrtimer_mode mode, const clockid_t clockid)
+{
+	return __hrtimer_nanosleep(rqtp, rmtp, mode, clockid, TASK_INTERRUPTIBLE);
+}
+
 SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
 		struct timespec __user *, rmtp)
 {
@@ -1667,6 +1889,26 @@
 	return hrtimer_nanosleep(&tu, rmtp, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
 }
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+/*
+ * Sleep for 1 ms in hope whoever holds what we want will let it go.
+ */
+void cpu_chill(void)
+{
+	struct timespec tu = {
+		.tv_nsec = NSEC_PER_MSEC,
+	};
+	unsigned int freeze_flag = current->flags & PF_NOFREEZE;
+
+	current->flags |= PF_NOFREEZE;
+	__hrtimer_nanosleep(&tu, NULL, HRTIMER_MODE_REL, CLOCK_MONOTONIC,
+			    TASK_UNINTERRUPTIBLE);
+	if (!freeze_flag)
+		current->flags &= ~PF_NOFREEZE;
+}
+EXPORT_SYMBOL(cpu_chill);
+#endif
+
 /*
  * Functions related to boot-time initialization:
  */
@@ -1678,9 +1920,13 @@
 	for (i = 0; i < HRTIMER_MAX_CLOCK_BASES; i++) {
 		cpu_base->clock_base[i].cpu_base = cpu_base;
 		timerqueue_init_head(&cpu_base->clock_base[i].active);
+		INIT_LIST_HEAD(&cpu_base->clock_base[i].expired);
 	}
 
 	hrtimer_init_hres(cpu_base);
+#ifdef CONFIG_PREEMPT_RT_BASE
+	init_waitqueue_head(&cpu_base->wait);
+#endif
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -1793,9 +2039,7 @@
 	hrtimer_cpu_notify(&hrtimers_nb, (unsigned long)CPU_UP_PREPARE,
 			  (void *)(long)smp_processor_id());
 	register_cpu_notifier(&hrtimers_nb);
-#ifdef CONFIG_HIGH_RES_TIMERS
 	open_softirq(HRTIMER_SOFTIRQ, run_hrtimer_softirq);
-#endif
 }
 
 /**
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 10e0772..f6b91bc 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -116,6 +116,8 @@
 irqreturn_t
 handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action)
 {
+	struct pt_regs *regs = get_irq_regs();
+	u64 ip = regs ? instruction_pointer(regs) : 0;
 	irqreturn_t retval = IRQ_NONE;
 	unsigned int flags = 0, irq = desc->irq_data.irq;
 
@@ -156,7 +158,11 @@
 		action = action->next;
 	} while (action);
 
-	add_interrupt_randomness(irq, flags);
+#ifndef CONFIG_PREEMPT_RT_FULL
+	add_interrupt_randomness(irq, flags, ip);
+#else
+	desc->random_ip = ip;
+#endif
 
 	if (!noirqdebug)
 		note_interrupt(irq, desc, retval);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 127a32e..e4549b2 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -18,6 +18,7 @@
 #include "internals.h"
 
 #ifdef CONFIG_IRQ_FORCED_THREADING
+# ifndef CONFIG_PREEMPT_RT_BASE
 __read_mostly bool force_irqthreads;
 
 static int __init setup_forced_irqthreads(char *arg)
@@ -26,6 +27,7 @@
 	return 0;
 }
 early_param("threadirqs", setup_forced_irqthreads);
+# endif
 #endif
 
 /**
@@ -139,6 +141,62 @@
 irq_get_pending(struct cpumask *mask, struct irq_desc *desc) { }
 #endif
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void _irq_affinity_notify(struct irq_affinity_notify *notify);
+static struct task_struct *set_affinity_helper;
+static LIST_HEAD(affinity_list);
+static DEFINE_RAW_SPINLOCK(affinity_list_lock);
+
+static int set_affinity_thread(void *unused)
+{
+	while (1) {
+		struct irq_affinity_notify *notify;
+		int empty;
+
+		set_current_state(TASK_INTERRUPTIBLE);
+
+		raw_spin_lock_irq(&affinity_list_lock);
+		empty = list_empty(&affinity_list);
+		raw_spin_unlock_irq(&affinity_list_lock);
+
+		if (empty)
+			schedule();
+		if (kthread_should_stop())
+			break;
+		set_current_state(TASK_RUNNING);
+try_next:
+		notify = NULL;
+
+		raw_spin_lock_irq(&affinity_list_lock);
+		if (!list_empty(&affinity_list)) {
+			notify = list_first_entry(&affinity_list,
+					struct irq_affinity_notify, list);
+			list_del_init(&notify->list);
+		}
+		raw_spin_unlock_irq(&affinity_list_lock);
+
+		if (!notify)
+			continue;
+		_irq_affinity_notify(notify);
+		goto try_next;
+	}
+	return 0;
+}
+
+static void init_helper_thread(void)
+{
+	if (set_affinity_helper)
+		return;
+	set_affinity_helper = kthread_run(set_affinity_thread, NULL,
+			"affinity-cb");
+	WARN_ON(IS_ERR(set_affinity_helper));
+}
+#else
+
+static inline void init_helper_thread(void) { }
+
+#endif
+
 int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask)
 {
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
@@ -164,7 +222,17 @@
 
 	if (desc->affinity_notify) {
 		kref_get(&desc->affinity_notify->kref);
+
+#ifdef CONFIG_PREEMPT_RT_FULL
+		raw_spin_lock(&affinity_list_lock);
+		if (list_empty(&desc->affinity_notify->list))
+			list_add_tail(&affinity_list,
+					&desc->affinity_notify->list);
+		raw_spin_unlock(&affinity_list_lock);
+		wake_up_process(set_affinity_helper);
+#else
 		schedule_work(&desc->affinity_notify->work);
+#endif
 	}
 	irqd_set(data, IRQD_AFFINITY_SET);
 
@@ -205,10 +273,8 @@
 }
 EXPORT_SYMBOL_GPL(irq_set_affinity_hint);
 
-static void irq_affinity_notify(struct work_struct *work)
+static void _irq_affinity_notify(struct irq_affinity_notify *notify)
 {
-	struct irq_affinity_notify *notify =
-		container_of(work, struct irq_affinity_notify, work);
 	struct irq_desc *desc = irq_to_desc(notify->irq);
 	cpumask_var_t cpumask;
 	unsigned long flags;
@@ -230,6 +296,13 @@
 	kref_put(&notify->kref, notify->release);
 }
 
+static void irq_affinity_notify(struct work_struct *work)
+{
+	struct irq_affinity_notify *notify =
+		container_of(work, struct irq_affinity_notify, work);
+	_irq_affinity_notify(notify);
+}
+
 /**
  *	irq_set_affinity_notifier - control notification of IRQ affinity changes
  *	@irq:		Interrupt for which to enable/disable notification
@@ -259,6 +332,8 @@
 		notify->irq = irq;
 		kref_init(&notify->kref);
 		INIT_WORK(&notify->work, irq_affinity_notify);
+		INIT_LIST_HEAD(&notify->list);
+		init_helper_thread();
 	}
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
@@ -749,7 +824,15 @@
 	local_bh_disable();
 	ret = action->thread_fn(action->irq, action->dev_id);
 	irq_finalize_oneshot(desc, action, false);
-	local_bh_enable();
+	/*
+	 * Interrupts which have real time requirements can be set up
+	 * to avoid softirq processing in the thread handler. This is
+	 * safe as these interrupts do not raise soft interrupts.
+	 */
+	if (irq_settings_no_softirq_call(desc))
+		_local_bh_enable();
+	else
+		local_bh_enable();
 	return ret;
 }
 
@@ -773,9 +856,6 @@
  */
 static int irq_thread(void *data)
 {
-	static const struct sched_param param = {
-		.sched_priority = MAX_USER_RT_PRIO/2,
-	};
 	struct irqaction *action = data;
 	struct irq_desc *desc = irq_to_desc(action->irq);
 	irqreturn_t (*handler_fn)(struct irq_desc *desc,
@@ -788,7 +868,6 @@
 	else
 		handler_fn = irq_thread_fn;
 
-	sched_setscheduler(current, SCHED_FIFO, &param);
 	current->irqaction = action;
 
 	while (!irq_wait_for_interrupt(action)) {
@@ -815,6 +894,12 @@
 			action_ret = handler_fn(desc, action);
 			if (action_ret == IRQ_HANDLED)
 				atomic_inc(&desc->threads_handled);
+#ifdef CONFIG_PREEMPT_RT_FULL
+			migrate_disable();
+			add_interrupt_randomness(action->irq, 0,
+						 desc->random_ip ^ (u64) action);
+			migrate_enable();
+#endif
 		}
 
 		wake = atomic_dec_and_test(&desc->threads_active);
@@ -945,6 +1030,9 @@
 	 */
 	if (new->thread_fn && !nested) {
 		struct task_struct *t;
+		static const struct sched_param param = {
+			.sched_priority = MAX_USER_RT_PRIO/2,
+		};
 
 		t = kthread_create(irq_thread, new, "irq/%d-%s", irq,
 				   new->name);
@@ -952,6 +1040,9 @@
 			ret = PTR_ERR(t);
 			goto out_mput;
 		}
+
+		sched_setscheduler_nocheck(t, SCHED_FIFO, &param);
+
 		/*
 		 * We keep the reference to the task struct even if
 		 * the thread dies to avoid that the interrupt code
@@ -1089,6 +1180,9 @@
 			irqd_set(&desc->irq_data, IRQD_NO_BALANCING);
 		}
 
+		if (new->flags & IRQF_NO_SOFTIRQ_CALL)
+			irq_settings_set_no_softirq_call(desc);
+
 		/* Set default affinity mask once everything is setup */
 		setup_affinity(irq, desc, mask);
 
diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h
index 1162f10..0d2c381 100644
--- a/kernel/irq/settings.h
+++ b/kernel/irq/settings.h
@@ -14,6 +14,7 @@
 	_IRQ_NO_BALANCING	= IRQ_NO_BALANCING,
 	_IRQ_NESTED_THREAD	= IRQ_NESTED_THREAD,
 	_IRQ_PER_CPU_DEVID	= IRQ_PER_CPU_DEVID,
+	_IRQ_NO_SOFTIRQ_CALL	= IRQ_NO_SOFTIRQ_CALL,
 	_IRQF_MODIFY_MASK	= IRQF_MODIFY_MASK,
 };
 
@@ -26,6 +27,7 @@
 #define IRQ_NOAUTOEN		GOT_YOU_MORON
 #define IRQ_NESTED_THREAD	GOT_YOU_MORON
 #define IRQ_PER_CPU_DEVID	GOT_YOU_MORON
+#define IRQ_NO_SOFTIRQ_CALL	GOT_YOU_MORON
 #undef IRQF_MODIFY_MASK
 #define IRQF_MODIFY_MASK	GOT_YOU_MORON
 
@@ -36,6 +38,16 @@
 	desc->status_use_accessors |= (set & _IRQF_MODIFY_MASK);
 }
 
+static inline bool irq_settings_no_softirq_call(struct irq_desc *desc)
+{
+	return desc->status_use_accessors & _IRQ_NO_SOFTIRQ_CALL;
+}
+
+static inline void irq_settings_set_no_softirq_call(struct irq_desc *desc)
+{
+	desc->status_use_accessors |= _IRQ_NO_SOFTIRQ_CALL;
+}
+
 static inline bool irq_settings_is_per_cpu(struct irq_desc *desc)
 {
 	return desc->status_use_accessors & _IRQ_PER_CPU;
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 6d426eb..0d11a24 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -438,6 +438,11 @@
 
 static int __init irqfixup_setup(char *str)
 {
+#ifdef CONFIG_PREEMPT_RT_BASE
+	printk(KERN_WARNING "irqfixup boot option not supported "
+		"w/ CONFIG_PREEMPT_RT\n");
+	return 1;
+#endif
 	irqfixup = 1;
 	printk(KERN_WARNING "Misrouted IRQ fixup support enabled.\n");
 	printk(KERN_WARNING "This may impact system performance.\n");
@@ -450,6 +455,11 @@
 
 static int __init irqpoll_setup(char *str)
 {
+#ifdef CONFIG_PREEMPT_RT_BASE
+	printk(KERN_WARNING "irqpoll boot option not supported "
+		"w/ CONFIG_PREEMPT_RT\n");
+	return 1;
+#endif
 	irqfixup = 2;
 	printk(KERN_WARNING "Misrouted IRQ fixup and polling support "
 				"enabled\n");
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index c3c46c7..727ba59 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -105,8 +105,10 @@
 	if (llist_empty(this_list))
 		return;
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 	BUG_ON(!in_irq());
 	BUG_ON(!irqs_disabled());
+#endif
 
 	llnode = llist_del_all(this_list);
 	while (llnode != NULL) {
diff --git a/kernel/itimer.c b/kernel/itimer.c
index d802883..2c582fc 100644
--- a/kernel/itimer.c
+++ b/kernel/itimer.c
@@ -214,6 +214,7 @@
 		/* We are sharing ->siglock with it_real_fn() */
 		if (hrtimer_try_to_cancel(timer) < 0) {
 			spin_unlock_irq(&tsk->sighand->siglock);
+			hrtimer_wait_for_timer(&tsk->signal->real_timer);
 			goto again;
 		}
 		expires = timeval_to_ktime(value->it_value);
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index 4e316e1..a546d33 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -133,6 +133,15 @@
 
 #endif /* CONFIG_KEXEC */
 
+#if defined(CONFIG_PREEMPT_RT_FULL)
+static ssize_t  realtime_show(struct kobject *kobj,
+			      struct kobj_attribute *attr, char *buf)
+{
+	return sprintf(buf, "%d\n", 1);
+}
+KERNEL_ATTR_RO(realtime);
+#endif
+
 /* whether file capabilities are enabled */
 static ssize_t fscaps_show(struct kobject *kobj,
 				  struct kobj_attribute *attr, char *buf)
@@ -182,6 +191,9 @@
 	&kexec_crash_size_attr.attr,
 	&vmcoreinfo_attr.attr,
 #endif
+#ifdef CONFIG_PREEMPT_RT_FULL
+	&realtime_attr.attr,
+#endif
 	NULL
 };
 
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index b2e08c9..334d3c0 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -3494,6 +3494,7 @@
 		}
 	}
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 	/*
 	 * We dont accurately track softirq state in e.g.
 	 * hardirq contexts (such as on 4KSTACKS), so only
@@ -3508,6 +3509,7 @@
 			DEBUG_LOCKS_WARN_ON(!current->softirqs_enabled);
 		}
 	}
+#endif
 
 	if (!debug_locks)
 		print_irqtrace_events(current);
diff --git a/kernel/mutex.c b/kernel/mutex.c
index 89096dd..a307cc9 100644
--- a/kernel/mutex.c
+++ b/kernel/mutex.c
@@ -240,9 +240,7 @@
 
 		/* didn't get the lock, go to sleep: */
 		spin_unlock_mutex(&lock->wait_lock, flags);
-		preempt_enable_no_resched();
-		schedule();
-		preempt_disable();
+		schedule_preempt_disabled();
 		spin_lock_mutex(&lock->wait_lock, flags);
 	}
 
diff --git a/kernel/panic.c b/kernel/panic.c
index 3458469..50f4de5 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -343,9 +343,11 @@
 
 static int init_oops_id(void)
 {
+#ifndef CONFIG_PREEMPT_RT_FULL
 	if (!oops_id)
 		get_random_bytes(&oops_id, sizeof(oops_id));
 	else
+#endif
 		oops_id++;
 
 	return 0;
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 962c291..61e7344 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -701,7 +701,7 @@
 	/*
 	 * Disarm any old timer after extracting its expiry time.
 	 */
-	BUG_ON(!irqs_disabled());
+	BUG_ON_NONRT(!irqs_disabled());
 
 	ret = 0;
 	old_incr = timer->it.cpu.incr;
@@ -1223,7 +1223,7 @@
 	/*
 	 * Now re-arm for the new expiry time.
 	 */
-	BUG_ON(!irqs_disabled());
+	BUG_ON_NONRT(!irqs_disabled());
 	arm_timer(timer);
 	spin_unlock(&p->sighand->siglock);
 
@@ -1290,10 +1290,11 @@
 	sig = tsk->signal;
 	if (sig->cputimer.running) {
 		struct task_cputime group_sample;
+		unsigned long flags;
 
-		raw_spin_lock(&sig->cputimer.lock);
+		raw_spin_lock_irqsave(&sig->cputimer.lock, flags);
 		group_sample = sig->cputimer.cputime;
-		raw_spin_unlock(&sig->cputimer.lock);
+		raw_spin_unlock_irqrestore(&sig->cputimer.lock, flags);
 
 		if (task_cputime_expired(&group_sample, &sig->cputime_expires))
 			return 1;
@@ -1307,13 +1308,13 @@
  * already updated our counts.  We need to check if any timers fire now.
  * Interrupts are disabled.
  */
-void run_posix_cpu_timers(struct task_struct *tsk)
+static void __run_posix_cpu_timers(struct task_struct *tsk)
 {
 	LIST_HEAD(firing);
 	struct k_itimer *timer, *next;
 	unsigned long flags;
 
-	BUG_ON(!irqs_disabled());
+	BUG_ON_NONRT(!irqs_disabled());
 
 	/*
 	 * The fast path checks that there are no expired thread or thread
@@ -1371,6 +1372,190 @@
 	}
 }
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+#include <linux/kthread.h>
+#include <linux/cpu.h>
+DEFINE_PER_CPU(struct task_struct *, posix_timer_task);
+DEFINE_PER_CPU(struct task_struct *, posix_timer_tasklist);
+
+static int posix_cpu_timers_thread(void *data)
+{
+	int cpu = (long)data;
+
+	BUG_ON(per_cpu(posix_timer_task,cpu) != current);
+
+	while (!kthread_should_stop()) {
+		struct task_struct *tsk = NULL;
+		struct task_struct *next = NULL;
+
+		if (cpu_is_offline(cpu))
+			goto wait_to_die;
+
+		/* grab task list */
+		raw_local_irq_disable();
+		tsk = per_cpu(posix_timer_tasklist, cpu);
+		per_cpu(posix_timer_tasklist, cpu) = NULL;
+		raw_local_irq_enable();
+
+		/* its possible the list is empty, just return */
+		if (!tsk) {
+			set_current_state(TASK_INTERRUPTIBLE);
+			schedule();
+			__set_current_state(TASK_RUNNING);
+			continue;
+		}
+
+		/* Process task list */
+		while (1) {
+			/* save next */
+			next = tsk->posix_timer_list;
+
+			/* run the task timers, clear its ptr and
+			 * unreference it
+			 */
+			__run_posix_cpu_timers(tsk);
+			tsk->posix_timer_list = NULL;
+			put_task_struct(tsk);
+
+			/* check if this is the last on the list */
+			if (next == tsk)
+				break;
+			tsk = next;
+		}
+	}
+	return 0;
+
+wait_to_die:
+	/* Wait for kthread_stop */
+	set_current_state(TASK_INTERRUPTIBLE);
+	while (!kthread_should_stop()) {
+		schedule();
+		set_current_state(TASK_INTERRUPTIBLE);
+	}
+	__set_current_state(TASK_RUNNING);
+	return 0;
+}
+
+static inline int __fastpath_timer_check(struct task_struct *tsk)
+{
+	/* tsk == current, ensure it is safe to use ->signal/sighand */
+	if (unlikely(tsk->exit_state))
+		return 0;
+
+	if (!task_cputime_zero(&tsk->cputime_expires))
+			return 1;
+
+	if (!task_cputime_zero(&tsk->signal->cputime_expires))
+			return 1;
+
+	return 0;
+}
+
+void run_posix_cpu_timers(struct task_struct *tsk)
+{
+	unsigned long cpu = smp_processor_id();
+	struct task_struct *tasklist;
+
+	BUG_ON(!irqs_disabled());
+	if(!per_cpu(posix_timer_task, cpu))
+		return;
+	/* get per-cpu references */
+	tasklist = per_cpu(posix_timer_tasklist, cpu);
+
+	/* check to see if we're already queued */
+	if (!tsk->posix_timer_list && __fastpath_timer_check(tsk)) {
+		get_task_struct(tsk);
+		if (tasklist) {
+			tsk->posix_timer_list = tasklist;
+		} else {
+			/*
+			 * The list is terminated by a self-pointing
+			 * task_struct
+			 */
+			tsk->posix_timer_list = tsk;
+		}
+		per_cpu(posix_timer_tasklist, cpu) = tsk;
+
+		wake_up_process(per_cpu(posix_timer_task, cpu));
+	}
+}
+
+/*
+ * posix_cpu_thread_call - callback that gets triggered when a CPU is added.
+ * Here we can start up the necessary migration thread for the new CPU.
+ */
+static int posix_cpu_thread_call(struct notifier_block *nfb,
+				 unsigned long action, void *hcpu)
+{
+	int cpu = (long)hcpu;
+	struct task_struct *p;
+	struct sched_param param;
+
+	switch (action) {
+	case CPU_UP_PREPARE:
+		p = kthread_create(posix_cpu_timers_thread, hcpu,
+					"posixcputmr/%d",cpu);
+		if (IS_ERR(p))
+			return NOTIFY_BAD;
+		p->flags |= PF_NOFREEZE;
+		kthread_bind(p, cpu);
+		/* Must be high prio to avoid getting starved */
+		param.sched_priority = MAX_RT_PRIO-1;
+		sched_setscheduler(p, SCHED_FIFO, &param);
+		per_cpu(posix_timer_task,cpu) = p;
+		break;
+	case CPU_ONLINE:
+		/* Strictly unneccessary, as first user will wake it. */
+		wake_up_process(per_cpu(posix_timer_task,cpu));
+		break;
+#ifdef CONFIG_HOTPLUG_CPU
+	case CPU_UP_CANCELED:
+		/* Unbind it from offline cpu so it can run.  Fall thru. */
+		kthread_bind(per_cpu(posix_timer_task,cpu),
+			     any_online_cpu(cpu_online_map));
+		kthread_stop(per_cpu(posix_timer_task,cpu));
+		per_cpu(posix_timer_task,cpu) = NULL;
+		break;
+	case CPU_DEAD:
+		kthread_stop(per_cpu(posix_timer_task,cpu));
+		per_cpu(posix_timer_task,cpu) = NULL;
+		break;
+#endif
+	}
+	return NOTIFY_OK;
+}
+
+/* Register at highest priority so that task migration (migrate_all_tasks)
+ * happens before everything else.
+ */
+static struct notifier_block __devinitdata posix_cpu_thread_notifier = {
+	.notifier_call = posix_cpu_thread_call,
+	.priority = 10
+};
+
+static int __init posix_cpu_thread_init(void)
+{
+	void *hcpu = (void *)(long)smp_processor_id();
+	/* Start one for boot CPU. */
+	unsigned long cpu;
+
+	/* init the per-cpu posix_timer_tasklets */
+	for_each_cpu_mask(cpu, cpu_possible_map)
+		per_cpu(posix_timer_tasklist, cpu) = NULL;
+
+	posix_cpu_thread_call(&posix_cpu_thread_notifier, CPU_UP_PREPARE, hcpu);
+	posix_cpu_thread_call(&posix_cpu_thread_notifier, CPU_ONLINE, hcpu);
+	register_cpu_notifier(&posix_cpu_thread_notifier);
+	return 0;
+}
+early_initcall(posix_cpu_thread_init);
+#else /* CONFIG_PREEMPT_RT_BASE */
+void run_posix_cpu_timers(struct task_struct *tsk)
+{
+	__run_posix_cpu_timers(tsk);
+}
+#endif /* CONFIG_PREEMPT_RT_BASE */
+
 /*
  * Set one of the process-wide special case CPU timers or RLIMIT_CPU.
  * The tsk->sighand->siglock must be held by the caller.
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 02824a5..f183690 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -439,6 +439,7 @@
 static struct pid *good_sigevent(sigevent_t * event)
 {
 	struct task_struct *rtn = current->group_leader;
+	int sig = event->sigev_signo;
 
 	if ((event->sigev_notify & SIGEV_THREAD_ID ) &&
 		(!(rtn = find_task_by_vpid(event->sigev_notify_thread_id)) ||
@@ -447,7 +448,8 @@
 		return NULL;
 
 	if (((event->sigev_notify & ~SIGEV_THREAD_ID) != SIGEV_NONE) &&
-	    ((event->sigev_signo <= 0) || (event->sigev_signo > SIGRTMAX)))
+	    (sig <= 0 || sig > SIGRTMAX || sig_kernel_only(sig) ||
+	     sig_kernel_coredump(sig)))
 		return NULL;
 
 	return task_pid(rtn);
@@ -772,6 +774,20 @@
 	return overrun;
 }
 
+/*
+ * Protected by RCU!
+ */
+static void timer_wait_for_callback(struct k_clock *kc, struct k_itimer *timr)
+{
+#ifdef CONFIG_PREEMPT_RT_FULL
+	if (kc->timer_set == common_timer_set)
+		hrtimer_wait_for_timer(&timr->it.real.timer);
+	else
+		/* FIXME: Whacky hack for posix-cpu-timers */
+		schedule_timeout(1);
+#endif
+}
+
 /* Set a POSIX.1b interval timer. */
 /* timr->it_lock is taken. */
 static int
@@ -849,6 +865,7 @@
 	if (!timr)
 		return -EINVAL;
 
+	rcu_read_lock();
 	kc = clockid_to_kclock(timr->it_clock);
 	if (WARN_ON_ONCE(!kc || !kc->timer_set))
 		error = -EINVAL;
@@ -857,9 +874,12 @@
 
 	unlock_timer(timr, flag);
 	if (error == TIMER_RETRY) {
+		timer_wait_for_callback(kc, timr);
 		rtn = NULL;	// We already got the old time...
+		rcu_read_unlock();
 		goto retry;
 	}
+	rcu_read_unlock();
 
 	if (old_setting && !error &&
 	    copy_to_user(old_setting, &old_spec, sizeof (old_spec)))
@@ -897,10 +917,15 @@
 	if (!timer)
 		return -EINVAL;
 
+	rcu_read_lock();
 	if (timer_delete_hook(timer) == TIMER_RETRY) {
 		unlock_timer(timer, flags);
+		timer_wait_for_callback(clockid_to_kclock(timer->it_clock),
+					timer);
+		rcu_read_unlock();
 		goto retry_delete;
 	}
+	rcu_read_unlock();
 
 	spin_lock(&current->sighand->siglock);
 	list_del(&timer->list);
@@ -926,8 +951,18 @@
 retry_delete:
 	spin_lock_irqsave(&timer->it_lock, flags);
 
-	if (timer_delete_hook(timer) == TIMER_RETRY) {
+	/* On RT we can race with a deletion */
+	if (!timer->it_signal) {
 		unlock_timer(timer, flags);
+		return;
+	}
+
+	if (timer_delete_hook(timer) == TIMER_RETRY) {
+		rcu_read_lock();
+		unlock_timer(timer, flags);
+		timer_wait_for_callback(clockid_to_kclock(timer->it_clock),
+					timer);
+		rcu_read_unlock();
 		goto retry_delete;
 	}
 	list_del(&timer->list);
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index e4ce628..6187c03 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -284,6 +284,8 @@
 
 	local_irq_disable();
 
+	system_state = SYSTEM_SUSPEND;
+
 	error = syscore_suspend();
 	if (error) {
 		printk(KERN_ERR "PM: Some system devices failed to power down, "
@@ -311,6 +313,7 @@
 	syscore_resume();
 
  Enable_irqs:
+	system_state = SYSTEM_RUNNING;
 	local_irq_enable();
 
  Enable_cpus:
@@ -439,6 +442,7 @@
 		goto Enable_cpus;
 
 	local_irq_disable();
+	system_state = SYSTEM_SUSPEND;
 
 	error = syscore_suspend();
 	if (error)
@@ -472,6 +476,7 @@
 	syscore_resume();
 
  Enable_irqs:
+	system_state = SYSTEM_RUNNING;
 	local_irq_enable();
 
  Enable_cpus:
@@ -560,6 +565,7 @@
 		goto Platform_finish;
 
 	local_irq_disable();
+	system_state = SYSTEM_SUSPEND;
 	syscore_suspend();
 	if (pm_wakeup_pending()) {
 		error = -EAGAIN;
@@ -572,6 +578,7 @@
 
  Power_up:
 	syscore_resume();
+	system_state = SYSTEM_RUNNING;
 	local_irq_enable();
 	enable_nonboot_cpus();
 
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index af48faa..ad3690c 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -172,6 +172,8 @@
 	arch_suspend_disable_irqs();
 	BUG_ON(!irqs_disabled());
 
+	system_state = SYSTEM_SUSPEND;
+
 	error = syscore_suspend();
 	if (!error) {
 		*wakeup = pm_wakeup_pending();
@@ -182,6 +184,8 @@
 		syscore_resume();
 	}
 
+	system_state = SYSTEM_RUNNING;
+
 	arch_suspend_enable_irqs();
 	BUG_ON(irqs_disabled());
 
diff --git a/kernel/printk.c b/kernel/printk.c
index c073f43..e230be6c 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -44,13 +44,6 @@
 
 #include <asm/uaccess.h>
 
-/*
- * Architectures can override it:
- */
-void asmlinkage __attribute__((weak)) early_printk(const char *fmt, ...)
-{
-}
-
 #define __LOG_BUF_LEN	(1 << CONFIG_LOG_BUF_SHIFT)
 
 /* printk's without a loglevel use this.. */
@@ -511,6 +504,7 @@
 {
 	struct console *con;
 
+	migrate_disable();
 	for_each_console(con) {
 		if (exclusive_console && con != exclusive_console)
 			continue;
@@ -519,8 +513,62 @@
 				(con->flags & CON_ANYTIME)))
 			con->write(con, &LOG_BUF(start), end - start);
 	}
+	migrate_enable();
 }
 
+#ifdef CONFIG_EARLY_PRINTK
+struct console *early_console;
+
+static void early_vprintk(const char *fmt, va_list ap)
+{
+	char buf[512];
+	int n = vscnprintf(buf, sizeof(buf), fmt, ap);
+	if (early_console)
+		early_console->write(early_console, buf, n);
+}
+
+asmlinkage void early_printk(const char *fmt, ...)
+{
+	va_list ap;
+	va_start(ap, fmt);
+	early_vprintk(fmt, ap);
+	va_end(ap);
+}
+
+/*
+ * This is independent of any log levels - a global
+ * kill switch that turns off all of printk.
+ *
+ * Used by the NMI watchdog if early-printk is enabled.
+ */
+static int __read_mostly printk_killswitch;
+
+static int __init force_early_printk_setup(char *str)
+{
+	printk_killswitch = 1;
+	return 0;
+}
+early_param("force_early_printk", force_early_printk_setup);
+
+void printk_kill(void)
+{
+	printk_killswitch = 1;
+}
+
+static int forced_early_printk(const char *fmt, va_list ap)
+{
+	if (!printk_killswitch)
+		return 0;
+	early_vprintk(fmt, ap);
+	return 1;
+}
+#else
+static inline int forced_early_printk(const char *fmt, va_list ap)
+{
+	return 0;
+}
+#endif
+
 static int __read_mostly ignore_loglevel;
 
 static int __init ignore_loglevel_setup(char *str)
@@ -792,12 +840,18 @@
  * interrupts disabled. It should return with 'lockbuf_lock'
  * released but interrupts still disabled.
  */
-static int console_trylock_for_printk(unsigned int cpu)
+static int console_trylock_for_printk(unsigned int cpu, unsigned long flags)
 	__releases(&logbuf_lock)
 {
 	int retval = 0, wake = 0;
+#ifdef CONFIG_PREEMPT_RT_FULL
+	int lock = !early_boot_irqs_disabled && !irqs_disabled_flags(flags) &&
+		(preempt_count() <= 1);
+#else
+	int lock = 1;
+#endif
 
-	if (console_trylock()) {
+	if (lock && console_trylock()) {
 		retval = 1;
 
 		/*
@@ -848,10 +902,17 @@
 	size_t plen;
 	char special;
 
+	/*
+	 * Fall back to early_printk if a debugging subsystem has
+	 * killed printk output
+	 */
+	if (unlikely(forced_early_printk(fmt, args)))
+		return 1;
+
 	boot_delay_msec();
 	printk_delay();
 
-	preempt_disable();
+	migrate_disable();
 	/* This stops the holder of console_sem just where we want him */
 	raw_local_irq_save(flags);
 	this_cpu = smp_processor_id();
@@ -968,14 +1029,21 @@
 	 * will release 'logbuf_lock' regardless of whether it
 	 * actually gets the semaphore or not.
 	 */
-	if (console_trylock_for_printk(this_cpu))
+	if (console_trylock_for_printk(this_cpu, flags)) {
+#ifndef CONFIG_PREEMPT_RT_FULL
 		console_unlock();
+#else
+		raw_local_irq_restore(flags);
+		console_unlock();
+		raw_local_irq_save(flags);
+#endif
+	}
 
 	lockdep_on();
 out_restore_irqs:
 	raw_local_irq_restore(flags);
 
-	preempt_enable();
+	migrate_enable();
 	return printed_len;
 }
 EXPORT_SYMBOL(printk);
@@ -1231,8 +1299,8 @@
 
 int printk_needs_cpu(int cpu)
 {
-	if (cpu_is_offline(cpu))
-		printk_tick();
+	if (unlikely(cpu_is_offline(cpu)))
+		__this_cpu_write(printk_pending, 0);
 	return __this_cpu_read(printk_pending);
 }
 
@@ -1278,11 +1346,16 @@
 		_con_start = con_start;
 		_log_end = log_end;
 		con_start = log_end;		/* Flush */
+#ifndef CONFIG_PREEMPT_RT_FULL
 		raw_spin_unlock(&logbuf_lock);
 		stop_critical_timings();	/* don't trace print latency */
 		call_console_drivers(_con_start, _log_end);
 		start_critical_timings();
 		local_irq_restore(flags);
+#else
+		raw_spin_unlock_irqrestore(&logbuf_lock, flags);
+		call_console_drivers(_con_start, _log_end);
+#endif
 	}
 	console_locked = 0;
 
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index c5b98e5..24dcc71 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -77,6 +77,7 @@
 }
 EXPORT_SYMBOL_GPL(debug_lockdep_rcu_enabled);
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /**
  * rcu_read_lock_bh_held() - might we be in RCU-bh read-side critical section?
  *
@@ -96,6 +97,7 @@
 	return in_softirq() || irqs_disabled();
 }
 EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held);
+#endif
 
 #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */
 
diff --git a/kernel/rcutiny.c b/kernel/rcutiny.c
index bc84596..724988c 100644
--- a/kernel/rcutiny.c
+++ b/kernel/rcutiny.c
@@ -248,6 +248,7 @@
 }
 EXPORT_SYMBOL_GPL(call_rcu_sched);
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /*
  * Post an RCU bottom-half callback to be invoked after any subsequent
  * quiescent state.
@@ -257,3 +258,4 @@
 	__call_rcu(head, func, &rcu_bh_ctrlblk);
 }
 EXPORT_SYMBOL_GPL(call_rcu_bh);
+#endif
diff --git a/kernel/rcutiny_plugin.h b/kernel/rcutiny_plugin.h
index 2b0484a..6242ccd 100644
--- a/kernel/rcutiny_plugin.h
+++ b/kernel/rcutiny_plugin.h
@@ -26,6 +26,7 @@
 #include <linux/module.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
+#include <linux/wait-simple.h>
 
 /* Global control variables for rcupdate callback mechanism. */
 struct rcu_ctrlblk {
@@ -250,7 +251,7 @@
 
 /* Controls for rcu_kthread() kthread. */
 static struct task_struct *rcu_kthread_task;
-static DECLARE_WAIT_QUEUE_HEAD(rcu_kthread_wq);
+static DEFINE_SWAIT_HEAD(rcu_kthread_wq);
 static unsigned long have_rcu_kthread_work;
 
 /*
@@ -720,7 +721,7 @@
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu);
 
-static DECLARE_WAIT_QUEUE_HEAD(sync_rcu_preempt_exp_wq);
+static DEFINE_SWAIT_HEAD(sync_rcu_preempt_exp_wq);
 static unsigned long sync_rcu_preempt_exp_count;
 static DEFINE_MUTEX(sync_rcu_preempt_exp_mutex);
 
@@ -742,7 +743,7 @@
  */
 static void rcu_report_exp_done(void)
 {
-	wake_up(&sync_rcu_preempt_exp_wq);
+	swait_wake(&sync_rcu_preempt_exp_wq);
 }
 
 /*
@@ -794,8 +795,8 @@
 	else {
 		rcu_initiate_boost();
 		local_irq_restore(flags);
-		wait_event(sync_rcu_preempt_exp_wq,
-			   !rcu_preempted_readers_exp());
+		swait_event(sync_rcu_preempt_exp_wq,
+			    !rcu_preempted_readers_exp());
 	}
 
 	/* Clean up and exit. */
@@ -882,7 +883,7 @@
 static void invoke_rcu_callbacks(void)
 {
 	have_rcu_kthread_work = 1;
-	wake_up(&rcu_kthread_wq);
+	swait_wake(&rcu_kthread_wq);
 }
 
 /*
@@ -899,8 +900,8 @@
 	unsigned long flags;
 
 	for (;;) {
-		wait_event_interruptible(rcu_kthread_wq,
-					 have_rcu_kthread_work != 0);
+		swait_event_interruptible(rcu_kthread_wq,
+					  have_rcu_kthread_work != 0);
 		morework = rcu_boost();
 		local_irq_save(flags);
 		work = have_rcu_kthread_work;
diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 1aa52af..6c2ec2d 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -170,6 +170,19 @@
 	rdp->passed_quiesce = 1;
 }
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void rcu_preempt_qs(int cpu);
+
+void rcu_bh_qs(int cpu)
+{
+	unsigned long flags;
+
+	/* Callers to this function, rcu_preempt_qs(), must disable irqs. */
+	local_irq_save(flags);
+	rcu_preempt_qs(cpu);
+	local_irq_restore(flags);
+}
+#else
 void rcu_bh_qs(int cpu)
 {
 	struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);
@@ -180,6 +193,7 @@
 		trace_rcu_grace_period("rcu_bh", rdp->gpnum, "cpuqs");
 	rdp->passed_quiesce = 1;
 }
+#endif
 
 /*
  * Note a context switch.  This is a quiescent state for RCU-sched,
@@ -225,6 +239,7 @@
 }
 EXPORT_SYMBOL_GPL(rcu_batches_completed_sched);
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /*
  * Return the number of RCU BH batches processed thus far for debug & stats.
  */
@@ -242,6 +257,7 @@
 	force_quiescent_state(&rcu_bh_state, 0);
 }
 EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state);
+#endif
 
 /*
  * Record the number of times rcutorture tests have been initiated and
@@ -1223,7 +1239,7 @@
 	else
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	if (need_report & RCU_OFL_TASKS_EXP_GP)
-		rcu_report_exp_rnp(rsp, rnp);
+		rcu_report_exp_rnp(rsp, rnp, true);
 	rcu_node_kthread_setaffinity(rnp, -1);
 }
 
@@ -1669,6 +1685,7 @@
 }
 EXPORT_SYMBOL_GPL(call_rcu_sched);
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /*
  * Queue an RCU for invocation after a quicker grace period.
  */
@@ -1677,6 +1694,7 @@
 	__call_rcu(head, func, &rcu_bh_state);
 }
 EXPORT_SYMBOL_GPL(call_rcu_bh);
+#endif
 
 /**
  * synchronize_sched - wait until an rcu-sched grace period has elapsed.
@@ -1709,6 +1727,7 @@
 }
 EXPORT_SYMBOL_GPL(synchronize_sched);
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /**
  * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed.
  *
@@ -1725,6 +1744,7 @@
 	wait_rcu_gp(call_rcu_bh);
 }
 EXPORT_SYMBOL_GPL(synchronize_rcu_bh);
+#endif
 
 /*
  * Check to see if there is any immediate RCU-related work to be done
@@ -1879,6 +1899,7 @@
 	mutex_unlock(&rcu_barrier_mutex);
 }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /**
  * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete.
  */
@@ -1887,6 +1908,7 @@
 	_rcu_barrier(&rcu_bh_state, call_rcu_bh);
 }
 EXPORT_SYMBOL_GPL(rcu_barrier_bh);
+#endif
 
 /**
  * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks.
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index 849ce9e..dca495d 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -451,7 +451,8 @@
 static void rcu_preempt_process_callbacks(void);
 void call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu));
 #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU)
-static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp);
+static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
+			       bool wake);
 #endif /* #if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_TREE_PREEMPT_RCU) */
 static int rcu_preempt_pending(int cpu);
 static int rcu_preempt_needs_cpu(int cpu);
diff --git a/kernel/rcutree_plugin.h b/kernel/rcutree_plugin.h
index 4b9b9f8..936441d 100644
--- a/kernel/rcutree_plugin.h
+++ b/kernel/rcutree_plugin.h
@@ -336,7 +336,7 @@
 	}
 
 	/* Hardware IRQ handlers cannot block. */
-	if (in_irq() || in_serving_softirq()) {
+	if (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_OFFSET)) {
 		local_irq_restore(flags);
 		return;
 	}
@@ -407,7 +407,7 @@
 		 * then we need to report up the rcu_node hierarchy.
 		 */
 		if (!empty_exp && !rcu_preempted_readers_exp(rnp))
-			rcu_report_exp_rnp(&rcu_preempt_state, rnp);
+			rcu_report_exp_rnp(&rcu_preempt_state, rnp, true);
 	} else {
 		local_irq_restore(flags);
 	}
@@ -731,7 +731,8 @@
  *
  * Caller must hold sync_rcu_preempt_exp_mutex.
  */
-static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
+static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
+			       bool wake)
 {
 	unsigned long flags;
 	unsigned long mask;
@@ -744,7 +745,8 @@
 		}
 		if (rnp->parent == NULL) {
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
-			wake_up(&sync_rcu_preempt_exp_wq);
+			if (wake)
+				wake_up(&sync_rcu_preempt_exp_wq);
 			break;
 		}
 		mask = rnp->grpmask;
@@ -777,7 +779,7 @@
 		must_wait = 1;
 	}
 	if (!must_wait)
-		rcu_report_exp_rnp(rsp, rnp);
+		rcu_report_exp_rnp(rsp, rnp, false);
 }
 
 /*
@@ -1069,9 +1071,9 @@
  * report on tasks preempted in RCU read-side critical sections during
  * expedited RCU grace periods.
  */
-static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp)
+static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
+			       bool wake)
 {
-	return;
 }
 
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
@@ -1931,7 +1933,7 @@
 
 #endif /* #else #ifndef CONFIG_SMP */
 
-#if !defined(CONFIG_RCU_FAST_NO_HZ)
+#if 1 /* !defined(CONFIG_RCU_FAST_NO_HZ) */
 
 /*
  * Check to see if any future RCU-related work will need to be done
diff --git a/kernel/relay.c b/kernel/relay.c
index a535fc9..c0af3e6 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -340,6 +340,10 @@
 {
 	struct rchan_buf *buf = (struct rchan_buf *)data;
 	wake_up_interruptible(&buf->read_wait);
+	/*
+	 * Stupid polling for now:
+	 */
+	mod_timer(&buf->timer, jiffies + 1);
 }
 
 /**
@@ -357,6 +361,7 @@
 		init_waitqueue_head(&buf->read_wait);
 		kref_init(&buf->kref);
 		setup_timer(&buf->timer, wakeup_readers, (unsigned long)buf);
+		mod_timer(&buf->timer, jiffies + 1);
 	} else
 		del_timer_sync(&buf->timer);
 
@@ -739,15 +744,6 @@
 		else
 			buf->early_bytes += buf->chan->subbuf_size -
 					    buf->padding[old_subbuf];
-		smp_mb();
-		if (waitqueue_active(&buf->read_wait))
-			/*
-			 * Calling wake_up_interruptible() from here
-			 * will deadlock if we happen to be logging
-			 * from the scheduler (trying to re-grab
-			 * rq->lock), so defer it.
-			 */
-			mod_timer(&buf->timer, jiffies + 1);
 	}
 
 	old = buf->data;
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index 34683ef..21e9ec4 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -43,7 +43,7 @@
 	struct res_counter *c, *u;
 
 	*limit_fail_at = NULL;
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 	for (c = counter; c != NULL; c = c->parent) {
 		spin_lock(&c->lock);
 		ret = res_counter_charge_locked(c, val);
@@ -62,7 +62,7 @@
 		spin_unlock(&u->lock);
 	}
 done:
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 	return ret;
 }
 
@@ -79,13 +79,13 @@
 	unsigned long flags;
 	struct res_counter *c;
 
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 	for (c = counter; c != NULL; c = c->parent) {
 		spin_lock(&c->lock);
 		res_counter_uncharge_locked(c, val);
 		spin_unlock(&c->lock);
 	}
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 }
 
 
diff --git a/kernel/rt.c b/kernel/rt.c
new file mode 100644
index 0000000..389f9bd
--- /dev/null
+++ b/kernel/rt.c
@@ -0,0 +1,446 @@
+/*
+ * kernel/rt.c
+ *
+ * Real-Time Preemption Support
+ *
+ * started by Ingo Molnar:
+ *
+ *  Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ *  Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com>
+ *
+ * historic credit for proving that Linux spinlocks can be implemented via
+ * RT-aware mutexes goes to many people: The Pmutex project (Dirk Grambow
+ * and others) who prototyped it on 2.4 and did lots of comparative
+ * research and analysis; TimeSys, for proving that you can implement a
+ * fully preemptible kernel via the use of IRQ threading and mutexes;
+ * Bill Huey for persuasively arguing on lkml that the mutex model is the
+ * right one; and to MontaVista, who ported pmutexes to 2.6.
+ *
+ * This code is a from-scratch implementation and is not based on pmutexes,
+ * but the idea of converting spinlocks to mutexes is used here too.
+ *
+ * lock debugging, locking tree, deadlock detection:
+ *
+ *  Copyright (C) 2004, LynuxWorks, Inc., Igor Manyilov, Bill Huey
+ *  Released under the General Public License (GPL).
+ *
+ * Includes portions of the generic R/W semaphore implementation from:
+ *
+ *  Copyright (c) 2001   David Howells (dhowells@redhat.com).
+ *  - Derived partially from idea by Andrea Arcangeli <andrea@suse.de>
+ *  - Derived also from comments by Linus
+ *
+ * Pending ownership of locks and ownership stealing:
+ *
+ *  Copyright (C) 2005, Kihon Technologies Inc., Steven Rostedt
+ *
+ *   (also by Steven Rostedt)
+ *    - Converted single pi_lock to individual task locks.
+ *
+ * By Esben Nielsen:
+ *    Doing priority inheritance with help of the scheduler.
+ *
+ *  Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com>
+ *  - major rework based on Esben Nielsens initial patch
+ *  - replaced thread_info references by task_struct refs
+ *  - removed task->pending_owner dependency
+ *  - BKL drop/reacquire for semaphore style locks to avoid deadlocks
+ *    in the scheduler return path as discussed with Steven Rostedt
+ *
+ *  Copyright (C) 2006, Kihon Technologies Inc.
+ *    Steven Rostedt <rostedt@goodmis.org>
+ *  - debugged and patched Thomas Gleixner's rework.
+ *  - added back the cmpxchg to the rework.
+ *  - turned atomic require back on for SMP.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/rtmutex.h>
+#include <linux/sched.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/kallsyms.h>
+#include <linux/syscalls.h>
+#include <linux/interrupt.h>
+#include <linux/plist.h>
+#include <linux/fs.h>
+#include <linux/futex.h>
+#include <linux/hrtimer.h>
+
+#include "rtmutex_common.h"
+
+/*
+ * struct mutex functions
+ */
+void __mutex_do_init(struct mutex *mutex, const char *name,
+		     struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/*
+	 * Make sure we are not reinitializing a held lock:
+	 */
+	debug_check_no_locks_freed((void *)mutex, sizeof(*mutex));
+	lockdep_init_map(&mutex->dep_map, name, key, 0);
+#endif
+	mutex->lock.save_state = 0;
+}
+EXPORT_SYMBOL(__mutex_do_init);
+
+void __lockfunc _mutex_lock(struct mutex *lock)
+{
+	mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+	rt_mutex_lock(&lock->lock);
+}
+EXPORT_SYMBOL(_mutex_lock);
+
+int __lockfunc _mutex_lock_interruptible(struct mutex *lock)
+{
+	int ret;
+
+	mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+	ret = rt_mutex_lock_interruptible(&lock->lock);
+	if (ret)
+		mutex_release(&lock->dep_map, 1, _RET_IP_);
+	return ret;
+}
+EXPORT_SYMBOL(_mutex_lock_interruptible);
+
+int __lockfunc _mutex_lock_killable(struct mutex *lock)
+{
+	int ret;
+
+	mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+	ret = rt_mutex_lock_killable(&lock->lock);
+	if (ret)
+		mutex_release(&lock->dep_map, 1, _RET_IP_);
+	return ret;
+}
+EXPORT_SYMBOL(_mutex_lock_killable);
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass)
+{
+	mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_);
+	rt_mutex_lock(&lock->lock);
+}
+EXPORT_SYMBOL(_mutex_lock_nested);
+
+void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest)
+{
+	mutex_acquire_nest(&lock->dep_map, 0, 0, nest, _RET_IP_);
+	rt_mutex_lock(&lock->lock);
+}
+EXPORT_SYMBOL(_mutex_lock_nest_lock);
+
+int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass)
+{
+	int ret;
+
+	mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_);
+	ret = rt_mutex_lock_interruptible(&lock->lock);
+	if (ret)
+		mutex_release(&lock->dep_map, 1, _RET_IP_);
+	return ret;
+}
+EXPORT_SYMBOL(_mutex_lock_interruptible_nested);
+
+int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass)
+{
+	int ret;
+
+	mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
+	ret = rt_mutex_lock_killable(&lock->lock);
+	if (ret)
+		mutex_release(&lock->dep_map, 1, _RET_IP_);
+	return ret;
+}
+EXPORT_SYMBOL(_mutex_lock_killable_nested);
+#endif
+
+int __lockfunc _mutex_trylock(struct mutex *lock)
+{
+	int ret = rt_mutex_trylock(&lock->lock);
+
+	if (ret)
+		mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+
+	return ret;
+}
+EXPORT_SYMBOL(_mutex_trylock);
+
+void __lockfunc _mutex_unlock(struct mutex *lock)
+{
+	mutex_release(&lock->dep_map, 1, _RET_IP_);
+	rt_mutex_unlock(&lock->lock);
+}
+EXPORT_SYMBOL(_mutex_unlock);
+
+/*
+ * rwlock_t functions
+ */
+int __lockfunc rt_write_trylock(rwlock_t *rwlock)
+{
+	int ret = rt_mutex_trylock(&rwlock->lock);
+
+	migrate_disable();
+	if (ret)
+		rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_);
+	else
+		migrate_enable();
+
+	return ret;
+}
+EXPORT_SYMBOL(rt_write_trylock);
+
+int __lockfunc rt_write_trylock_irqsave(rwlock_t *rwlock, unsigned long *flags)
+{
+	int ret;
+
+	*flags = 0;
+	migrate_disable();
+	ret = rt_write_trylock(rwlock);
+	if (!ret)
+		migrate_enable();
+	return ret;
+}
+EXPORT_SYMBOL(rt_write_trylock_irqsave);
+
+int __lockfunc rt_read_trylock(rwlock_t *rwlock)
+{
+	struct rt_mutex *lock = &rwlock->lock;
+	int ret = 1;
+
+	/*
+	 * recursive read locks succeed when current owns the lock,
+	 * but not when read_depth == 0 which means that the lock is
+	 * write locked.
+	 */
+	migrate_disable();
+	if (rt_mutex_owner(lock) != current) {
+		ret = rt_mutex_trylock(lock);
+		if (ret)
+			rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_);
+	} else if (!rwlock->read_depth) {
+		ret = 0;
+	}
+
+	if (ret)
+		rwlock->read_depth++;
+	else
+		migrate_enable();
+
+	return ret;
+}
+EXPORT_SYMBOL(rt_read_trylock);
+
+void __lockfunc rt_write_lock(rwlock_t *rwlock)
+{
+	rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_);
+	__rt_spin_lock(&rwlock->lock);
+}
+EXPORT_SYMBOL(rt_write_lock);
+
+void __lockfunc rt_read_lock(rwlock_t *rwlock)
+{
+	struct rt_mutex *lock = &rwlock->lock;
+
+	/*
+	 * recursive read locks succeed when current owns the lock
+	 */
+	if (rt_mutex_owner(lock) != current) {
+		rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_);
+		__rt_spin_lock(lock);
+	}
+	rwlock->read_depth++;
+}
+
+EXPORT_SYMBOL(rt_read_lock);
+
+void __lockfunc rt_write_unlock(rwlock_t *rwlock)
+{
+	/* NOTE: we always pass in '1' for nested, for simplicity */
+	rwlock_release(&rwlock->dep_map, 1, _RET_IP_);
+	__rt_spin_unlock(&rwlock->lock);
+}
+EXPORT_SYMBOL(rt_write_unlock);
+
+void __lockfunc rt_read_unlock(rwlock_t *rwlock)
+{
+	/* Release the lock only when read_depth is down to 0 */
+	if (--rwlock->read_depth == 0) {
+		rwlock_release(&rwlock->dep_map, 1, _RET_IP_);
+		__rt_spin_unlock(&rwlock->lock);
+	}
+}
+EXPORT_SYMBOL(rt_read_unlock);
+
+unsigned long __lockfunc rt_write_lock_irqsave(rwlock_t *rwlock)
+{
+	rt_write_lock(rwlock);
+
+	return 0;
+}
+EXPORT_SYMBOL(rt_write_lock_irqsave);
+
+unsigned long __lockfunc rt_read_lock_irqsave(rwlock_t *rwlock)
+{
+	rt_read_lock(rwlock);
+
+	return 0;
+}
+EXPORT_SYMBOL(rt_read_lock_irqsave);
+
+void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/*
+	 * Make sure we are not reinitializing a held lock:
+	 */
+	debug_check_no_locks_freed((void *)rwlock, sizeof(*rwlock));
+	lockdep_init_map(&rwlock->dep_map, name, key, 0);
+#endif
+	rwlock->lock.save_state = 1;
+	rwlock->read_depth = 0;
+}
+EXPORT_SYMBOL(__rt_rwlock_init);
+
+/*
+ * rw_semaphores
+ */
+
+void  rt_up_write(struct rw_semaphore *rwsem)
+{
+	rwsem_release(&rwsem->dep_map, 1, _RET_IP_);
+	rt_mutex_unlock(&rwsem->lock);
+}
+EXPORT_SYMBOL(rt_up_write);
+
+void  rt_up_read(struct rw_semaphore *rwsem)
+{
+	if (--rwsem->read_depth == 0) {
+		rwsem_release(&rwsem->dep_map, 1, _RET_IP_);
+		rt_mutex_unlock(&rwsem->lock);
+	}
+}
+EXPORT_SYMBOL(rt_up_read);
+
+/*
+ * downgrade a write lock into a read lock
+ * - just wake up any readers at the front of the queue
+ */
+void  rt_downgrade_write(struct rw_semaphore *rwsem)
+{
+	BUG_ON(rt_mutex_owner(&rwsem->lock) != current);
+	rwsem->read_depth = 1;
+}
+EXPORT_SYMBOL(rt_downgrade_write);
+
+int  rt_down_write_trylock(struct rw_semaphore *rwsem)
+{
+	int ret = rt_mutex_trylock(&rwsem->lock);
+
+	if (ret)
+		rwsem_acquire(&rwsem->dep_map, 0, 1, _RET_IP_);
+	return ret;
+}
+EXPORT_SYMBOL(rt_down_write_trylock);
+
+void  rt_down_write(struct rw_semaphore *rwsem)
+{
+	rwsem_acquire(&rwsem->dep_map, 0, 0, _RET_IP_);
+	rt_mutex_lock(&rwsem->lock);
+}
+EXPORT_SYMBOL(rt_down_write);
+
+void  rt_down_write_nested(struct rw_semaphore *rwsem, int subclass)
+{
+	rwsem_acquire(&rwsem->dep_map, subclass, 0, _RET_IP_);
+	rt_mutex_lock(&rwsem->lock);
+}
+EXPORT_SYMBOL(rt_down_write_nested);
+
+int  rt_down_read_trylock(struct rw_semaphore *rwsem)
+{
+	struct rt_mutex *lock = &rwsem->lock;
+	int ret = 1;
+
+	/*
+	 * recursive read locks succeed when current owns the rwsem,
+	 * but not when read_depth == 0 which means that the rwsem is
+	 * write locked.
+	 */
+	if (rt_mutex_owner(lock) != current) {
+		ret = rt_mutex_trylock(&rwsem->lock);
+		if (ret)
+			rwsem_acquire(&rwsem->dep_map, 0, 1, _RET_IP_);
+	} else if (!rwsem->read_depth) {
+		ret = 0;
+	}
+
+	if (ret)
+		rwsem->read_depth++;
+	return ret;
+}
+EXPORT_SYMBOL(rt_down_read_trylock);
+
+static void __rt_down_read(struct rw_semaphore *rwsem, int subclass)
+{
+	struct rt_mutex *lock = &rwsem->lock;
+
+	if (rt_mutex_owner(lock) != current) {
+		rwsem_acquire(&rwsem->dep_map, subclass, 0, _RET_IP_);
+		rt_mutex_lock(&rwsem->lock);
+	}
+	rwsem->read_depth++;
+}
+
+void  rt_down_read(struct rw_semaphore *rwsem)
+{
+	__rt_down_read(rwsem, 0);
+}
+EXPORT_SYMBOL(rt_down_read);
+
+void  rt_down_read_nested(struct rw_semaphore *rwsem, int subclass)
+{
+	__rt_down_read(rwsem, subclass);
+}
+EXPORT_SYMBOL(rt_down_read_nested);
+
+void  __rt_rwsem_init(struct rw_semaphore *rwsem, char *name,
+			      struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/*
+	 * Make sure we are not reinitializing a held lock:
+	 */
+	debug_check_no_locks_freed((void *)rwsem, sizeof(*rwsem));
+	lockdep_init_map(&rwsem->dep_map, name, key, 0);
+#endif
+	rwsem->read_depth = 0;
+	rwsem->lock.save_state = 0;
+}
+EXPORT_SYMBOL(__rt_rwsem_init);
+
+/**
+ * atomic_dec_and_mutex_lock - return holding mutex if we dec to 0
+ * @cnt: the atomic which we are to dec
+ * @lock: the mutex to return holding if we dec to 0
+ *
+ * return true and hold lock if we dec to 0, return false otherwise
+ */
+int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock)
+{
+	/* dec if we can't possibly hit 0 */
+	if (atomic_add_unless(cnt, -1, 1))
+		return 0;
+	/* we might hit 0, so take the lock */
+	mutex_lock(lock);
+	if (!atomic_dec_and_test(cnt)) {
+		/* when we actually did the dec, we didn't hit 0 */
+		mutex_unlock(lock);
+		return 0;
+	}
+	/* we hit 0, and we hold the lock */
+	return 1;
+}
+EXPORT_SYMBOL(atomic_dec_and_mutex_lock);
diff --git a/kernel/rtmutex-debug.c b/kernel/rtmutex-debug.c
index 8eafd1b..5726637 100644
--- a/kernel/rtmutex-debug.c
+++ b/kernel/rtmutex-debug.c
@@ -65,12 +65,13 @@
  * the deadlock. We print when we return. act_waiter can be NULL in
  * case of a remove waiter operation.
  */
-void debug_rt_mutex_deadlock(int detect, struct rt_mutex_waiter *act_waiter,
+void debug_rt_mutex_deadlock(enum rtmutex_chainwalk chwalk,
+			     struct rt_mutex_waiter *act_waiter,
 			     struct rt_mutex *lock)
 {
 	struct task_struct *task;
 
-	if (!debug_locks || detect || !act_waiter)
+	if (!debug_locks || chwalk == RT_MUTEX_FULL_CHAINWALK || !act_waiter)
 		return;
 
 	task = rt_mutex_owner(act_waiter->lock);
diff --git a/kernel/rtmutex-debug.h b/kernel/rtmutex-debug.h
index ab29b6a..d0519c3 100644
--- a/kernel/rtmutex-debug.h
+++ b/kernel/rtmutex-debug.h
@@ -20,14 +20,15 @@
 extern void debug_rt_mutex_proxy_lock(struct rt_mutex *lock,
 				      struct task_struct *powner);
 extern void debug_rt_mutex_proxy_unlock(struct rt_mutex *lock);
-extern void debug_rt_mutex_deadlock(int detect, struct rt_mutex_waiter *waiter,
+extern void debug_rt_mutex_deadlock(enum rtmutex_chainwalk chwalk,
+				    struct rt_mutex_waiter *waiter,
 				    struct rt_mutex *lock);
 extern void debug_rt_mutex_print_deadlock(struct rt_mutex_waiter *waiter);
 # define debug_rt_mutex_reset_waiter(w)			\
 	do { (w)->deadlock_lock = NULL; } while (0)
 
-static inline int debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *waiter,
-						 int detect)
+static inline bool debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *waiter,
+						  enum rtmutex_chainwalk walk)
 {
 	return (waiter != NULL);
 }
diff --git a/kernel/rtmutex-tester.c b/kernel/rtmutex-tester.c
index 3d9f31c..9eb84bb 100644
--- a/kernel/rtmutex-tester.c
+++ b/kernel/rtmutex-tester.c
@@ -14,7 +14,7 @@
 #include <linux/timer.h>
 #include <linux/freezer.h>
 
-#include "rtmutex.h"
+#include "rtmutex_common.h"
 
 #define MAX_RT_TEST_THREADS	8
 #define MAX_RT_TEST_MUTEXES	8
@@ -105,7 +105,7 @@
 
 		td->mutexes[id] = 1;
 		td->event = atomic_add_return(1, &rttest_event);
-		ret = rt_mutex_lock_interruptible(&mutexes[id], 0);
+		ret = rt_mutex_lock_interruptible(&mutexes[id]);
 		td->event = atomic_add_return(1, &rttest_event);
 		td->mutexes[id] = ret ? 0 : 4;
 		return ret ? -EINTR : 0;
diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c
index 1928f3d..52cab27 100644
--- a/kernel/rtmutex.c
+++ b/kernel/rtmutex.c
@@ -8,6 +8,12 @@
  *  Copyright (C) 2005 Kihon Technologies Inc., Steven Rostedt
  *  Copyright (C) 2006 Esben Nielsen
  *
+ * Adaptive Spinlocks:
+ *  Copyright (C) 2008 Novell, Inc., Gregory Haskins, Sven Dietrich,
+ *                                   and Peter Morreale,
+ * Adaptive Spinlocks simplification:
+ *  Copyright (C) 2008 Red Hat, Inc., Steven Rostedt <srostedt@redhat.com>
+ *
  *  See Documentation/rt-mutex-design.txt for details.
  */
 #include <linux/spinlock.h>
@@ -67,6 +73,12 @@
 		clear_rt_mutex_waiters(lock);
 }
 
+static int rt_mutex_real_waiter(struct rt_mutex_waiter *waiter)
+{
+	return waiter && waiter != PI_WAKEUP_INPROGRESS &&
+		waiter != PI_REQUEUE_INPROGRESS;
+}
+
 /*
  * We can speed up the acquire/release, if the architecture
  * supports cmpxchg and if there's no debugging state to be set up
@@ -142,6 +154,37 @@
 }
 #endif
 
+static inline void
+rt_mutex_enqueue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
+{
+	plist_add(&waiter->list_entry, &lock->wait_list);
+}
+
+static inline void
+rt_mutex_dequeue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
+{
+	plist_del(&waiter->list_entry, &lock->wait_list);
+}
+
+static inline void
+rt_mutex_enqueue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
+{
+	waiter->pi_list_entry.prio = waiter->list_entry.prio;
+	plist_add(&waiter->pi_list_entry, &task->pi_waiters);
+}
+
+static inline void
+rt_mutex_dequeue_pi(struct task_struct *task, struct rt_mutex_waiter *waiter)
+{
+	plist_del(&waiter->pi_list_entry, &task->pi_waiters);
+}
+
+static inline void init_lists(struct rt_mutex *lock)
+{
+	if (unlikely(!lock->wait_list.node_list.prev))
+		plist_head_init(&lock->wait_list);
+}
+
 /*
  * Calculate task priority from the waiter list priority
  *
@@ -158,6 +201,18 @@
 }
 
 /*
+ * Called by sched_setscheduler() to check whether the priority change
+ * is overruled by a possible priority boosting.
+ */
+int rt_mutex_check_prio(struct task_struct *task, int newprio)
+{
+	if (!task_has_pi_waiters(task))
+		return 0;
+
+	return task_top_pi_waiter(task)->pi_list_entry.prio <= newprio;
+}
+
+/*
  * Adjust the priority of a task, after its pi_waiters got modified.
  *
  * This can be both boosting and unboosting. task->pi_lock must be held.
@@ -188,6 +243,40 @@
 	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 }
 
+static void rt_mutex_wake_waiter(struct rt_mutex_waiter *waiter)
+{
+	if (waiter->savestate)
+		wake_up_lock_sleeper(waiter->task);
+	else
+		wake_up_process(waiter->task);
+}
+
+/*
+ * Deadlock detection is conditional:
+ *
+ * If CONFIG_DEBUG_RT_MUTEXES=n, deadlock detection is only conducted
+ * if the detect argument is == RT_MUTEX_FULL_CHAINWALK.
+ *
+ * If CONFIG_DEBUG_RT_MUTEXES=y, deadlock detection is always
+ * conducted independent of the detect argument.
+ *
+ * If the waiter argument is NULL this indicates the deboost path and
+ * deadlock detection is disabled independent of the detect argument
+ * and the config settings.
+ */
+static bool rt_mutex_cond_detect_deadlock(struct rt_mutex_waiter *waiter,
+					  enum rtmutex_chainwalk chwalk)
+{
+	/*
+	 * This is just a wrapper function for the following call,
+	 * because debug_rt_mutex_detect_deadlock() smells like a magic
+	 * debug feature and I wanted to keep the cond function in the
+	 * main source file along with the comments instead of having
+	 * two of the same in the headers.
+	 */
+	return debug_rt_mutex_detect_deadlock(waiter, chwalk);
+}
+
 /*
  * Max number of times we'll walk the boosting chain:
  */
@@ -218,21 +307,65 @@
  * @top_task:	the current top waiter
  *
  * Returns 0 or -EDEADLK.
+ *
+ * Chain walk basics and protection scope
+ *
+ * [R] refcount on task
+ * [P] task->pi_lock held
+ * [L] rtmutex->wait_lock held
+ *
+ * Step	Description				Protected by
+ *	function arguments:
+ *	@task					[R]
+ *	@orig_lock if != NULL			@top_task is blocked on it
+ *	@next_lock				Unprotected. Cannot be
+ *						dereferenced. Only used for
+ *						comparison.
+ *	@orig_waiter if != NULL			@top_task is blocked on it
+ *	@top_task				current, or in case of proxy
+ *						locking protected by calling
+ *						code
+ *	again:
+ *	  loop_sanity_check();
+ *	retry:
+ * [1]	  lock(task->pi_lock);			[R] acquire [P]
+ * [2]	  waiter = task->pi_blocked_on;		[P]
+ * [3]	  check_exit_conditions_1();		[P]
+ * [4]	  lock = waiter->lock;			[P]
+ * [5]	  if (!try_lock(lock->wait_lock)) {	[P] try to acquire [L]
+ *	    unlock(task->pi_lock);		release [P]
+ *	    goto retry;
+ *	  }
+ * [6]	  check_exit_conditions_2();		[P] + [L]
+ * [7]	  requeue_lock_waiter(lock, waiter);	[P] + [L]
+ * [8]	  unlock(task->pi_lock);		release [P]
+ *	  put_task_struct(task);		release [R]
+ * [9]	  check_exit_conditions_3();		[L]
+ * [10]	  task = owner(lock);			[L]
+ *	  get_task_struct(task);		[L] acquire [R]
+ *	  lock(task->pi_lock);			[L] acquire [P]
+ * [11]	  requeue_pi_waiter(tsk, waiters(lock));[P] + [L]
+ * [12]	  check_exit_conditions_4();		[P] + [L]
+ * [13]	  unlock(task->pi_lock);		release [P]
+ *	  unlock(lock->wait_lock);		release [L]
+ *	  goto again;
  */
 static int rt_mutex_adjust_prio_chain(struct task_struct *task,
-				      int deadlock_detect,
+				      enum rtmutex_chainwalk chwalk,
 				      struct rt_mutex *orig_lock,
 				      struct rt_mutex *next_lock,
 				      struct rt_mutex_waiter *orig_waiter,
 				      struct task_struct *top_task)
 {
-	struct rt_mutex *lock;
 	struct rt_mutex_waiter *waiter, *top_waiter = orig_waiter;
-	int detect_deadlock, ret = 0, depth = 0;
+	struct rt_mutex_waiter *prerequeue_top_waiter;
+	int ret = 0, depth = 0;
+	struct rt_mutex *lock;
+	bool detect_deadlock;
 	unsigned long flags;
+	bool requeue = true;
 
-	detect_deadlock = debug_rt_mutex_detect_deadlock(orig_waiter,
-							 deadlock_detect);
+	detect_deadlock = rt_mutex_cond_detect_deadlock(orig_waiter, chwalk);
 
 	/*
 	 * The (de)boosting is a step by step approach with a lot of
@@ -241,6 +374,9 @@
 	 * carefully whether things change under us.
 	 */
  again:
+	/*
+	 * We limit the lock chain length for each invocation.
+	 */
 	if (++depth > max_lock_depth) {
 		static int prev_max;
 
@@ -258,19 +394,34 @@
 
 		return -EDEADLK;
 	}
+
+	/*
+	 * We are fully preemptible here and only hold the refcount on
+	 * @task. So everything can have changed under us since the
+	 * caller or our own code below (goto retry/again) dropped all
+	 * locks.
+	 */
  retry:
 	/*
-	 * Task can not go away as we did a get_task() before !
+	 * [1] Task cannot go away as we did a get_task() before !
 	 */
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
 
+	/*
+	 * [2] Get the waiter on which @task is blocked on.
+	 */
 	waiter = task->pi_blocked_on;
+
+	/*
+	 * [3] check_exit_conditions_1() protected by task->pi_lock.
+	 */
+
 	/*
 	 * Check whether the end of the boosting chain has been
 	 * reached or the state of the chain has changed while we
 	 * dropped the locks.
 	 */
-	if (!waiter)
+	if (!rt_mutex_real_waiter(waiter))
 		goto out_unlock_pi;
 
 	/*
@@ -302,20 +453,41 @@
 			goto out_unlock_pi;
 		/*
 		 * If deadlock detection is off, we stop here if we
-		 * are not the top pi waiter of the task.
+		 * are not the top pi waiter of the task. If deadlock
+		 * detection is enabled we continue, but stop the
+		 * requeueing in the chain walk.
 		 */
-		if (!detect_deadlock && top_waiter != task_top_pi_waiter(task))
-			goto out_unlock_pi;
+		if (top_waiter != task_top_pi_waiter(task)) {
+			if (!detect_deadlock)
+				goto out_unlock_pi;
+			else
+				requeue = false;
+		}
 	}
 
 	/*
-	 * When deadlock detection is off then we check, if further
-	 * priority adjustment is necessary.
+	 * If the waiter priority is the same as the task priority
+	 * then there is no further priority adjustment necessary.  If
+	 * deadlock detection is off, we stop the chain walk. If its
+	 * enabled we continue, but stop the requeueing in the chain
+	 * walk.
 	 */
-	if (!detect_deadlock && waiter->list_entry.prio == task->prio)
-		goto out_unlock_pi;
+	if (waiter->list_entry.prio == task->prio) {
+		if (!detect_deadlock)
+			goto out_unlock_pi;
+		else
+			requeue = false;
+	}
 
+	/*
+	 * [4] Get the next lock
+	 */
 	lock = waiter->lock;
+	/*
+	 * [5] We need to trylock here as we are holding task->pi_lock,
+	 * which is the reverse lock order versus the other rtmutex
+	 * operations.
+	 */
 	if (!raw_spin_trylock(&lock->wait_lock)) {
 		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 		cpu_relax();
@@ -323,81 +495,183 @@
 	}
 
 	/*
+	 * [6] check_exit_conditions_2() protected by task->pi_lock and
+	 * lock->wait_lock.
+	 *
 	 * Deadlock detection. If the lock is the same as the original
 	 * lock which caused us to walk the lock chain or if the
 	 * current lock is owned by the task which initiated the chain
 	 * walk, we detected a deadlock.
 	 */
 	if (lock == orig_lock || rt_mutex_owner(lock) == top_task) {
-		debug_rt_mutex_deadlock(deadlock_detect, orig_waiter, lock);
+		debug_rt_mutex_deadlock(chwalk, orig_waiter, lock);
 		raw_spin_unlock(&lock->wait_lock);
 		ret = -EDEADLK;
 		goto out_unlock_pi;
 	}
 
-	top_waiter = rt_mutex_top_waiter(lock);
-
-	/* Requeue the waiter */
-	plist_del(&waiter->list_entry, &lock->wait_list);
-	waiter->list_entry.prio = task->prio;
-	plist_add(&waiter->list_entry, &lock->wait_list);
-
-	/* Release the task */
-	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
-	if (!rt_mutex_owner(lock)) {
+	/*
+	 * If we just follow the lock chain for deadlock detection, no
+	 * need to do all the requeue operations. To avoid a truckload
+	 * of conditionals around the various places below, just do the
+	 * minimum chain walk checks.
+	 */
+	if (!requeue) {
 		/*
-		 * If the requeue above changed the top waiter, then we need
-		 * to wake the new top waiter up to try to get the lock.
+		 * No requeue[7] here. Just release @task [8]
 		 */
+		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+		put_task_struct(task);
 
-		if (top_waiter != rt_mutex_top_waiter(lock))
-			wake_up_process(rt_mutex_top_waiter(lock)->task);
+		/*
+		 * [9] check_exit_conditions_3 protected by lock->wait_lock.
+		 * If there is no owner of the lock, end of chain.
+		 */
+		if (!rt_mutex_owner(lock)) {
+			raw_spin_unlock(&lock->wait_lock);
+			return 0;
+		}
+
+		/* [10] Grab the next task, i.e. owner of @lock */
+		task = rt_mutex_owner(lock);
+		get_task_struct(task);
+		raw_spin_lock_irqsave(&task->pi_lock, flags);
+
+		/*
+		 * No requeue [11] here. We just do deadlock detection.
+		 *
+		 * [12] Store whether owner is blocked
+		 * itself. Decision is made after dropping the locks
+		 */
+		next_lock = task_blocked_on_lock(task);
+		/*
+		 * Get the top waiter for the next iteration
+		 */
+		top_waiter = rt_mutex_top_waiter(lock);
+
+		/* [13] Drop locks */
+		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 		raw_spin_unlock(&lock->wait_lock);
-		goto out_put_task;
+
+		/* If owner is not blocked, end of chain. */
+		if (!next_lock)
+			goto out_put_task;
+		goto again;
 	}
+
+	/*
+	 * Store the current top waiter before doing the requeue
+	 * operation on @lock. We need it for the boost/deboost
+	 * decision below.
+	 */
+	prerequeue_top_waiter = rt_mutex_top_waiter(lock);
+
+	/* [7] Requeue the waiter in the lock waiter list. */
+	rt_mutex_dequeue(lock, waiter);
+	waiter->list_entry.prio = task->prio;
+	rt_mutex_enqueue(lock, waiter);
+
+	/* [8] Release the task */
+	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 	put_task_struct(task);
 
-	/* Grab the next task */
+	/*
+	 * [9] check_exit_conditions_3 protected by lock->wait_lock.
+	 *
+	 * We must abort the chain walk if there is no lock owner even
+	 * in the dead lock detection case, as we have nothing to
+	 * follow here. This is the end of the chain we are walking.
+	 */
+	if (!rt_mutex_owner(lock)) {
+		struct rt_mutex_waiter *lock_top_waiter;
+
+		/*
+		 * If the requeue [7] above changed the top waiter,
+		 * then we need to wake the new top waiter up to try
+		 * to get the lock.
+		 */
+		lock_top_waiter = rt_mutex_top_waiter(lock);
+		if (prerequeue_top_waiter != lock_top_waiter)
+			rt_mutex_wake_waiter(lock_top_waiter);
+		raw_spin_unlock(&lock->wait_lock);
+		return 0;
+	}
+
+	/* [10] Grab the next task, i.e. the owner of @lock */
 	task = rt_mutex_owner(lock);
 	get_task_struct(task);
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
 
+	/* [11] requeue the pi waiters if necessary */
 	if (waiter == rt_mutex_top_waiter(lock)) {
-		/* Boost the owner */
-		plist_del(&top_waiter->pi_list_entry, &task->pi_waiters);
-		waiter->pi_list_entry.prio = waiter->list_entry.prio;
-		plist_add(&waiter->pi_list_entry, &task->pi_waiters);
+		/*
+		 * The waiter became the new top (highest priority)
+		 * waiter on the lock. Replace the previous top waiter
+		 * in the owner tasks pi waiters list with this waiter
+		 * and adjust the priority of the owner.
+		 */
+		rt_mutex_dequeue_pi(task, prerequeue_top_waiter);
+		rt_mutex_enqueue_pi(task, waiter);
 		__rt_mutex_adjust_prio(task);
 
-	} else if (top_waiter == waiter) {
-		/* Deboost the owner */
-		plist_del(&waiter->pi_list_entry, &task->pi_waiters);
+	} else if (prerequeue_top_waiter == waiter) {
+		/*
+		 * The waiter was the top waiter on the lock, but is
+		 * no longer the top prority waiter. Replace waiter in
+		 * the owner tasks pi waiters list with the new top
+		 * (highest priority) waiter and adjust the priority
+		 * of the owner.
+		 * The new top waiter is stored in @waiter so that
+		 * @waiter == @top_waiter evaluates to true below and
+		 * we continue to deboost the rest of the chain.
+		 */
+		rt_mutex_dequeue_pi(task, waiter);
 		waiter = rt_mutex_top_waiter(lock);
-		waiter->pi_list_entry.prio = waiter->list_entry.prio;
-		plist_add(&waiter->pi_list_entry, &task->pi_waiters);
+		rt_mutex_enqueue_pi(task, waiter);
 		__rt_mutex_adjust_prio(task);
+	} else {
+		/*
+		 * Nothing changed. No need to do any priority
+		 * adjustment.
+		 */
 	}
 
 	/*
+	 * [12] check_exit_conditions_4() protected by task->pi_lock
+	 * and lock->wait_lock. The actual decisions are made after we
+	 * dropped the locks.
+	 *
 	 * Check whether the task which owns the current lock is pi
 	 * blocked itself. If yes we store a pointer to the lock for
 	 * the lock chain change detection above. After we dropped
 	 * task->pi_lock next_lock cannot be dereferenced anymore.
 	 */
 	next_lock = task_blocked_on_lock(task);
-
-	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
-
+	/*
+	 * Store the top waiter of @lock for the end of chain walk
+	 * decision below.
+	 */
 	top_waiter = rt_mutex_top_waiter(lock);
+
+	/* [13] Drop the locks */
+	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 	raw_spin_unlock(&lock->wait_lock);
 
 	/*
+	 * Make the actual exit decisions [12], based on the stored
+	 * values.
+	 *
 	 * We reached the end of the lock chain. Stop right here. No
 	 * point to go back just to figure that out.
 	 */
 	if (!next_lock)
 		goto out_put_task;
 
+	/*
+	 * If the current waiter is not the top waiter on the lock,
+	 * then we can stop the chain walk here if we are not in full
+	 * deadlock detection mode.
+	 */
 	if (!detect_deadlock && waiter != top_waiter)
 		goto out_put_task;
 
@@ -411,82 +685,146 @@
 	return ret;
 }
 
+
+#define STEAL_NORMAL  0
+#define STEAL_LATERAL 1
+
+/*
+ * Note that RT tasks are excluded from lateral-steals to prevent the
+ * introduction of an unbounded latency
+ */
+static inline int lock_is_stealable(struct task_struct *task,
+				    struct task_struct *pendowner, int mode)
+{
+    if (mode == STEAL_NORMAL || rt_task(task)) {
+	    if (task->prio >= pendowner->prio)
+		    return 0;
+    } else if (task->prio > pendowner->prio)
+	    return 0;
+    return 1;
+}
+
 /*
  * Try to take an rt-mutex
  *
  * Must be called with lock->wait_lock held.
  *
- * @lock:   the lock to be acquired.
- * @task:   the task which wants to acquire the lock
- * @waiter: the waiter that is queued to the lock's wait list. (could be NULL)
+ * @lock:   The lock to be acquired.
+ * @task:   The task which wants to acquire the lock
+ * @waiter: The waiter that is queued to the lock's wait list if the
+ *	    callsite called task_blocked_on_lock(), otherwise NULL
  */
-static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
-		struct rt_mutex_waiter *waiter)
+static int
+__try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
+		       struct rt_mutex_waiter *waiter, int mode)
 {
+	unsigned long flags;
+
 	/*
-	 * We have to be careful here if the atomic speedups are
-	 * enabled, such that, when
-	 *  - no other waiter is on the lock
-	 *  - the lock has been released since we did the cmpxchg
-	 * the lock can be released or taken while we are doing the
-	 * checks and marking the lock with RT_MUTEX_HAS_WAITERS.
+	 * Before testing whether we can acquire @lock, we set the
+	 * RT_MUTEX_HAS_WAITERS bit in @lock->owner. This forces all
+	 * other tasks which try to modify @lock into the slow path
+	 * and they serialize on @lock->wait_lock.
 	 *
-	 * The atomic acquire/release aware variant of
-	 * mark_rt_mutex_waiters uses a cmpxchg loop. After setting
-	 * the WAITERS bit, the atomic release / acquire can not
-	 * happen anymore and lock->wait_lock protects us from the
-	 * non-atomic case.
+	 * The RT_MUTEX_HAS_WAITERS bit can have a transitional state
+	 * as explained at the top of this file if and only if:
 	 *
-	 * Note, that this might set lock->owner =
-	 * RT_MUTEX_HAS_WAITERS in the case the lock is not contended
-	 * any more. This is fixed up when we take the ownership.
-	 * This is the transitional state explained at the top of this file.
+	 * - There is a lock owner. The caller must fixup the
+	 *   transient state if it does a trylock or leaves the lock
+	 *   function due to a signal or timeout.
+	 *
+	 * - @task acquires the lock and there are no other
+	 *   waiters. This is undone in rt_mutex_set_owner(@task) at
+	 *   the end of this function.
 	 */
 	mark_rt_mutex_waiters(lock);
 
+	/*
+	 * If @lock has an owner, give up.
+	 */
 	if (rt_mutex_owner(lock))
 		return 0;
 
 	/*
-	 * It will get the lock because of one of these conditions:
-	 * 1) there is no waiter
-	 * 2) higher priority than waiters
-	 * 3) it is top waiter
+	 * If @waiter != NULL, @task has already enqueued the waiter
+	 * into @lock waiter list. If @waiter == NULL then this is a
+	 * trylock attempt.
 	 */
-	if (rt_mutex_has_waiters(lock)) {
-		if (task->prio >= rt_mutex_top_waiter(lock)->list_entry.prio) {
-			if (!waiter || waiter != rt_mutex_top_waiter(lock))
-				return 0;
-		}
-	}
-
-	if (waiter || rt_mutex_has_waiters(lock)) {
-		unsigned long flags;
-		struct rt_mutex_waiter *top;
-
-		raw_spin_lock_irqsave(&task->pi_lock, flags);
-
-		/* remove the queued waiter. */
-		if (waiter) {
-			plist_del(&waiter->list_entry, &lock->wait_list);
-			task->pi_blocked_on = NULL;
-		}
+	if (waiter) {
+		/*
+		 * If waiter is not the highest priority waiter of
+		 * @lock, give up.
+		 */
+		if (waiter != rt_mutex_top_waiter(lock))
+			return 0;
 
 		/*
-		 * We have to enqueue the top waiter(if it exists) into
-		 * task->pi_waiters list.
+		 * We can acquire the lock. Remove the waiter from the
+		 * lock waiters list.
+		 */
+		rt_mutex_dequeue(lock, waiter);
+
+	} else {
+		/*
+		 * If the lock has waiters already we check whether @task is
+		 * eligible to take over the lock.
+		 *
+		 * If there are no other waiters, @task can acquire
+		 * the lock.  @task->pi_blocked_on is NULL, so it does
+		 * not need to be dequeued.
 		 */
 		if (rt_mutex_has_waiters(lock)) {
-			top = rt_mutex_top_waiter(lock);
-			top->pi_list_entry.prio = top->list_entry.prio;
-			plist_add(&top->pi_list_entry, &task->pi_waiters);
+			struct task_struct *pown = rt_mutex_top_waiter(lock)->task;
+
+			/*
+			 * If @task->prio is greater than or equal to
+			 * the top waiter priority (kernel view),
+			 * @task lost.
+			 */
+			if (task != pown && !lock_is_stealable(task, pown, mode))
+				return 0;
+
+			/*
+			 * The current top waiter stays enqueued. We
+			 * don't have to change anything in the lock
+			 * waiters order.
+			 */
+		} else {
+			/*
+			 * No waiters. Take the lock without the
+			 * pi_lock dance.@task->pi_blocked_on is NULL
+			 * and we have no waiters to enqueue in @task
+			 * pi waiters list.
+			 */
+			goto takeit;
 		}
-		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 	}
 
+	/*
+	 * Clear @task->pi_blocked_on. Requires protection by
+	 * @task->pi_lock. Redundant operation for the @waiter == NULL
+	 * case, but conditionals are more expensive than a redundant
+	 * store.
+	 */
+	raw_spin_lock_irqsave(&task->pi_lock, flags);
+	task->pi_blocked_on = NULL;
+	/*
+	 * Finish the lock acquisition. @task is the new owner. If
+	 * other waiters exist we have to insert the highest priority
+	 * waiter into @task->pi_waiters list.
+	 */
+	if (rt_mutex_has_waiters(lock))
+		rt_mutex_enqueue_pi(task, rt_mutex_top_waiter(lock));
+	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+
+takeit:
 	/* We got the lock. */
 	debug_rt_mutex_lock(lock);
 
+	/*
+	 * This either preserves the RT_MUTEX_HAS_WAITERS bit if there
+	 * are still waiters or clears it.
+	 */
 	rt_mutex_set_owner(lock, task);
 
 	rt_mutex_deadlock_account_lock(lock, task);
@@ -494,6 +832,13 @@
 	return 1;
 }
 
+static inline int
+try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
+		     struct rt_mutex_waiter *waiter)
+{
+	return __try_to_take_rt_mutex(lock, task, waiter, STEAL_NORMAL);
+}
+
 /*
  * Task blocks on lock.
  *
@@ -504,7 +849,7 @@
 static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 				   struct rt_mutex_waiter *waiter,
 				   struct task_struct *task,
-				   int detect_deadlock)
+				   enum rtmutex_chainwalk chwalk)
 {
 	struct task_struct *owner = rt_mutex_owner(lock);
 	struct rt_mutex_waiter *top_waiter = waiter;
@@ -525,6 +870,23 @@
 		return -EDEADLK;
 
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
+
+	/*
+	 * In the case of futex requeue PI, this will be a proxy
+	 * lock. The task will wake unaware that it is enqueueed on
+	 * this lock. Avoid blocking on two locks and corrupting
+	 * pi_blocked_on via the PI_WAKEUP_INPROGRESS
+	 * flag. futex_wait_requeue_pi() sets this when it wakes up
+	 * before requeue (due to a signal or timeout). Do not enqueue
+	 * the task if PI_WAKEUP_INPROGRESS is set.
+	 */
+	if (task != current && task->pi_blocked_on == PI_WAKEUP_INPROGRESS) {
+		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+		return -EAGAIN;
+	}
+
+	BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on));
+
 	__rt_mutex_adjust_prio(task);
 	waiter->task = task;
 	waiter->lock = lock;
@@ -534,7 +896,7 @@
 	/* Get the top priority waiter on the lock */
 	if (rt_mutex_has_waiters(lock))
 		top_waiter = rt_mutex_top_waiter(lock);
-	plist_add(&waiter->list_entry, &lock->wait_list);
+	rt_mutex_enqueue(lock, waiter);
 
 	task->pi_blocked_on = waiter;
 
@@ -545,13 +907,13 @@
 
 	raw_spin_lock_irqsave(&owner->pi_lock, flags);
 	if (waiter == rt_mutex_top_waiter(lock)) {
-		plist_del(&top_waiter->pi_list_entry, &owner->pi_waiters);
-		plist_add(&waiter->pi_list_entry, &owner->pi_waiters);
+		rt_mutex_dequeue_pi(owner, top_waiter);
+		rt_mutex_enqueue_pi(owner, waiter);
 
 		__rt_mutex_adjust_prio(owner);
-		if (owner->pi_blocked_on)
+		if (rt_mutex_real_waiter(owner->pi_blocked_on))
 			chain_walk = 1;
-	} else if (debug_rt_mutex_detect_deadlock(waiter, detect_deadlock)) {
+	} else if (rt_mutex_cond_detect_deadlock(waiter, chwalk)) {
 		chain_walk = 1;
 	}
 
@@ -576,7 +938,7 @@
 
 	raw_spin_unlock(&lock->wait_lock);
 
-	res = rt_mutex_adjust_prio_chain(owner, detect_deadlock, lock,
+	res = rt_mutex_adjust_prio_chain(owner, chwalk, lock,
 					 next_lock, waiter, task);
 
 	raw_spin_lock(&lock->wait_lock);
@@ -607,7 +969,7 @@
 	 * boosted mode and go back to normal after releasing
 	 * lock->wait_lock.
 	 */
-	plist_del(&waiter->pi_list_entry, &current->pi_waiters);
+	rt_mutex_dequeue_pi(current, waiter);
 
 	/*
 	 * As we are waking up the top waiter, and the waiter stays
@@ -626,7 +988,7 @@
 	 * long as we hold lock->wait_lock. The waiter task needs to
 	 * acquire it in order to dequeue the waiter.
 	 */
-	wake_up_process(waiter->task);
+	rt_mutex_wake_waiter(waiter);
 }
 
 /*
@@ -638,41 +1000,44 @@
 static void remove_waiter(struct rt_mutex *lock,
 			  struct rt_mutex_waiter *waiter)
 {
-	int first = (waiter == rt_mutex_top_waiter(lock));
+	bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock));
 	struct task_struct *owner = rt_mutex_owner(lock);
 	struct rt_mutex *next_lock = NULL;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&current->pi_lock, flags);
-	plist_del(&waiter->list_entry, &lock->wait_list);
+	rt_mutex_dequeue(lock, waiter);
 	current->pi_blocked_on = NULL;
 	raw_spin_unlock_irqrestore(&current->pi_lock, flags);
 
-	if (!owner)
+	/*
+	 * Only update priority if the waiter was the highest priority
+	 * waiter of the lock and there is an owner to update.
+	 */
+	if (!owner || !is_top_waiter)
 		return;
 
-	if (first) {
+	raw_spin_lock_irqsave(&owner->pi_lock, flags);
 
-		raw_spin_lock_irqsave(&owner->pi_lock, flags);
+	rt_mutex_dequeue_pi(owner, waiter);
 
-		plist_del(&waiter->pi_list_entry, &owner->pi_waiters);
+	if (rt_mutex_has_waiters(lock))
+		rt_mutex_enqueue_pi(owner, rt_mutex_top_waiter(lock));
 
-		if (rt_mutex_has_waiters(lock)) {
-			struct rt_mutex_waiter *next;
+	__rt_mutex_adjust_prio(owner);
 
-			next = rt_mutex_top_waiter(lock);
-			plist_add(&next->pi_list_entry, &owner->pi_waiters);
-		}
-		__rt_mutex_adjust_prio(owner);
-
-		/* Store the lock on which owner is blocked or NULL */
+	/* Store the lock on which owner is blocked or NULL */
+	if (rt_mutex_real_waiter(owner->pi_blocked_on))
 		next_lock = task_blocked_on_lock(owner);
 
-		raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
-	}
+	raw_spin_unlock_irqrestore(&owner->pi_lock, flags);
 
 	WARN_ON(!plist_node_empty(&waiter->pi_list_entry));
 
+	/*
+	 * Don't walk the chain, if the owner task is not blocked
+	 * itself.
+	 */
 	if (!next_lock)
 		return;
 
@@ -681,7 +1046,8 @@
 
 	raw_spin_unlock(&lock->wait_lock);
 
-	rt_mutex_adjust_prio_chain(owner, 0, lock, next_lock, NULL, current);
+	rt_mutex_adjust_prio_chain(owner, RT_MUTEX_MIN_CHAINWALK, lock,
+				   next_lock, NULL, current);
 
 	raw_spin_lock(&lock->wait_lock);
 }
@@ -700,24 +1066,340 @@
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
 
 	waiter = task->pi_blocked_on;
-	if (!waiter || waiter->list_entry.prio == task->prio) {
+	if (!rt_mutex_real_waiter(waiter) ||
+	    waiter->list_entry.prio == task->prio) {
 		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 		return;
 	}
-	next_lock = waiter->lock;
-	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 
 	/* gets dropped in rt_mutex_adjust_prio_chain()! */
 	get_task_struct(task);
-
-	rt_mutex_adjust_prio_chain(task, 0, NULL, next_lock, NULL, task);
+	next_lock = waiter->lock;
+	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+	rt_mutex_adjust_prio_chain(task, RT_MUTEX_MIN_CHAINWALK, NULL,
+				   next_lock, NULL, task);
 }
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+/*
+ * preemptible spin_lock functions:
+ */
+static inline void rt_spin_lock_fastlock(struct rt_mutex *lock,
+					 void  (*slowfn)(struct rt_mutex *lock))
+{
+	might_sleep();
+
+	if (likely(rt_mutex_cmpxchg(lock, NULL, current)))
+		rt_mutex_deadlock_account_lock(lock, current);
+	else
+		slowfn(lock);
+}
+
+static inline void rt_spin_lock_fastunlock(struct rt_mutex *lock,
+					   void  (*slowfn)(struct rt_mutex *lock))
+{
+	if (likely(rt_mutex_cmpxchg(lock, current, NULL)))
+		rt_mutex_deadlock_account_unlock(current);
+	else
+		slowfn(lock);
+}
+
+#ifdef CONFIG_SMP
+/*
+ * Note that owner is a speculative pointer and dereferencing relies
+ * on rcu_read_lock() and the check against the lock owner.
+ */
+static int adaptive_wait(struct rt_mutex *lock,
+			 struct task_struct *owner)
+{
+	int res = 0;
+
+	rcu_read_lock();
+	for (;;) {
+		if (owner != rt_mutex_owner(lock))
+			break;
+		/*
+		 * Ensure that owner->on_cpu is dereferenced _after_
+		 * checking the above to be valid.
+		 */
+		barrier();
+		if (!owner->on_cpu) {
+			res = 1;
+			break;
+		}
+		cpu_relax();
+	}
+	rcu_read_unlock();
+	return res;
+}
+#else
+static int adaptive_wait(struct rt_mutex *lock,
+			 struct task_struct *orig_owner)
+{
+	return 1;
+}
+#endif
+
+# define pi_lock(lock)			raw_spin_lock_irq(lock)
+# define pi_unlock(lock)		raw_spin_unlock_irq(lock)
+
+/*
+ * Slow path lock function spin_lock style: this variant is very
+ * careful not to miss any non-lock wakeups.
+ *
+ * We store the current state under p->pi_lock in p->saved_state and
+ * the try_to_wake_up() code handles this accordingly.
+ */
+static void  noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock)
+{
+	struct task_struct *lock_owner, *self = current;
+	struct rt_mutex_waiter waiter, *top_waiter;
+	int ret;
+
+	rt_mutex_init_waiter(&waiter, true);
+
+	raw_spin_lock(&lock->wait_lock);
+	init_lists(lock);
+
+	if (__try_to_take_rt_mutex(lock, self, NULL, STEAL_LATERAL)) {
+		raw_spin_unlock(&lock->wait_lock);
+		return;
+	}
+
+	BUG_ON(rt_mutex_owner(lock) == self);
+
+	/*
+	 * We save whatever state the task is in and we'll restore it
+	 * after acquiring the lock taking real wakeups into account
+	 * as well. We are serialized via pi_lock against wakeups. See
+	 * try_to_wake_up().
+	 */
+	pi_lock(&self->pi_lock);
+	self->saved_state = self->state;
+	__set_current_state(TASK_UNINTERRUPTIBLE);
+	pi_unlock(&self->pi_lock);
+
+	ret = task_blocks_on_rt_mutex(lock, &waiter, self, 0);
+	BUG_ON(ret);
+
+	for (;;) {
+		/* Try to acquire the lock again. */
+		if (__try_to_take_rt_mutex(lock, self, &waiter, STEAL_LATERAL))
+			break;
+
+		top_waiter = rt_mutex_top_waiter(lock);
+		lock_owner = rt_mutex_owner(lock);
+
+		raw_spin_unlock(&lock->wait_lock);
+
+		debug_rt_mutex_print_deadlock(&waiter);
+
+		if (top_waiter != &waiter || adaptive_wait(lock, lock_owner))
+			schedule_rt_mutex(lock);
+
+		raw_spin_lock(&lock->wait_lock);
+
+		pi_lock(&self->pi_lock);
+		__set_current_state(TASK_UNINTERRUPTIBLE);
+		pi_unlock(&self->pi_lock);
+	}
+
+	/*
+	 * Restore the task state to current->saved_state. We set it
+	 * to the original state above and the try_to_wake_up() code
+	 * has possibly updated it when a real (non-rtmutex) wakeup
+	 * happened while we were blocked. Clear saved_state so
+	 * try_to_wakeup() does not get confused.
+	 */
+	pi_lock(&self->pi_lock);
+	__set_current_state(self->saved_state);
+	self->saved_state = TASK_RUNNING;
+	pi_unlock(&self->pi_lock);
+
+	/*
+	 * try_to_take_rt_mutex() sets the waiter bit
+	 * unconditionally. We might have to fix that up:
+	 */
+	fixup_rt_mutex_waiters(lock);
+
+	BUG_ON(rt_mutex_has_waiters(lock) && &waiter == rt_mutex_top_waiter(lock));
+	BUG_ON(!plist_node_empty(&waiter.list_entry));
+
+	raw_spin_unlock(&lock->wait_lock);
+
+	debug_rt_mutex_free_waiter(&waiter);
+}
+
+/*
+ * Slow path to release a rt_mutex spin_lock style
+ */
+static void __sched __rt_spin_lock_slowunlock(struct rt_mutex *lock)
+{
+	debug_rt_mutex_unlock(lock);
+
+	rt_mutex_deadlock_account_unlock(current);
+
+	if (!rt_mutex_has_waiters(lock)) {
+		lock->owner = NULL;
+		raw_spin_unlock(&lock->wait_lock);
+		return;
+	}
+
+	wakeup_next_waiter(lock);
+
+	raw_spin_unlock(&lock->wait_lock);
+
+	/* Undo pi boosting.when necessary */
+	rt_mutex_adjust_prio(current);
+}
+
+static void  noinline __sched rt_spin_lock_slowunlock(struct rt_mutex *lock)
+{
+	raw_spin_lock(&lock->wait_lock);
+	__rt_spin_lock_slowunlock(lock);
+}
+
+static void  noinline __sched rt_spin_lock_slowunlock_hirq(struct rt_mutex *lock)
+{
+	int ret;
+
+	do {
+		ret = raw_spin_trylock(&lock->wait_lock);
+	} while (!ret);
+
+	__rt_spin_lock_slowunlock(lock);
+}
+
+void __lockfunc rt_spin_lock(spinlock_t *lock)
+{
+	rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock);
+	spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+}
+EXPORT_SYMBOL(rt_spin_lock);
+
+void __lockfunc __rt_spin_lock(struct rt_mutex *lock)
+{
+	rt_spin_lock_fastlock(lock, rt_spin_lock_slowlock);
+}
+EXPORT_SYMBOL(__rt_spin_lock);
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass)
+{
+	rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock);
+	spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
+}
+EXPORT_SYMBOL(rt_spin_lock_nested);
+#endif
+
+void __lockfunc rt_spin_unlock(spinlock_t *lock)
+{
+	/* NOTE: we always pass in '1' for nested, for simplicity */
+	spin_release(&lock->dep_map, 1, _RET_IP_);
+	rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock);
+}
+EXPORT_SYMBOL(rt_spin_unlock);
+
+void __lockfunc rt_spin_unlock_after_trylock_in_irq(spinlock_t *lock)
+{
+	/* NOTE: we always pass in '1' for nested, for simplicity */
+	spin_release(&lock->dep_map, 1, _RET_IP_);
+	rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock_hirq);
+}
+
+void __lockfunc __rt_spin_unlock(struct rt_mutex *lock)
+{
+	rt_spin_lock_fastunlock(lock, rt_spin_lock_slowunlock);
+}
+EXPORT_SYMBOL(__rt_spin_unlock);
+
+/*
+ * Wait for the lock to get unlocked: instead of polling for an unlock
+ * (like raw spinlocks do), we lock and unlock, to force the kernel to
+ * schedule if there's contention:
+ */
+void __lockfunc rt_spin_unlock_wait(spinlock_t *lock)
+{
+	spin_lock(lock);
+	spin_unlock(lock);
+}
+EXPORT_SYMBOL(rt_spin_unlock_wait);
+
+int __lockfunc rt_spin_trylock(spinlock_t *lock)
+{
+	int ret = rt_mutex_trylock(&lock->lock);
+
+	if (ret)
+		spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+	return ret;
+}
+EXPORT_SYMBOL(rt_spin_trylock);
+
+int __lockfunc rt_spin_trylock_bh(spinlock_t *lock)
+{
+	int ret;
+
+	local_bh_disable();
+	ret = rt_mutex_trylock(&lock->lock);
+	if (ret) {
+		migrate_disable();
+		spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+	} else
+		local_bh_enable();
+	return ret;
+}
+EXPORT_SYMBOL(rt_spin_trylock_bh);
+
+int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags)
+{
+	int ret;
+
+	*flags = 0;
+	migrate_disable();
+	ret = rt_mutex_trylock(&lock->lock);
+	if (ret)
+		spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+	else
+		migrate_enable();
+	return ret;
+}
+EXPORT_SYMBOL(rt_spin_trylock_irqsave);
+
+int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock)
+{
+	/* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */
+	if (atomic_add_unless(atomic, -1, 1))
+		return 0;
+	migrate_disable();
+	rt_spin_lock(lock);
+	if (atomic_dec_and_test(atomic))
+		return 1;
+	rt_spin_unlock(lock);
+	migrate_enable();
+	return 0;
+}
+EXPORT_SYMBOL(atomic_dec_and_spin_lock);
+
+void
+__rt_spin_lock_init(spinlock_t *lock, char *name, struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/*
+	 * Make sure we are not reinitializing a held lock:
+	 */
+	debug_check_no_locks_freed((void *)lock, sizeof(*lock));
+	lockdep_init_map(&lock->dep_map, name, key, 0);
+#endif
+}
+EXPORT_SYMBOL(__rt_spin_lock_init);
+
+#endif /* PREEMPT_RT_FULL */
+
 /**
  * __rt_mutex_slowlock() - Perform the wait-wake-try-to-take loop
  * @lock:		 the rt_mutex to take
  * @state:		 the state the task should block in (TASK_INTERRUPTIBLE
- * 			 or TASK_UNINTERRUPTIBLE)
+ *			 or TASK_UNINTERRUPTIBLE)
  * @timeout:		 the pre-initialized and started timer, or NULL for none
  * @waiter:		 the pre-initialized rt_mutex_waiter
  *
@@ -796,14 +1478,15 @@
 static int __sched
 rt_mutex_slowlock(struct rt_mutex *lock, int state,
 		  struct hrtimer_sleeper *timeout,
-		  int detect_deadlock)
+		  enum rtmutex_chainwalk chwalk)
 {
 	struct rt_mutex_waiter waiter;
 	int ret = 0;
 
-	debug_rt_mutex_init_waiter(&waiter);
+	rt_mutex_init_waiter(&waiter, false);
 
 	raw_spin_lock(&lock->wait_lock);
+	init_lists(lock);
 
 	/* Try to acquire the lock again: */
 	if (try_to_take_rt_mutex(lock, current, NULL)) {
@@ -820,7 +1503,7 @@
 			timeout->task = NULL;
 	}
 
-	ret = task_blocks_on_rt_mutex(lock, &waiter, current, detect_deadlock);
+	ret = task_blocks_on_rt_mutex(lock, &waiter, current, chwalk);
 
 	if (likely(!ret))
 		ret = __rt_mutex_slowlock(lock, state, timeout, &waiter);
@@ -828,8 +1511,9 @@
 	set_current_state(TASK_RUNNING);
 
 	if (unlikely(ret)) {
-		remove_waiter(lock, &waiter);
-		rt_mutex_handle_deadlock(ret, detect_deadlock, &waiter);
+		if (rt_mutex_has_waiters(lock))
+			remove_waiter(lock, &waiter);
+		rt_mutex_handle_deadlock(ret, chwalk, &waiter);
 	}
 
 	/*
@@ -852,22 +1536,33 @@
 /*
  * Slow path try-lock function:
  */
-static inline int
-rt_mutex_slowtrylock(struct rt_mutex *lock)
+static inline int rt_mutex_slowtrylock(struct rt_mutex *lock)
 {
-	int ret = 0;
+	int ret;
 
-	raw_spin_lock(&lock->wait_lock);
+	/*
+	 * If the lock already has an owner we fail to get the lock.
+	 * This can be done without taking the @lock->wait_lock as
+	 * it is only being read, and this is a trylock anyway.
+	 */
+	if (rt_mutex_owner(lock))
+		return 0;
 
-	if (likely(rt_mutex_owner(lock) != current)) {
+	/*
+	 * The mutex has currently no owner. Lock the wait lock and
+	 * try to acquire the lock.
+	 */
+	if (!raw_spin_trylock(&lock->wait_lock))
+		return 0;
+	init_lists(lock);
 
-		ret = try_to_take_rt_mutex(lock, current, NULL);
-		/*
-		 * try_to_take_rt_mutex() sets the lock waiters
-		 * bit unconditionally. Clean this up.
-		 */
-		fixup_rt_mutex_waiters(lock);
-	}
+	ret = try_to_take_rt_mutex(lock, current, NULL);
+
+	/*
+	 * try_to_take_rt_mutex() sets the lock waiters bit
+	 * unconditionally. Clean this up.
+	 */
+	fixup_rt_mutex_waiters(lock);
 
 	raw_spin_unlock(&lock->wait_lock);
 
@@ -945,30 +1640,31 @@
  */
 static inline int
 rt_mutex_fastlock(struct rt_mutex *lock, int state,
-		  int detect_deadlock,
 		  int (*slowfn)(struct rt_mutex *lock, int state,
 				struct hrtimer_sleeper *timeout,
-				int detect_deadlock))
+				enum rtmutex_chainwalk chwalk))
 {
-	if (!detect_deadlock && likely(rt_mutex_cmpxchg(lock, NULL, current))) {
+	if (likely(rt_mutex_cmpxchg(lock, NULL, current))) {
 		rt_mutex_deadlock_account_lock(lock, current);
 		return 0;
 	} else
-		return slowfn(lock, state, NULL, detect_deadlock);
+		return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK);
 }
 
 static inline int
 rt_mutex_timed_fastlock(struct rt_mutex *lock, int state,
-			struct hrtimer_sleeper *timeout, int detect_deadlock,
+			struct hrtimer_sleeper *timeout,
+			enum rtmutex_chainwalk chwalk,
 			int (*slowfn)(struct rt_mutex *lock, int state,
 				      struct hrtimer_sleeper *timeout,
 				      int detect_deadlock))
 {
-	if (!detect_deadlock && likely(rt_mutex_cmpxchg(lock, NULL, current))) {
+	if (chwalk == RT_MUTEX_MIN_CHAINWALK &&
+	    likely(rt_mutex_cmpxchg(lock, NULL, current))) {
 		rt_mutex_deadlock_account_lock(lock, current);
 		return 0;
 	} else
-		return slowfn(lock, state, timeout, detect_deadlock);
+		return slowfn(lock, state, timeout, chwalk);
 }
 
 static inline int
@@ -1001,54 +1697,77 @@
 {
 	might_sleep();
 
-	rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, 0, rt_mutex_slowlock);
+	rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock);
 }
 EXPORT_SYMBOL_GPL(rt_mutex_lock);
 
 /**
  * rt_mutex_lock_interruptible - lock a rt_mutex interruptible
  *
- * @lock: 		the rt_mutex to be locked
- * @detect_deadlock:	deadlock detection on/off
+ * @lock:		the rt_mutex to be locked
  *
  * Returns:
- *  0 		on success
- * -EINTR 	when interrupted by a signal
- * -EDEADLK	when the lock would deadlock (when deadlock detection is on)
+ *  0		on success
+ * -EINTR	when interrupted by a signal
  */
-int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock,
-						 int detect_deadlock)
+int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock)
 {
 	might_sleep();
 
-	return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE,
-				 detect_deadlock, rt_mutex_slowlock);
+	return rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, rt_mutex_slowlock);
 }
 EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible);
 
+/*
+ * Futex variant with full deadlock detection.
+ */
+int rt_mutex_timed_futex_lock(struct rt_mutex *lock,
+			      struct hrtimer_sleeper *timeout)
+{
+	might_sleep();
+
+	return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout,
+				       RT_MUTEX_FULL_CHAINWALK, rt_mutex_slowlock);
+}
+
+/**
+ * rt_mutex_lock_killable - lock a rt_mutex killable
+ *
+ * @lock:		the rt_mutex to be locked
+ *
+ * Returns:
+ *  0		on success
+ * -EINTR	when interrupted by a signal
+ * -EDEADLK	when the lock would deadlock (when deadlock detection is on)
+ */
+int __sched rt_mutex_lock_killable(struct rt_mutex *lock)
+{
+	might_sleep();
+
+	return rt_mutex_fastlock(lock, TASK_KILLABLE, rt_mutex_slowlock);
+}
+EXPORT_SYMBOL_GPL(rt_mutex_lock_killable);
+
 /**
  * rt_mutex_timed_lock - lock a rt_mutex interruptible
  *			the timeout structure is provided
  *			by the caller
  *
- * @lock: 		the rt_mutex to be locked
+ * @lock:		the rt_mutex to be locked
  * @timeout:		timeout structure or NULL (no timeout)
- * @detect_deadlock:	deadlock detection on/off
  *
  * Returns:
- *  0 		on success
- * -EINTR 	when interrupted by a signal
+ *  0		on success
+ * -EINTR	when interrupted by a signal
  * -ETIMEDOUT	when the timeout expired
- * -EDEADLK	when the lock would deadlock (when deadlock detection is on)
  */
 int
-rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout,
-		    int detect_deadlock)
+rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout)
 {
 	might_sleep();
 
 	return rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout,
-				       detect_deadlock, rt_mutex_slowlock);
+				       RT_MUTEX_MIN_CHAINWALK, rt_mutex_slowlock);
 }
 EXPORT_SYMBOL_GPL(rt_mutex_timed_lock);
 
@@ -1106,12 +1825,11 @@
 void __rt_mutex_init(struct rt_mutex *lock, const char *name)
 {
 	lock->owner = NULL;
-	raw_spin_lock_init(&lock->wait_lock);
 	plist_head_init(&lock->wait_list);
 
 	debug_rt_mutex_init(lock, name);
 }
-EXPORT_SYMBOL_GPL(__rt_mutex_init);
+EXPORT_SYMBOL(__rt_mutex_init);
 
 /**
  * rt_mutex_init_proxy_locked - initialize and lock a rt_mutex on behalf of a
@@ -1126,7 +1844,7 @@
 void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
 				struct task_struct *proxy_owner)
 {
-	__rt_mutex_init(lock, NULL);
+	rt_mutex_init(lock);
 	debug_rt_mutex_proxy_lock(lock, proxy_owner);
 	rt_mutex_set_owner(lock, proxy_owner);
 	rt_mutex_deadlock_account_lock(lock, proxy_owner);
@@ -1153,7 +1871,6 @@
  * @lock:		the rt_mutex to take
  * @waiter:		the pre-initialized rt_mutex_waiter
  * @task:		the task to prepare
- * @detect_deadlock:	perform deadlock detection (1) or not (0)
  *
  * Returns:
  *  0 - task blocked on lock
@@ -1164,7 +1881,7 @@
  */
 int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 			      struct rt_mutex_waiter *waiter,
-			      struct task_struct *task, int detect_deadlock)
+			      struct task_struct *task)
 {
 	int ret;
 
@@ -1175,8 +1892,38 @@
 		return 1;
 	}
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+	/*
+	 * In PREEMPT_RT there's an added race.
+	 * If the task, that we are about to requeue, times out,
+	 * it can set the PI_WAKEUP_INPROGRESS. This tells the requeue
+	 * to skip this task. But right after the task sets
+	 * its pi_blocked_on to PI_WAKEUP_INPROGRESS it can then
+	 * block on the spin_lock(&hb->lock), which in RT is an rtmutex.
+	 * This will replace the PI_WAKEUP_INPROGRESS with the actual
+	 * lock that it blocks on. We *must not* place this task
+	 * on this proxy lock in that case.
+	 *
+	 * To prevent this race, we first take the task's pi_lock
+	 * and check if it has updated its pi_blocked_on. If it has,
+	 * we assume that it woke up and we return -EAGAIN.
+	 * Otherwise, we set the task's pi_blocked_on to
+	 * PI_REQUEUE_INPROGRESS, so that if the task is waking up
+	 * it will know that we are in the process of requeuing it.
+	 */
+	raw_spin_lock_irq(&task->pi_lock);
+	if (task->pi_blocked_on) {
+		raw_spin_unlock_irq(&task->pi_lock);
+		raw_spin_unlock(&lock->wait_lock);
+		return -EAGAIN;
+	}
+	task->pi_blocked_on = PI_REQUEUE_INPROGRESS;
+	raw_spin_unlock_irq(&task->pi_lock);
+#endif
+
 	/* We enforce deadlock detection for futexes */
-	ret = task_blocks_on_rt_mutex(lock, waiter, task, 1);
+	ret = task_blocks_on_rt_mutex(lock, waiter, task,
+				      RT_MUTEX_FULL_CHAINWALK);
 
 	if (ret && !rt_mutex_owner(lock)) {
 		/*
@@ -1222,22 +1969,20 @@
  * rt_mutex_finish_proxy_lock() - Complete lock acquisition
  * @lock:		the rt_mutex we were woken on
  * @to:			the timeout, null if none. hrtimer should already have
- * 			been started.
+ *			been started.
  * @waiter:		the pre-initialized rt_mutex_waiter
- * @detect_deadlock:	perform deadlock detection (1) or not (0)
  *
  * Complete the lock acquisition started our behalf by another thread.
  *
  * Returns:
  *  0 - success
- * <0 - error, one of -EINTR, -ETIMEDOUT, or -EDEADLK
+ * <0 - error, one of -EINTR, -ETIMEDOUT
  *
  * Special API call for PI-futex requeue support
  */
 int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
 			       struct hrtimer_sleeper *to,
-			       struct rt_mutex_waiter *waiter,
-			       int detect_deadlock)
+			       struct rt_mutex_waiter *waiter)
 {
 	int ret;
 
diff --git a/kernel/rtmutex.h b/kernel/rtmutex.h
index f6a1f3c..c406058 100644
--- a/kernel/rtmutex.h
+++ b/kernel/rtmutex.h
@@ -22,10 +22,15 @@
 #define debug_rt_mutex_init(m, n)			do { } while (0)
 #define debug_rt_mutex_deadlock(d, a ,l)		do { } while (0)
 #define debug_rt_mutex_print_deadlock(w)		do { } while (0)
-#define debug_rt_mutex_detect_deadlock(w,d)		(d)
 #define debug_rt_mutex_reset_waiter(w)			do { } while (0)
 
 static inline void rt_mutex_print_deadlock(struct rt_mutex_waiter *w)
 {
 	WARN(1, "rtmutex deadlock detected\n");
 }
+
+static inline bool debug_rt_mutex_detect_deadlock(struct rt_mutex_waiter *w,
+						  enum rtmutex_chainwalk walk)
+{
+	return walk == RT_MUTEX_FULL_CHAINWALK;
+}
diff --git a/kernel/rtmutex_common.h b/kernel/rtmutex_common.h
index 53a66c8..213c7bf 100644
--- a/kernel/rtmutex_common.h
+++ b/kernel/rtmutex_common.h
@@ -49,6 +49,7 @@
 	struct plist_node	pi_list_entry;
 	struct task_struct	*task;
 	struct rt_mutex		*lock;
+	bool			savestate;
 #ifdef CONFIG_DEBUG_RT_MUTEXES
 	unsigned long		ip;
 	struct pid		*deadlock_task_pid;
@@ -101,8 +102,26 @@
 }
 
 /*
+ * Constants for rt mutex functions which have a selectable deadlock
+ * detection.
+ *
+ * RT_MUTEX_MIN_CHAINWALK:	Stops the lock chain walk when there are
+ *				no further PI adjustments to be made.
+ *
+ * RT_MUTEX_FULL_CHAINWALK:	Invoke deadlock detection with a full
+ *				walk of the lock chain.
+ */
+enum rtmutex_chainwalk {
+	RT_MUTEX_MIN_CHAINWALK,
+	RT_MUTEX_FULL_CHAINWALK,
+};
+
+/*
  * PI-futex support (proxy locking functions, etc.):
  */
+#define PI_WAKEUP_INPROGRESS	((struct rt_mutex_waiter *) 1)
+#define PI_REQUEUE_INPROGRESS	((struct rt_mutex_waiter *) 2)
+
 extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock);
 extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
 				       struct task_struct *proxy_owner);
@@ -110,12 +129,11 @@
 				  struct task_struct *proxy_owner);
 extern int rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 				     struct rt_mutex_waiter *waiter,
-				     struct task_struct *task,
-				     int detect_deadlock);
+				     struct task_struct *task);
 extern int rt_mutex_finish_proxy_lock(struct rt_mutex *lock,
 				      struct hrtimer_sleeper *to,
-				      struct rt_mutex_waiter *waiter,
-				      int detect_deadlock);
+				      struct rt_mutex_waiter *waiter);
+extern int rt_mutex_timed_futex_lock(struct rt_mutex *l, struct hrtimer_sleeper *to);
 
 #ifdef CONFIG_DEBUG_RT_MUTEXES
 # include "rtmutex-debug.h"
@@ -123,4 +141,12 @@
 # include "rtmutex.h"
 #endif
 
+static inline void
+rt_mutex_init_waiter(struct rt_mutex_waiter *waiter, bool savestate)
+{
+	debug_rt_mutex_init_waiter(waiter);
+	waiter->task = NULL;
+	waiter->savestate = savestate;
+}
+
 #endif
diff --git a/kernel/sched.c b/kernel/sched.c
index fe33d0f..74cfb31 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -189,6 +189,7 @@
 
 	hrtimer_init(&rt_b->rt_period_timer,
 			CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	rt_b->rt_period_timer.irqsafe = 1;
 	rt_b->rt_period_timer.function = sched_rt_period_timer;
 }
 
@@ -938,7 +939,11 @@
  * Number of tasks to iterate in a single balance run.
  * Limited because this is done with IRQs disabled.
  */
+#ifndef CONFIG_PREEMPT_RT_FULL
 const_debug unsigned int sysctl_sched_nr_migrate = 32;
+#else
+const_debug unsigned int sysctl_sched_nr_migrate = 8;
+#endif
 
 /*
  * period over which we average the RT time consumption, measured
@@ -1274,6 +1279,7 @@
 
 	hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	rq->hrtick_timer.function = hrtick;
+	rq->hrtick_timer.irqsafe = 1;
 }
 #else	/* CONFIG_SCHED_HRTICK */
 static inline void hrtick_clear(struct rq *rq)
@@ -2444,7 +2450,8 @@
 		 * is actually now running somewhere else!
 		 */
 		while (task_running(rq, p)) {
-			if (match_state && unlikely(p->state != match_state))
+			if (match_state && unlikely(p->state != match_state)
+			    && unlikely(p->saved_state != match_state))
 				return 0;
 			cpu_relax();
 		}
@@ -2459,7 +2466,8 @@
 		running = task_running(rq, p);
 		on_rq = p->on_rq;
 		ncsw = 0;
-		if (!match_state || p->state == match_state)
+		if (!match_state || p->state == match_state
+		    || p->saved_state == match_state)
 			ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
 		task_rq_unlock(rq, p, &flags);
 
@@ -2564,7 +2572,6 @@
 		printk(KERN_INFO "process %d (%s) no longer affine to cpu%d\n",
 				task_pid_nr(p), p->comm, cpu);
 	}
-
 	return dest_cpu;
 }
 
@@ -2644,10 +2651,6 @@
 {
 	activate_task(rq, p, en_flags);
 	p->on_rq = 1;
-
-	/* if a worker is waking up, notify workqueue */
-	if (p->flags & PF_WQ_WORKER)
-		wq_worker_waking_up(p, cpu_of(rq));
 }
 
 /*
@@ -2825,8 +2828,27 @@
 
 	smp_wmb();
 	raw_spin_lock_irqsave(&p->pi_lock, flags);
-	if (!(p->state & state))
+	if (!(p->state & state)) {
+		/*
+		 * The task might be running due to a spinlock sleeper
+		 * wakeup. Check the saved state and set it to running
+		 * if the wakeup condition is true.
+		 */
+		if (!(wake_flags & WF_LOCK_SLEEPER)) {
+			if (p->saved_state & state) {
+				p->saved_state = TASK_RUNNING;
+				success = 1;
+			}
+		}
 		goto out;
+	}
+
+	/*
+	 * If this is a regular wakeup, then we can unconditionally
+	 * clear the saved state of a "lock sleeper".
+	 */
+	if (!(wake_flags & WF_LOCK_SLEEPER))
+		p->saved_state = TASK_RUNNING;
 
 	success = 1; /* we're going to change ->state */
 	cpu = task_cpu(p);
@@ -2882,42 +2904,6 @@
 }
 
 /**
- * try_to_wake_up_local - try to wake up a local task with rq lock held
- * @p: the thread to be awakened
- *
- * Put @p on the run-queue if it's not already there. The caller must
- * ensure that this_rq() is locked, @p is bound to this_rq() and not
- * the current task.
- */
-static void try_to_wake_up_local(struct task_struct *p)
-{
-	struct rq *rq = task_rq(p);
-
-	if (WARN_ON_ONCE(rq != this_rq()) ||
-	    WARN_ON_ONCE(p == current))
-		return;
-
-	lockdep_assert_held(&rq->lock);
-
-	if (!raw_spin_trylock(&p->pi_lock)) {
-		raw_spin_unlock(&rq->lock);
-		raw_spin_lock(&p->pi_lock);
-		raw_spin_lock(&rq->lock);
-	}
-
-	if (!(p->state & TASK_NORMAL))
-		goto out;
-
-	if (!p->on_rq)
-		ttwu_activate(rq, p, ENQUEUE_WAKEUP);
-
-	ttwu_do_wakeup(rq, p, 0);
-	ttwu_stat(p, smp_processor_id(), 0);
-out:
-	raw_spin_unlock(&p->pi_lock);
-}
-
-/**
  * wake_up_process - Wake up a specific process
  * @p: The process to be woken up.
  *
@@ -2935,6 +2921,18 @@
 }
 EXPORT_SYMBOL(wake_up_process);
 
+/**
+ * wake_up_lock_sleeper - Wake up a specific process blocked on a "sleeping lock"
+ * @p: The process to be woken up.
+ *
+ * Same as wake_up_process() above, but wake_flags=WF_LOCK_SLEEPER to indicate
+ * the nature of the wakeup.
+ */
+int wake_up_lock_sleeper(struct task_struct *p)
+{
+	return try_to_wake_up(p, TASK_ALL, WF_LOCK_SLEEPER);
+}
+
 int wake_up_state(struct task_struct *p, unsigned int state)
 {
 	return try_to_wake_up(p, state, 0);
@@ -3209,8 +3207,12 @@
 	finish_lock_switch(rq, prev);
 
 	fire_sched_in_preempt_notifiers(current);
+	/*
+	 * We use mmdrop_delayed() here so we don't have to do the
+	 * full __mmdrop() when we are the last user.
+	 */
 	if (mm)
-		mmdrop(mm);
+		mmdrop_delayed(mm);
 	if (unlikely(prev_state == TASK_DEAD)) {
 		/*
 		 * Remove function-return probe instances associated with this
@@ -4484,8 +4486,13 @@
 	DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >=
 				PREEMPT_MASK - 10);
 #endif
-	if (preempt_count() == val)
-		trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1));
+	if (preempt_count() == val) {
+		unsigned long ip = get_parent_ip(CALLER_ADDR1);
+#ifdef CONFIG_DEBUG_PREEMPT
+		current->preempt_disable_ip = ip;
+#endif
+		trace_preempt_off(CALLER_ADDR0, ip);
+	}
 }
 EXPORT_SYMBOL(add_preempt_count);
 
@@ -4527,6 +4534,13 @@
 	print_modules();
 	if (irqs_disabled())
 		print_irqtrace_events(prev);
+#ifdef DEBUG_PREEMPT
+	if (in_atomic_preempt_off()) {
+		pr_err("Preemption disabled at:");
+		print_ip_sym(current->preempt_disable_ip);
+		pr_cont("\n");
+	}
+#endif
 
 	if (regs)
 		show_regs(regs);
@@ -4553,6 +4567,126 @@
 	schedstat_inc(this_rq(), sched_count);
 }
 
+#if defined(CONFIG_PREEMPT_RT_FULL) && defined(CONFIG_SMP)
+#define MIGRATE_DISABLE_SET_AFFIN	(1<<30) /* Can't make a negative */
+#define migrate_disabled_updated(p)	((p)->migrate_disable & MIGRATE_DISABLE_SET_AFFIN)
+#define migrate_disable_count(p)	((p)->migrate_disable & ~MIGRATE_DISABLE_SET_AFFIN)
+
+static inline void update_migrate_disable(struct task_struct *p)
+{
+	const struct cpumask *mask;
+
+	if (likely(!p->migrate_disable))
+		return;
+
+	/* Did we already update affinity? */
+	if (unlikely(migrate_disabled_updated(p)))
+		return;
+
+	/*
+	 * Since this is always current we can get away with only locking
+	 * rq->lock, the ->cpus_allowed value can normally only be changed
+	 * while holding both p->pi_lock and rq->lock, but seeing that this
+	 * is current, we cannot actually be waking up, so all code that
+	 * relies on serialization against p->pi_lock is out of scope.
+	 *
+	 * Having rq->lock serializes us against things like
+	 * set_cpus_allowed_ptr() that can still happen concurrently.
+	 */
+	mask = tsk_cpus_allowed(p);
+
+	if (p->sched_class->set_cpus_allowed)
+		p->sched_class->set_cpus_allowed(p, mask);
+	p->rt.nr_cpus_allowed = cpumask_weight(mask);
+
+	/* Let migrate_enable know to fix things back up */
+	p->migrate_disable |= MIGRATE_DISABLE_SET_AFFIN;
+}
+
+void migrate_disable(void)
+{
+	struct task_struct *p = current;
+
+	if (in_atomic()) {
+#ifdef CONFIG_SCHED_DEBUG
+		p->migrate_disable_atomic++;
+#endif
+		return;
+	}
+
+#ifdef CONFIG_SCHED_DEBUG
+	WARN_ON_ONCE(p->migrate_disable_atomic);
+#endif
+
+	preempt_disable();
+	if (p->migrate_disable) {
+		p->migrate_disable++;
+		preempt_enable();
+		return;
+	}
+
+	pin_current_cpu();
+	p->migrate_disable = 1;
+	preempt_enable();
+}
+EXPORT_SYMBOL(migrate_disable);
+
+void migrate_enable(void)
+{
+	struct task_struct *p = current;
+	const struct cpumask *mask;
+	unsigned long flags;
+	struct rq *rq;
+
+	if (in_atomic()) {
+#ifdef CONFIG_SCHED_DEBUG
+		p->migrate_disable_atomic--;
+#endif
+		return;
+	}
+
+#ifdef CONFIG_SCHED_DEBUG
+	WARN_ON_ONCE(p->migrate_disable_atomic);
+#endif
+	WARN_ON_ONCE(p->migrate_disable <= 0);
+
+	preempt_disable();
+	if (migrate_disable_count(p) > 1) {
+		p->migrate_disable--;
+		preempt_enable();
+		return;
+	}
+
+	if (unlikely(migrate_disabled_updated(p))) {
+		/*
+		 * Undo whatever update_migrate_disable() did, also see there
+		 * about locking.
+		 */
+		rq = this_rq();
+		raw_spin_lock_irqsave(&rq->lock, flags);
+
+		/*
+		 * Clearing migrate_disable causes tsk_cpus_allowed to
+		 * show the tasks original cpu affinity.
+		 */
+		p->migrate_disable = 0;
+		mask = tsk_cpus_allowed(p);
+		if (p->sched_class->set_cpus_allowed)
+			p->sched_class->set_cpus_allowed(p, mask);
+		p->rt.nr_cpus_allowed = cpumask_weight(mask);
+		raw_spin_unlock_irqrestore(&rq->lock, flags);
+	} else
+		p->migrate_disable = 0;
+
+	unpin_current_cpu();
+	preempt_enable();
+}
+EXPORT_SYMBOL(migrate_enable);
+#else
+static inline void update_migrate_disable(struct task_struct *p) { }
+#define migrate_disabled_updated(p)		0
+#endif
+
 static void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
 	if (prev->on_rq || rq->skip_clock_update < 0)
@@ -4612,6 +4746,8 @@
 
 	raw_spin_lock_irq(&rq->lock);
 
+	update_migrate_disable(prev);
+
 	switch_count = &prev->nivcsw;
 	if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
 		if (unlikely(signal_pending_state(prev->state, prev))) {
@@ -4619,19 +4755,6 @@
 		} else {
 			deactivate_task(rq, prev, DEQUEUE_SLEEP);
 			prev->on_rq = 0;
-
-			/*
-			 * If a worker went to sleep, notify and ask workqueue
-			 * whether it wants to wake up a task to maintain
-			 * concurrency.
-			 */
-			if (prev->flags & PF_WQ_WORKER) {
-				struct task_struct *to_wakeup;
-
-				to_wakeup = wq_worker_sleeping(prev, cpu);
-				if (to_wakeup)
-					try_to_wake_up_local(to_wakeup);
-			}
 		}
 		switch_count = &prev->nvcsw;
 	}
@@ -4665,7 +4788,7 @@
 
 	post_schedule(rq);
 
-	preempt_enable_no_resched();
+	__preempt_enable_no_resched();
 	if (need_resched())
 		goto need_resched;
 }
@@ -4675,6 +4798,19 @@
 	if (!tsk->state)
 		return;
 	/*
+	 * If a worker went to sleep, notify and ask workqueue whether
+	 * it wants to wake up a task to maintain concurrency.
+	 * Only call wake up if prev isn't blocked on a sleeping
+	 * spin lock.
+	 */
+	if (tsk->flags & PF_WQ_WORKER && !tsk->saved_state)
+		wq_worker_sleeping(tsk);
+
+
+	if (tsk_is_pi_blocked(tsk))
+		return;
+
+	/*
 	 * If we are going to sleep and we have plugged IO queued,
 	 * make sure to submit it to avoid deadlocks.
 	 */
@@ -4682,15 +4818,34 @@
 		blk_schedule_flush_plug(tsk);
 }
 
+static inline void sched_update_worker(struct task_struct *tsk)
+{
+	if (tsk->flags & PF_WQ_WORKER)
+		wq_worker_running(tsk);
+}
+
 asmlinkage void __sched schedule(void)
 {
 	struct task_struct *tsk = current;
 
 	sched_submit_work(tsk);
 	__schedule();
+	sched_update_worker(tsk);
 }
 EXPORT_SYMBOL(schedule);
 
+/**
+ * schedule_preempt_disabled - called with preemption disabled
+ *
+ * Returns with preemption disabled. Note: preempt_count must be 1
+ */
+void __sched schedule_preempt_disabled(void)
+{
+	__preempt_enable_no_resched();
+	schedule();
+	preempt_disable();
+}
+
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
 
 static inline bool owner_running(struct mutex *lock, struct task_struct *owner)
@@ -4755,7 +4910,16 @@
 
 	do {
 		add_preempt_count_notrace(PREEMPT_ACTIVE);
+		/*
+		 * The add/subtract must not be traced by the function
+		 * tracer. But we still want to account for the
+		 * preempt off latency tracer. Since the _notrace versions
+		 * of add/subtract skip the accounting for latency tracer
+		 * we must force it manually.
+		 */
+		start_critical_timings();
 		__schedule();
+		stop_critical_timings();
 		sub_preempt_count_notrace(PREEMPT_ACTIVE);
 
 		/*
@@ -4851,9 +5015,9 @@
 /*
  * Same as __wake_up but called with the spinlock in wait_queue_head_t held.
  */
-void __wake_up_locked(wait_queue_head_t *q, unsigned int mode)
+void __wake_up_locked(wait_queue_head_t *q, unsigned int mode, int nr)
 {
-	__wake_up_common(q, mode, 1, 0, NULL);
+	__wake_up_common(q, mode, nr, 0, NULL);
 }
 EXPORT_SYMBOL_GPL(__wake_up_locked);
 
@@ -5200,7 +5364,8 @@
  * This function changes the 'effective' priority of a task. It does
  * not touch ->normal_prio like __setscheduler().
  *
- * Used by the rt_mutex code to implement priority inheritance logic.
+ * Used by the rt_mutex code to implement priority inheritance
+ * logic. Call site only calls if the priority of the task changed.
  */
 void rt_mutex_setprio(struct task_struct *p, int prio)
 {
@@ -5212,6 +5377,24 @@
 
 	rq = __task_rq_lock(p);
 
+	/*
+	 * Idle task boosting is a nono in general. There is one
+	 * exception, when PREEMPT_RT and NOHZ is active:
+	 *
+	 * The idle task calls get_next_timer_interrupt() and holds
+	 * the timer wheel base->lock on the CPU and another CPU wants
+	 * to access the timer (probably to cancel it). We can safely
+	 * ignore the boosting request, as the idle CPU runs this code
+	 * with interrupts disabled and will complete the lock
+	 * protected section without being interrupted. So there is no
+	 * real need to boost.
+	 */
+	if (unlikely(p == rq->idle)) {
+		WARN_ON(p != rq->curr);
+		WARN_ON(p->pi_blocked_on);
+		goto out_unlock;
+	}
+
 	trace_sched_pi_setprio(p, prio);
 	oldprio = p->prio;
 	prev_class = p->sched_class;
@@ -5238,11 +5421,10 @@
 		enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0);
 
 	check_class_changed(rq, p, prev_class, oldprio);
+out_unlock:
 	__task_rq_unlock(rq);
 }
-
 #endif
-
 void set_user_nice(struct task_struct *p, long nice)
 {
 	int old_prio, delta, on_rq;
@@ -5409,20 +5591,25 @@
 	return pid ? find_task_by_vpid(pid) : current;
 }
 
-/* Actually do priority change: must hold rq lock. */
-static void
-__setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
+static void __setscheduler_params(struct task_struct *p, int policy, int prio)
 {
 	p->policy = policy;
 	p->rt_priority = prio;
 	p->normal_prio = normal_prio(p);
+	set_load_weight(p);
+}
+
+/* Actually do priority change: must hold rq lock. */
+static void
+__setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio)
+{
+	__setscheduler_params(p, policy, prio);
 	/* we are holding p->pi_lock already */
 	p->prio = rt_mutex_getprio(p);
 	if (rt_prio(p->prio))
 		p->sched_class = &rt_sched_class;
 	else
 		p->sched_class = &fair_sched_class;
-	set_load_weight(p);
 }
 
 /*
@@ -5447,6 +5634,7 @@
 static int __sched_setscheduler(struct task_struct *p, int policy,
 				const struct sched_param *param, bool user)
 {
+	int newprio = MAX_RT_PRIO - 1 - param->sched_priority;
 	int retval, oldprio, oldpolicy = -1, on_rq, running;
 	unsigned long flags;
 	const struct sched_class *prev_class;
@@ -5542,11 +5730,13 @@
 	}
 
 	/*
-	 * If not changing anything there's no need to proceed further:
+	 * If not changing anything there's no need to proceed
+	 * further, but store a possible modification of
+	 * reset_on_fork.
 	 */
 	if (unlikely(policy == p->policy && (!rt_policy(policy) ||
 			param->sched_priority == p->rt_priority))) {
-
+		p->sched_reset_on_fork = reset_on_fork;
 		__task_rq_unlock(rq);
 		raw_spin_unlock_irqrestore(&p->pi_lock, flags);
 		return 0;
@@ -5573,6 +5763,25 @@
 		task_rq_unlock(rq, p, &flags);
 		goto recheck;
 	}
+
+	p->sched_reset_on_fork = reset_on_fork;
+	oldprio = p->prio;
+
+	/*
+	 * Special case for priority boosted tasks.
+	 *
+	 * If the new priority is lower or equal (user space view)
+	 * than the current (boosted) priority, we just store the new
+	 * normal parameters and do not touch the scheduler class and
+	 * the runqueue. This will be done when the task deboost
+	 * itself.
+	 */
+	if (rt_mutex_check_prio(p, newprio)) {
+		__setscheduler_params(p, policy, param->sched_priority);
+		task_rq_unlock(rq, p, &flags);
+		return 0;
+	}
+
 	on_rq = p->on_rq;
 	running = task_current(rq, p);
 	if (on_rq)
@@ -5580,16 +5789,18 @@
 	if (running)
 		p->sched_class->put_prev_task(rq, p);
 
-	p->sched_reset_on_fork = reset_on_fork;
-
-	oldprio = p->prio;
 	prev_class = p->sched_class;
 	__setscheduler(rq, p, policy, param->sched_priority);
 
 	if (running)
 		p->sched_class->set_curr_task(rq);
-	if (on_rq)
-		activate_task(rq, p, 0);
+	if (on_rq) {
+		/*
+		 * We enqueue to tail when the priority of a task is
+		 * increased (user space view).
+		 */
+		activate_task(rq, p, oldprio <= p->prio ? ENQUEUE_HEAD : 0);
+	}
 
 	check_class_changed(rq, p, prev_class, oldprio);
 	task_rq_unlock(rq, p, &flags);
@@ -5922,7 +6133,7 @@
 	__release(rq->lock);
 	spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
 	do_raw_spin_unlock(&rq->lock);
-	preempt_enable_no_resched();
+	__preempt_enable_no_resched();
 
 	schedule();
 
@@ -5936,9 +6147,17 @@
 
 static void __cond_resched(void)
 {
-	add_preempt_count(PREEMPT_ACTIVE);
-	__schedule();
-	sub_preempt_count(PREEMPT_ACTIVE);
+	do {
+		add_preempt_count(PREEMPT_ACTIVE);
+		__schedule();
+		sub_preempt_count(PREEMPT_ACTIVE);
+		/*
+		 * Check again in case we missed a preemption
+		 * opportunity between schedule and now.
+		 */
+		barrier();
+
+	} while (need_resched());
 }
 
 int __sched _cond_resched(void)
@@ -5979,6 +6198,7 @@
 }
 EXPORT_SYMBOL(__cond_resched_lock);
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 int __sched __cond_resched_softirq(void)
 {
 	BUG_ON(!in_softirq());
@@ -5992,6 +6212,7 @@
 	return 0;
 }
 EXPORT_SYMBOL(__cond_resched_softirq);
+#endif
 
 /**
  * yield - yield the current processor to other threads.
@@ -6302,6 +6523,7 @@
 	rcu_read_unlock();
 
 	rq->curr = rq->idle = idle;
+	idle->on_rq = 1;
 #if defined(CONFIG_SMP)
 	idle->on_cpu = 1;
 #endif
@@ -6370,11 +6592,90 @@
 #ifdef CONFIG_SMP
 void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
 {
-	if (p->sched_class && p->sched_class->set_cpus_allowed)
-		p->sched_class->set_cpus_allowed(p, new_mask);
-
+	if (!migrate_disabled_updated(p)) {
+		if (p->sched_class && p->sched_class->set_cpus_allowed)
+			p->sched_class->set_cpus_allowed(p, new_mask);
+		p->rt.nr_cpus_allowed = cpumask_weight(new_mask);
+	}
 	cpumask_copy(&p->cpus_allowed, new_mask);
-	p->rt.nr_cpus_allowed = cpumask_weight(new_mask);
+}
+
+static DEFINE_PER_CPU(struct cpumask, sched_cpumasks);
+static DEFINE_MUTEX(sched_down_mutex);
+static cpumask_t sched_down_cpumask;
+
+void tell_sched_cpu_down_begin(int cpu)
+{
+	mutex_lock(&sched_down_mutex);
+	cpumask_set_cpu(cpu, &sched_down_cpumask);
+	mutex_unlock(&sched_down_mutex);
+}
+
+void tell_sched_cpu_down_done(int cpu)
+{
+	mutex_lock(&sched_down_mutex);
+	cpumask_clear_cpu(cpu, &sched_down_cpumask);
+	mutex_unlock(&sched_down_mutex);
+}
+
+/**
+ * migrate_me - try to move the current task off this cpu
+ *
+ * Used by the pin_current_cpu() code to try to get tasks
+ * to move off the current CPU as it is going down.
+ * It will only move the task if the task isn't pinned to
+ * the CPU (with migrate_disable, affinity or THREAD_BOUND)
+ * and the task has to be in a RUNNING state. Otherwise the
+ * movement of the task will wake it up (change its state
+ * to running) when the task did not expect it.
+ *
+ * Returns 1 if it succeeded in moving the current task
+ *         0 otherwise.
+ */
+int migrate_me(void)
+{
+	struct task_struct *p = current;
+	struct migration_arg arg;
+	struct cpumask *cpumask;
+	struct cpumask *mask;
+	unsigned long flags;
+	unsigned int dest_cpu;
+	struct rq *rq;
+
+	/*
+	 * We can not migrate tasks bounded to a CPU or tasks not
+	 * running. The movement of the task will wake it up.
+	 */
+	if (p->flags & PF_THREAD_BOUND || p->state)
+		return 0;
+
+	mutex_lock(&sched_down_mutex);
+	rq = task_rq_lock(p, &flags);
+
+	cpumask = &__get_cpu_var(sched_cpumasks);
+	mask = &p->cpus_allowed;
+
+	cpumask_andnot(cpumask, mask, &sched_down_cpumask);
+
+	if (!cpumask_weight(cpumask)) {
+		/* It's only on this CPU? */
+		task_rq_unlock(rq, p, &flags);
+		mutex_unlock(&sched_down_mutex);
+		return 0;
+	}
+
+	dest_cpu = cpumask_any_and(cpu_active_mask, cpumask);
+
+	arg.task = p;
+	arg.dest_cpu = dest_cpu;
+
+	task_rq_unlock(rq, p, &flags);
+
+	stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
+	tlb_migrate_finish(p->mm);
+	mutex_unlock(&sched_down_mutex);
+
+	return 1;
 }
 
 /*
@@ -6425,7 +6726,7 @@
 	do_set_cpus_allowed(p, new_mask);
 
 	/* Can the task run on the task's current CPU? If so, we're done */
-	if (cpumask_test_cpu(task_cpu(p), new_mask))
+	if (cpumask_test_cpu(task_cpu(p), new_mask) || __migrate_disabled(p))
 		goto out;
 
 	dest_cpu = cpumask_any_and(cpu_active_mask, new_mask);
@@ -6514,6 +6815,8 @@
 
 #ifdef CONFIG_HOTPLUG_CPU
 
+static DEFINE_PER_CPU(struct mm_struct *, idle_last_mm);
+
 /*
  * Ensures that the idle task is using init_mm right before its cpu goes
  * offline.
@@ -6526,7 +6829,12 @@
 
 	if (mm != &init_mm)
 		switch_mm(mm, &init_mm, current);
-	mmdrop(mm);
+
+	/*
+	 * Defer the cleanup to an alive cpu. On RT we can neither
+	 * call mmdrop() nor mmdrop_delayed() from here.
+	 */
+	per_cpu(idle_last_mm, smp_processor_id()) = mm;
 }
 
 /*
@@ -6879,6 +7187,12 @@
 		migrate_nr_uninterruptible(rq);
 		calc_global_load_remove(rq);
 		break;
+	case CPU_DEAD:
+		if (per_cpu(idle_last_mm, cpu)) {
+			mmdrop(per_cpu(idle_last_mm, cpu));
+			per_cpu(idle_last_mm, cpu) = NULL;
+		}
+		break;
 #endif
 	}
 
@@ -8624,7 +8938,8 @@
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 static inline int preempt_count_equals(int preempt_offset)
 {
-	int nested = (preempt_count() & ~PREEMPT_ACTIVE) + rcu_preempt_depth();
+	int nested = (preempt_count() & ~PREEMPT_ACTIVE) +
+		sched_rcu_preempt_depth();
 
 	return (nested == preempt_offset);
 }
@@ -8634,7 +8949,8 @@
 	static unsigned long prev_jiffy;	/* ratelimiting */
 
 	rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */
-	if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) ||
+	if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
+	     !is_idle_task(current)) ||
 	    system_state != SYSTEM_RUNNING || oops_in_progress)
 		return;
 	if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
@@ -8652,6 +8968,13 @@
 	debug_show_held_locks(current);
 	if (irqs_disabled())
 		print_irqtrace_events(current);
+#ifdef DEBUG_PREEMPT
+	if (!preempt_count_equals(preempt_offset)) {
+		pr_err("Preemption disabled at:");
+		print_ip_sym(current->preempt_disable_ip);
+		pr_cont("\n");
+	}
+#endif
 	dump_stack();
 }
 EXPORT_SYMBOL(__might_sleep);
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 704ffe3..4f9b167 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -243,6 +243,9 @@
 	P(rt_throttled);
 	PN(rt_time);
 	PN(rt_runtime);
+#ifdef CONFIG_SMP
+	P(rt_nr_migratory);
+#endif
 
 #undef PN
 #undef P
@@ -492,6 +495,10 @@
 	P(se.load.weight);
 	P(policy);
 	P(prio);
+#ifdef CONFIG_PREEMPT_RT_FULL
+	P(migrate_disable);
+#endif
+	P(rt.nr_cpus_allowed);
 #undef PN
 #undef __PN
 #undef P
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 4c6dae1..ffbc079 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -2901,6 +2901,10 @@
 		 */
 		if (idle == CPU_NEWLY_IDLE)
 			break;
+
+		if (raw_spin_is_contended(&this_rq->lock) ||
+		    raw_spin_is_contended(&busiest->lock))
+			break;
 #endif
 
 		/*
@@ -3041,6 +3045,20 @@
 		rem_load_move -= moved_load;
 		if (rem_load_move < 0)
 			break;
+
+#ifdef CONFIG_PREEMPT
+		/*
+		 * NEWIDLE balancing is a source of latency, so preemptible
+		 * kernels will stop after the first task is pulled to minimize
+		 * the critical section.
+		 */
+		if (idle == CPU_NEWLY_IDLE && this_rq->nr_running)
+			break;
+
+		if (raw_spin_is_contended(&this_rq->lock) ||
+		    raw_spin_is_contended(&busiest->lock))
+			break;
+#endif
 	}
 	rcu_read_unlock();
 
diff --git a/kernel/sched_features.h b/kernel/sched_features.h
index 8480224..0007001 100644
--- a/kernel/sched_features.h
+++ b/kernel/sched_features.h
@@ -60,11 +60,15 @@
  */
 SCHED_FEAT(NONTASK_POWER, 1)
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /*
  * Queue remote wakeups on the target CPU and process them
  * using the scheduler IPI. Reduces rq->lock contention/bounces.
  */
 SCHED_FEAT(TTWU_QUEUE, 1)
+#else
+SCHED_FEAT(TTWU_QUEUE, 0)
+#endif
 
 SCHED_FEAT(FORCE_SD_OVERLAP, 0)
 SCHED_FEAT(RT_RUNTIME_SHARE, 1)
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index bd4afa4..37ef951 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -581,12 +581,9 @@
 
 static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
 {
-	int i, idle = 1;
+	int i, idle = 1, throttled = 0;
 	const struct cpumask *span;
 
-	if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
-		return 1;
-
 	span = sched_rt_period_mask();
 #ifdef CONFIG_RT_GROUP_SCHED
 	/*
@@ -634,12 +631,17 @@
 			if (!rt_rq_throttled(rt_rq))
 				enqueue = 1;
 		}
+		if (rt_rq->rt_throttled)
+			throttled = 1;
 
 		if (enqueue)
 			sched_rt_rq_enqueue(rt_rq);
 		raw_spin_unlock(&rq->lock);
 	}
 
+	if (!throttled && (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF))
+		return 1;
+
 	return idle;
 }
 
@@ -671,8 +673,24 @@
 		return 0;
 
 	if (rt_rq->rt_time > runtime) {
-		rt_rq->rt_throttled = 1;
-		printk_once(KERN_WARNING "sched: RT throttling activated\n");
+		struct rt_bandwidth *rt_b = sched_rt_bandwidth(rt_rq);
+
+		/*
+		 * Don't actually throttle groups that have no runtime assigned
+		 * but accrue some time due to boosting.
+		 */
+		if (likely(rt_b->rt_runtime)) {
+			rt_rq->rt_throttled = 1;
+			printk_once(KERN_WARNING "sched: RT throttling activated\n");
+		} else {
+			/*
+			 * In case we did anyway, make it go away,
+			 * replenishment is a joke, since it will replenish us
+			 * with exactly 0 ns.
+			 */
+			rt_rq->rt_time = 0;
+		}
+
 		if (rt_rq_throttled(rt_rq)) {
 			sched_rt_rq_dequeue(rt_rq);
 			return 1;
@@ -700,7 +718,8 @@
 	if (unlikely((s64)delta_exec < 0))
 		delta_exec = 0;
 
-	schedstat_set(curr->se.statistics.exec_max, max(curr->se.statistics.exec_max, delta_exec));
+	schedstat_set(curr->se.statistics.exec_max,
+		      max(curr->se.statistics.exec_max, delta_exec));
 
 	curr->se.sum_exec_runtime += delta_exec;
 	account_group_exec_runtime(curr, delta_exec);
diff --git a/kernel/signal.c b/kernel/signal.c
index 3ecf574..459df74 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -344,13 +344,45 @@
 	return false;
 }
 
+#ifdef __HAVE_ARCH_CMPXCHG
+static inline struct sigqueue *get_task_cache(struct task_struct *t)
+{
+	struct sigqueue *q = t->sigqueue_cache;
+
+	if (cmpxchg(&t->sigqueue_cache, q, NULL) != q)
+		return NULL;
+	return q;
+}
+
+static inline int put_task_cache(struct task_struct *t, struct sigqueue *q)
+{
+	if (cmpxchg(&t->sigqueue_cache, NULL, q) == NULL)
+		return 0;
+	return 1;
+}
+
+#else
+
+static inline struct sigqueue *get_task_cache(struct task_struct *t)
+{
+	return NULL;
+}
+
+static inline int put_task_cache(struct task_struct *t, struct sigqueue *q)
+{
+	return 1;
+}
+
+#endif
+
 /*
  * allocate a new signal queue record
  * - this may be called without locks if and only if t == current, otherwise an
  *   appropriate lock must be held to stop the target task from exiting
  */
 static struct sigqueue *
-__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimit)
+__sigqueue_do_alloc(int sig, struct task_struct *t, gfp_t flags,
+		    int override_rlimit, int fromslab)
 {
 	struct sigqueue *q = NULL;
 	struct user_struct *user;
@@ -367,7 +399,10 @@
 	if (override_rlimit ||
 	    atomic_read(&user->sigpending) <=
 			task_rlimit(t, RLIMIT_SIGPENDING)) {
-		q = kmem_cache_alloc(sigqueue_cachep, flags);
+		if (!fromslab)
+			q = get_task_cache(t);
+		if (!q)
+			q = kmem_cache_alloc(sigqueue_cachep, flags);
 	} else {
 		print_dropped_signal(sig);
 	}
@@ -384,6 +419,13 @@
 	return q;
 }
 
+static struct sigqueue *
+__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags,
+		 int override_rlimit)
+{
+	return __sigqueue_do_alloc(sig, t, flags, override_rlimit, 0);
+}
+
 static void __sigqueue_free(struct sigqueue *q)
 {
 	if (q->flags & SIGQUEUE_PREALLOC)
@@ -393,6 +435,21 @@
 	kmem_cache_free(sigqueue_cachep, q);
 }
 
+static void sigqueue_free_current(struct sigqueue *q)
+{
+	struct user_struct *up;
+
+	if (q->flags & SIGQUEUE_PREALLOC)
+		return;
+
+	up = q->user;
+	if (rt_prio(current->normal_prio) && !put_task_cache(current, q)) {
+		atomic_dec(&up->sigpending);
+		free_uid(up);
+	} else
+		  __sigqueue_free(q);
+}
+
 void flush_sigqueue(struct sigpending *queue)
 {
 	struct sigqueue *q;
@@ -406,6 +463,21 @@
 }
 
 /*
+ * Called from __exit_signal. Flush tsk->pending and
+ * tsk->sigqueue_cache
+ */
+void flush_task_sigqueue(struct task_struct *tsk)
+{
+	struct sigqueue *q;
+
+	flush_sigqueue(&tsk->pending);
+
+	q = get_task_cache(tsk);
+	if (q)
+		kmem_cache_free(sigqueue_cachep, q);
+}
+
+/*
  * Flush all pending signals for a task.
  */
 void __flush_signals(struct task_struct *t)
@@ -557,7 +629,7 @@
 still_pending:
 		list_del_init(&first->list);
 		copy_siginfo(info, &first->info);
-		__sigqueue_free(first);
+		sigqueue_free_current(first);
 	} else {
 		/*
 		 * Ok, it wasn't in the queue.  This must be
@@ -603,6 +675,8 @@
 {
 	int signr;
 
+	WARN_ON_ONCE(tsk != current);
+
 	/* We only dequeue private signals from ourselves, we don't let
 	 * signalfd steal them
 	 */
@@ -682,6 +756,10 @@
 void signal_wake_up_state(struct task_struct *t, unsigned int state)
 {
 	set_tsk_thread_flag(t, TIF_SIGPENDING);
+
+	if (unlikely(t == current))
+		return;
+
 	/*
 	 * TASK_WAKEKILL also means wake it up in the stopped/traced/killable
 	 * case. We don't check t->state here because there is a race with it
@@ -1193,8 +1271,8 @@
  * We don't want to have recursive SIGSEGV's etc, for example,
  * that is why we also clear SIGNAL_UNKILLABLE.
  */
-int
-force_sig_info(int sig, struct siginfo *info, struct task_struct *t)
+static int
+do_force_sig_info(int sig, struct siginfo *info, struct task_struct *t)
 {
 	unsigned long int flags;
 	int ret, blocked, ignored;
@@ -1219,6 +1297,39 @@
 	return ret;
 }
 
+int force_sig_info(int sig, struct siginfo *info, struct task_struct *t)
+{
+/*
+ * On some archs, PREEMPT_RT has to delay sending a signal from a trap
+ * since it can not enable preemption, and the signal code's spin_locks
+ * turn into mutexes. Instead, it must set TIF_NOTIFY_RESUME which will
+ * send the signal on exit of the trap.
+ */
+#ifdef ARCH_RT_DELAYS_SIGNAL_SEND
+	if (in_atomic()) {
+		if (WARN_ON_ONCE(t != current))
+			return 0;
+		if (WARN_ON_ONCE(t->forced_info.si_signo))
+			return 0;
+
+		if (is_si_special(info)) {
+			WARN_ON_ONCE(info != SEND_SIG_PRIV);
+			t->forced_info.si_signo = sig;
+			t->forced_info.si_errno = 0;
+			t->forced_info.si_code = SI_KERNEL;
+			t->forced_info.si_pid = 0;
+			t->forced_info.si_uid = 0;
+		} else {
+			t->forced_info = *info;
+		}
+
+		set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);
+		return 0;
+	}
+#endif
+	return do_force_sig_info(sig, info, t);
+}
+
 /*
  * Nuke all other threads in the group.
  */
@@ -1249,12 +1360,12 @@
 	struct sighand_struct *sighand;
 
 	for (;;) {
-		local_irq_save(*flags);
+		local_irq_save_nort(*flags);
 		rcu_read_lock();
 		sighand = rcu_dereference(tsk->sighand);
 		if (unlikely(sighand == NULL)) {
 			rcu_read_unlock();
-			local_irq_restore(*flags);
+			local_irq_restore_nort(*flags);
 			break;
 		}
 
@@ -1265,7 +1376,7 @@
 		}
 		spin_unlock(&sighand->siglock);
 		rcu_read_unlock();
-		local_irq_restore(*flags);
+		local_irq_restore_nort(*flags);
 	}
 
 	return sighand;
@@ -1512,7 +1623,8 @@
  */
 struct sigqueue *sigqueue_alloc(void)
 {
-	struct sigqueue *q = __sigqueue_alloc(-1, current, GFP_KERNEL, 0);
+	/* Preallocated sigqueue objects always from the slabcache ! */
+	struct sigqueue *q = __sigqueue_do_alloc(-1, current, GFP_KERNEL, 0, 1);
 
 	if (q)
 		q->flags |= SIGQUEUE_PREALLOC;
@@ -1867,15 +1979,7 @@
 		if (gstop_done && ptrace_reparented(current))
 			do_notify_parent_cldstop(current, false, why);
 
-		/*
-		 * Don't want to allow preemption here, because
-		 * sys_ptrace() needs this task to be inactive.
-		 *
-		 * XXX: implement read_unlock_no_resched().
-		 */
-		preempt_disable();
 		read_unlock(&tasklist_lock);
-		preempt_enable_no_resched();
 		schedule();
 	} else {
 		/*
diff --git a/kernel/smp.c b/kernel/smp.c
index 9e800b2..d5f3238 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -712,3 +712,93 @@
 	return ret;
 }
 EXPORT_SYMBOL(on_each_cpu);
+
+/**
+ * on_each_cpu_mask(): Run a function on processors specified by
+ * cpumask, which may include the local processor.
+ * @mask: The set of cpus to run on (only runs on online subset).
+ * @func: The function to run. This must be fast and non-blocking.
+ * @info: An arbitrary pointer to pass to the function.
+ * @wait: If true, wait (atomically) until function has completed
+ *        on other CPUs.
+ *
+ * If @wait is true, then returns once @func has returned.
+ *
+ * You must not call this function with disabled interrupts or
+ * from a hardware interrupt handler or from a bottom half handler.
+ */
+void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func,
+			void *info, bool wait)
+{
+	int cpu = get_cpu();
+
+	smp_call_function_many(mask, func, info, wait);
+	if (cpumask_test_cpu(cpu, mask)) {
+		local_irq_disable();
+		func(info);
+		local_irq_enable();
+	}
+	put_cpu();
+}
+EXPORT_SYMBOL(on_each_cpu_mask);
+
+/*
+ * on_each_cpu_cond(): Call a function on each processor for which
+ * the supplied function cond_func returns true, optionally waiting
+ * for all the required CPUs to finish. This may include the local
+ * processor.
+ * @cond_func:	A callback function that is passed a cpu id and
+ *		the the info parameter. The function is called
+ *		with preemption disabled. The function should
+ *		return a blooean value indicating whether to IPI
+ *		the specified CPU.
+ * @func:	The function to run on all applicable CPUs.
+ *		This must be fast and non-blocking.
+ * @info:	An arbitrary pointer to pass to both functions.
+ * @wait:	If true, wait (atomically) until function has
+ *		completed on other CPUs.
+ * @gfp_flags:	GFP flags to use when allocating the cpumask
+ *		used internally by the function.
+ *
+ * The function might sleep if the GFP flags indicates a non
+ * atomic allocation is allowed.
+ *
+ * Preemption is disabled to protect against CPUs going offline but not online.
+ * CPUs going online during the call will not be seen or sent an IPI.
+ *
+ * You must not call this function with disabled interrupts or
+ * from a hardware interrupt handler or from a bottom half handler.
+ */
+void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
+			smp_call_func_t func, void *info, bool wait,
+			gfp_t gfp_flags)
+{
+	cpumask_var_t cpus;
+	int cpu, ret;
+
+	might_sleep_if(gfp_flags & __GFP_WAIT);
+
+	if (likely(zalloc_cpumask_var(&cpus, (gfp_flags|__GFP_NOWARN)))) {
+		preempt_disable();
+		for_each_online_cpu(cpu)
+			if (cond_func(cpu, info))
+				cpumask_set_cpu(cpu, cpus);
+		on_each_cpu_mask(cpus, func, info, wait);
+		preempt_enable();
+		free_cpumask_var(cpus);
+	} else {
+		/*
+		 * No free cpumask, bother. No matter, we'll
+		 * just have to IPI them one by one.
+		 */
+		preempt_disable();
+		for_each_online_cpu(cpu)
+			if (cond_func(cpu, info)) {
+				ret = smp_call_function_single(cpu, func,
+								info, wait);
+				WARN_ON_ONCE(!ret);
+			}
+		preempt_enable();
+	}
+}
+EXPORT_SYMBOL(on_each_cpu_cond);
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 44bc103..b7d6839 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -21,9 +21,11 @@
 #include <linux/freezer.h>
 #include <linux/kthread.h>
 #include <linux/rcupdate.h>
+#include <linux/delay.h>
 #include <linux/ftrace.h>
 #include <linux/smp.h>
 #include <linux/tick.h>
+#include <linux/locallock.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/irq.h>
@@ -61,6 +63,67 @@
 	"TASKLET", "SCHED", "HRTIMER", "RCU"
 };
 
+#ifdef CONFIG_NO_HZ
+# ifdef CONFIG_PREEMPT_RT_FULL
+/*
+ * On preempt-rt a softirq might be blocked on a lock. There might be
+ * no other runnable task on this CPU because the lock owner runs on
+ * some other CPU. So we have to go into idle with the pending bit
+ * set. Therefor we need to check this otherwise we warn about false
+ * positives which confuses users and defeats the whole purpose of
+ * this test.
+ *
+ * This code is called with interrupts disabled.
+ */
+void softirq_check_pending_idle(void)
+{
+	static int rate_limit;
+	u32 warnpending = 0, pending = local_softirq_pending();
+
+	if (rate_limit >= 10)
+		return;
+
+	if (pending) {
+		struct task_struct *tsk;
+
+		tsk = __get_cpu_var(ksoftirqd);
+		/*
+		 * The wakeup code in rtmutex.c wakes up the task
+		 * _before_ it sets pi_blocked_on to NULL under
+		 * tsk->pi_lock. So we need to check for both: state
+		 * and pi_blocked_on.
+		 */
+		raw_spin_lock(&tsk->pi_lock);
+
+		if (!tsk->pi_blocked_on && !(tsk->state == TASK_RUNNING))
+			warnpending = 1;
+
+		raw_spin_unlock(&tsk->pi_lock);
+	}
+
+	if (warnpending) {
+		printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
+		       pending);
+		rate_limit++;
+	}
+}
+# else
+/*
+ * On !PREEMPT_RT we just printk rate limited:
+ */
+void softirq_check_pending_idle(void)
+{
+	static int rate_limit;
+
+	if (rate_limit < 10) {
+		printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
+		       local_softirq_pending());
+		rate_limit++;
+	}
+}
+# endif
+#endif
+
 /*
  * we cannot loop indefinitely here to avoid userspace starvation,
  * but we also don't want to introduce a worst case 1/HZ latency
@@ -76,6 +139,36 @@
 		wake_up_process(tsk);
 }
 
+static void handle_pending_softirqs(u32 pending, int cpu, int need_rcu_bh_qs)
+{
+	struct softirq_action *h = softirq_vec;
+	unsigned int prev_count = preempt_count();
+
+	local_irq_enable();
+	for ( ; pending; h++, pending >>= 1) {
+		unsigned int vec_nr = h - softirq_vec;
+
+		if (!(pending & 1))
+			continue;
+
+		kstat_incr_softirqs_this_cpu(vec_nr);
+		trace_softirq_entry(vec_nr);
+		h->action(h);
+		trace_softirq_exit(vec_nr);
+		if (unlikely(prev_count != preempt_count())) {
+			printk(KERN_ERR
+ "huh, entered softirq %u %s %p with preempt_count %08x exited with %08x?\n",
+			       vec_nr, softirq_to_name[vec_nr], h->action,
+			       prev_count, (unsigned int) preempt_count());
+			preempt_count() = prev_count;
+		}
+		if (need_rcu_bh_qs)
+			rcu_bh_qs(cpu);
+	}
+	local_irq_disable();
+}
+
+#ifndef CONFIG_PREEMPT_RT_FULL
 /*
  * preempt_count and SOFTIRQ_OFFSET usage:
  * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving
@@ -209,9 +302,46 @@
 #define MAX_SOFTIRQ_TIME  msecs_to_jiffies(2)
 #define MAX_SOFTIRQ_RESTART 10
 
+#ifdef CONFIG_TRACE_IRQFLAGS
+/*
+ * Convoluted means of passing __do_softirq() a message through the various
+ * architecture execute_on_stack() bits.
+ *
+ * When we run softirqs from irq_exit() and thus on the hardirq stack we need
+ * to keep the lockdep irq context tracking as tight as possible in order to
+ * not miss-qualify lock contexts and miss possible deadlocks.
+ */
+static DEFINE_PER_CPU(int, softirq_from_hardirq);
+
+static inline void lockdep_softirq_from_hardirq(void)
+{
+	this_cpu_write(softirq_from_hardirq, 1);
+}
+
+static inline void lockdep_softirq_start(void)
+{
+	if (this_cpu_read(softirq_from_hardirq))
+		trace_hardirq_exit();
+	lockdep_softirq_enter();
+}
+
+static inline void lockdep_softirq_end(void)
+{
+	lockdep_softirq_exit();
+	if (this_cpu_read(softirq_from_hardirq)) {
+		this_cpu_write(softirq_from_hardirq, 0);
+		trace_hardirq_enter();
+	}
+}
+
+#else
+static inline void lockdep_softirq_from_hardirq(void) { }
+static inline void lockdep_softirq_start(void) { }
+static inline void lockdep_softirq_end(void) { }
+#endif
+
 asmlinkage void __do_softirq(void)
 {
-	struct softirq_action *h;
 	__u32 pending;
 	unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
 	int cpu;
@@ -221,44 +351,15 @@
 	account_system_vtime(current);
 
 	__local_bh_disable((unsigned long)__builtin_return_address(0),
-				SOFTIRQ_OFFSET);
-	lockdep_softirq_enter();
+			   SOFTIRQ_OFFSET);
+	lockdep_softirq_start();
 
 	cpu = smp_processor_id();
 restart:
 	/* Reset the pending bitmask before enabling irqs */
 	set_softirq_pending(0);
 
-	local_irq_enable();
-
-	h = softirq_vec;
-
-	do {
-		if (pending & 1) {
-			unsigned int vec_nr = h - softirq_vec;
-			int prev_count = preempt_count();
-
-			kstat_incr_softirqs_this_cpu(vec_nr);
-
-			trace_softirq_entry(vec_nr);
-			h->action(h);
-			trace_softirq_exit(vec_nr);
-			if (unlikely(prev_count != preempt_count())) {
-				printk(KERN_ERR "huh, entered softirq %u %s %p"
-				       "with preempt_count %08x,"
-				       " exited with %08x?\n", vec_nr,
-				       softirq_to_name[vec_nr], h->action,
-				       prev_count, preempt_count());
-				preempt_count() = prev_count;
-			}
-
-			rcu_bh_qs(cpu);
-		}
-		h++;
-		pending >>= 1;
-	} while (pending);
-
-	local_irq_disable();
+	handle_pending_softirqs(pending, cpu, 1);
 
 	pending = local_softirq_pending();
 	if (pending) {
@@ -269,12 +370,32 @@
 		wakeup_softirqd();
 	}
 
-	lockdep_softirq_exit();
+	lockdep_softirq_end();
 
 	account_system_vtime(current);
 	__local_bh_enable(SOFTIRQ_OFFSET);
 }
 
+/*
+ * Called with preemption disabled from run_ksoftirqd()
+ */
+static int ksoftirqd_do_softirq(int cpu)
+{
+	/*
+	 * Preempt disable stops cpu going offline.
+	 * If already offline, we'll be on wrong CPU:
+	 * don't process.
+	 */
+	if (cpu_is_offline(cpu))
+		return -1;
+
+	local_irq_disable();
+	if (local_softirq_pending())
+		__do_softirq();
+	local_irq_enable();
+	return 0;
+}
+
 #ifndef __ARCH_HAS_DO_SOFTIRQ
 
 asmlinkage void do_softirq(void)
@@ -297,6 +418,191 @@
 
 #endif
 
+static inline void local_bh_disable_nort(void) { local_bh_disable(); }
+static inline void _local_bh_enable_nort(void) { _local_bh_enable(); }
+static inline void ksoftirqd_set_sched_params(void) { }
+static inline void ksoftirqd_clr_sched_params(void) { }
+
+#else /* !PREEMPT_RT_FULL */
+
+/*
+ * On RT we serialize softirq execution with a cpu local lock
+ */
+static DEFINE_LOCAL_IRQ_LOCK(local_softirq_lock);
+static DEFINE_PER_CPU(struct task_struct *, local_softirq_runner);
+
+static void __do_softirq_common(int need_rcu_bh_qs);
+
+void __do_softirq(void)
+{
+	__do_softirq_common(0);
+}
+
+void __init softirq_early_init(void)
+{
+	local_irq_lock_init(local_softirq_lock);
+}
+
+void local_bh_disable(void)
+{
+	migrate_disable();
+	current->softirq_nestcnt++;
+}
+EXPORT_SYMBOL(local_bh_disable);
+
+void local_bh_enable(void)
+{
+	if (WARN_ON(current->softirq_nestcnt == 0))
+		return;
+
+	if ((current->softirq_nestcnt == 1) &&
+	    local_softirq_pending() &&
+	    local_trylock(local_softirq_lock)) {
+
+		local_irq_disable();
+		if (local_softirq_pending())
+			__do_softirq();
+		local_irq_enable();
+		local_unlock(local_softirq_lock);
+		WARN_ON(current->softirq_nestcnt != 1);
+	}
+	current->softirq_nestcnt--;
+	migrate_enable();
+}
+EXPORT_SYMBOL(local_bh_enable);
+
+void local_bh_enable_ip(unsigned long ip)
+{
+	local_bh_enable();
+}
+EXPORT_SYMBOL(local_bh_enable_ip);
+
+void _local_bh_enable(void)
+{
+	current->softirq_nestcnt--;
+	migrate_enable();
+}
+EXPORT_SYMBOL(_local_bh_enable);
+
+/* For tracing */
+int notrace __in_softirq(void)
+{
+	if (__get_cpu_var(local_softirq_lock).owner == current)
+		return __get_cpu_var(local_softirq_lock).nestcnt;
+	return 0;
+}
+
+int in_serving_softirq(void)
+{
+	int res;
+
+	preempt_disable();
+	res = __get_cpu_var(local_softirq_runner) == current;
+	preempt_enable();
+	return res;
+}
+EXPORT_SYMBOL(in_serving_softirq);
+
+/*
+ * Called with bh and local interrupts disabled. For full RT cpu must
+ * be pinned.
+ */
+static void __do_softirq_common(int need_rcu_bh_qs)
+{
+	u32 pending = local_softirq_pending();
+	int cpu = smp_processor_id();
+
+	current->softirq_nestcnt++;
+
+	/* Reset the pending bitmask before enabling irqs */
+	set_softirq_pending(0);
+
+	__get_cpu_var(local_softirq_runner) = current;
+
+	lockdep_softirq_enter();
+
+	handle_pending_softirqs(pending, cpu, need_rcu_bh_qs);
+
+	pending = local_softirq_pending();
+	if (pending)
+		wakeup_softirqd();
+
+	lockdep_softirq_exit();
+	__get_cpu_var(local_softirq_runner) = NULL;
+
+	current->softirq_nestcnt--;
+}
+
+static int __thread_do_softirq(int cpu)
+{
+	/*
+	 * Prevent the current cpu from going offline.
+	 * pin_current_cpu() can reenable preemption and block on the
+	 * hotplug mutex. When it returns, the current cpu is
+	 * pinned. It might be the wrong one, but the offline check
+	 * below catches that.
+	 */
+	pin_current_cpu();
+	/*
+	 * If called from ksoftirqd (cpu >= 0) we need to check
+	 * whether we are on the wrong cpu due to cpu offlining. If
+	 * called via thread_do_softirq() no action required.
+	 */
+	if (cpu >= 0 && cpu_is_offline(cpu)) {
+		unpin_current_cpu();
+		return -1;
+	}
+	preempt_enable();
+	local_lock(local_softirq_lock);
+	local_irq_disable();
+	/*
+	 * We cannot switch stacks on RT as we want to be able to
+	 * schedule!
+	 */
+	if (local_softirq_pending())
+		__do_softirq_common(cpu >= 0);
+	local_unlock(local_softirq_lock);
+	unpin_current_cpu();
+	preempt_disable();
+	local_irq_enable();
+	return 0;
+}
+
+/*
+ * Called from netif_rx_ni(). Preemption enabled.
+ */
+void thread_do_softirq(void)
+{
+	if (!in_serving_softirq()) {
+		preempt_disable();
+		__thread_do_softirq(-1);
+		preempt_enable();
+	}
+}
+
+static int ksoftirqd_do_softirq(int cpu)
+{
+	return __thread_do_softirq(cpu);
+}
+
+static inline void local_bh_disable_nort(void) { }
+static inline void _local_bh_enable_nort(void) { }
+
+static inline void ksoftirqd_set_sched_params(void)
+{
+	struct sched_param param = { .sched_priority = 1 };
+
+	sched_setscheduler(current, SCHED_FIFO, &param);
+}
+
+static inline void ksoftirqd_clr_sched_params(void)
+{
+	struct sched_param param = { .sched_priority = 0 };
+
+	sched_setscheduler(current, SCHED_NORMAL, &param);
+}
+
+#endif /* PREEMPT_RT_FULL */
 /*
  * Enter an interrupt context.
  */
@@ -310,9 +616,9 @@
 		 * Prevent raise_softirq from needlessly waking up ksoftirqd
 		 * here, as softirq will be serviced on return from interrupt.
 		 */
-		local_bh_disable();
+		local_bh_disable_nort();
 		tick_check_idle(cpu);
-		_local_bh_enable();
+		_local_bh_enable_nort();
 	}
 
 	__irq_enter();
@@ -321,26 +627,36 @@
 #ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED
 static inline void invoke_softirq(void)
 {
-	if (!force_irqthreads)
+#ifndef CONFIG_PREEMPT_RT_FULL
+	if (!force_irqthreads) {
+		lockdep_softirq_from_hardirq();
 		__do_softirq();
-	else {
+	} else {
 		__local_bh_disable((unsigned long)__builtin_return_address(0),
 				SOFTIRQ_OFFSET);
 		wakeup_softirqd();
 		__local_bh_enable(SOFTIRQ_OFFSET);
 	}
+#else
+	wakeup_softirqd();
+#endif
 }
 #else
 static inline void invoke_softirq(void)
 {
-	if (!force_irqthreads)
+#ifndef CONFIG_PREEMPT_RT_FULL
+	if (!force_irqthreads) {
+		lockdep_softirq_from_hardirq();
 		do_softirq();
-	else {
+	} else {
 		__local_bh_disable((unsigned long)__builtin_return_address(0),
 				SOFTIRQ_OFFSET);
 		wakeup_softirqd();
 		__local_bh_enable(SOFTIRQ_OFFSET);
 	}
+#else
+	wakeup_softirqd();
+#endif
 }
 #endif
 
@@ -350,7 +666,6 @@
 void irq_exit(void)
 {
 	account_system_vtime(current);
-	trace_hardirq_exit();
 	sub_preempt_count(IRQ_EXIT_OFFSET);
 	if (!in_interrupt() && local_softirq_pending())
 		invoke_softirq();
@@ -361,7 +676,8 @@
 	if (idle_cpu(smp_processor_id()) && !in_interrupt() && !need_resched())
 		tick_nohz_stop_sched_tick(0);
 #endif
-	preempt_enable_no_resched();
+	trace_hardirq_exit(); /* must be last! */
+	__preempt_enable_no_resched();
 }
 
 /*
@@ -410,15 +726,45 @@
 static DEFINE_PER_CPU(struct tasklet_head, tasklet_vec);
 static DEFINE_PER_CPU(struct tasklet_head, tasklet_hi_vec);
 
+static void inline
+__tasklet_common_schedule(struct tasklet_struct *t, struct tasklet_head *head, unsigned int nr)
+{
+	if (tasklet_trylock(t)) {
+again:
+		/* We may have been preempted before tasklet_trylock
+		 * and __tasklet_action may have already run.
+		 * So double check the sched bit while the takslet
+		 * is locked before adding it to the list.
+		 */
+		if (test_bit(TASKLET_STATE_SCHED, &t->state)) {
+			t->next = NULL;
+			*head->tail = t;
+			head->tail = &(t->next);
+			raise_softirq_irqoff(nr);
+			tasklet_unlock(t);
+		} else {
+			/* This is subtle. If we hit the corner case above
+			 * It is possible that we get preempted right here,
+			 * and another task has successfully called
+			 * tasklet_schedule(), then this function, and
+			 * failed on the trylock. Thus we must be sure
+			 * before releasing the tasklet lock, that the
+			 * SCHED_BIT is clear. Otherwise the tasklet
+			 * may get its SCHED_BIT set, but not added to the
+			 * list
+			 */
+			if (!tasklet_tryunlock(t))
+				goto again;
+		}
+	}
+}
+
 void __tasklet_schedule(struct tasklet_struct *t)
 {
 	unsigned long flags;
 
 	local_irq_save(flags);
-	t->next = NULL;
-	*__this_cpu_read(tasklet_vec.tail) = t;
-	__this_cpu_write(tasklet_vec.tail, &(t->next));
-	raise_softirq_irqoff(TASKLET_SOFTIRQ);
+	__tasklet_common_schedule(t, &__get_cpu_var(tasklet_vec), TASKLET_SOFTIRQ);
 	local_irq_restore(flags);
 }
 
@@ -429,10 +775,7 @@
 	unsigned long flags;
 
 	local_irq_save(flags);
-	t->next = NULL;
-	*__this_cpu_read(tasklet_hi_vec.tail) = t;
-	__this_cpu_write(tasklet_hi_vec.tail,  &(t->next));
-	raise_softirq_irqoff(HI_SOFTIRQ);
+	__tasklet_common_schedule(t, &__get_cpu_var(tasklet_hi_vec), HI_SOFTIRQ);
 	local_irq_restore(flags);
 }
 
@@ -440,50 +783,119 @@
 
 void __tasklet_hi_schedule_first(struct tasklet_struct *t)
 {
-	BUG_ON(!irqs_disabled());
-
-	t->next = __this_cpu_read(tasklet_hi_vec.head);
-	__this_cpu_write(tasklet_hi_vec.head, t);
-	__raise_softirq_irqoff(HI_SOFTIRQ);
+	__tasklet_hi_schedule(t);
 }
 
 EXPORT_SYMBOL(__tasklet_hi_schedule_first);
 
-static void tasklet_action(struct softirq_action *a)
+void  tasklet_enable(struct tasklet_struct *t)
 {
-	struct tasklet_struct *list;
+	if (!atomic_dec_and_test(&t->count))
+		return;
+	if (test_and_clear_bit(TASKLET_STATE_PENDING, &t->state))
+		tasklet_schedule(t);
+}
 
-	local_irq_disable();
-	list = __this_cpu_read(tasklet_vec.head);
-	__this_cpu_write(tasklet_vec.head, NULL);
-	__this_cpu_write(tasklet_vec.tail, &__get_cpu_var(tasklet_vec).head);
-	local_irq_enable();
+EXPORT_SYMBOL(tasklet_enable);
+
+void  tasklet_hi_enable(struct tasklet_struct *t)
+{
+	if (!atomic_dec_and_test(&t->count))
+		return;
+	if (test_and_clear_bit(TASKLET_STATE_PENDING, &t->state))
+		tasklet_hi_schedule(t);
+}
+
+EXPORT_SYMBOL(tasklet_hi_enable);
+
+static void
+__tasklet_action(struct softirq_action *a, struct tasklet_struct *list)
+{
+	int loops = 1000000;
 
 	while (list) {
 		struct tasklet_struct *t = list;
 
 		list = list->next;
 
-		if (tasklet_trylock(t)) {
-			if (!atomic_read(&t->count)) {
-				if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state))
-					BUG();
-				t->func(t->data);
-				tasklet_unlock(t);
-				continue;
-			}
-			tasklet_unlock(t);
+		/*
+		 * Should always succeed - after a tasklist got on the
+		 * list (after getting the SCHED bit set from 0 to 1),
+		 * nothing but the tasklet softirq it got queued to can
+		 * lock it:
+		 */
+		if (!tasklet_trylock(t)) {
+			WARN_ON(1);
+			continue;
 		}
 
-		local_irq_disable();
 		t->next = NULL;
-		*__this_cpu_read(tasklet_vec.tail) = t;
-		__this_cpu_write(tasklet_vec.tail, &(t->next));
-		__raise_softirq_irqoff(TASKLET_SOFTIRQ);
-		local_irq_enable();
+
+		/*
+		 * If we cannot handle the tasklet because it's disabled,
+		 * mark it as pending. tasklet_enable() will later
+		 * re-schedule the tasklet.
+		 */
+		if (unlikely(atomic_read(&t->count))) {
+out_disabled:
+			/* implicit unlock: */
+			wmb();
+			t->state = TASKLET_STATEF_PENDING;
+			continue;
+		}
+
+		/*
+		 * After this point on the tasklet might be rescheduled
+		 * on another CPU, but it can only be added to another
+		 * CPU's tasklet list if we unlock the tasklet (which we
+		 * dont do yet).
+		 */
+		if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state))
+			WARN_ON(1);
+
+again:
+		t->func(t->data);
+
+		/*
+		 * Try to unlock the tasklet. We must use cmpxchg, because
+		 * another CPU might have scheduled or disabled the tasklet.
+		 * We only allow the STATE_RUN -> 0 transition here.
+		 */
+		while (!tasklet_tryunlock(t)) {
+			/*
+			 * If it got disabled meanwhile, bail out:
+			 */
+			if (atomic_read(&t->count))
+				goto out_disabled;
+			/*
+			 * If it got scheduled meanwhile, re-execute
+			 * the tasklet function:
+			 */
+			if (test_and_clear_bit(TASKLET_STATE_SCHED, &t->state))
+				goto again;
+			if (!--loops) {
+				printk("hm, tasklet state: %08lx\n", t->state);
+				WARN_ON(1);
+				tasklet_unlock(t);
+				break;
+			}
+		}
 	}
 }
 
+static void tasklet_action(struct softirq_action *a)
+{
+	struct tasklet_struct *list;
+
+	local_irq_disable();
+	list = __get_cpu_var(tasklet_vec).head;
+	__get_cpu_var(tasklet_vec).head = NULL;
+	__get_cpu_var(tasklet_vec).tail = &__get_cpu_var(tasklet_vec).head;
+	local_irq_enable();
+
+	__tasklet_action(a, list);
+}
+
 static void tasklet_hi_action(struct softirq_action *a)
 {
 	struct tasklet_struct *list;
@@ -494,29 +906,7 @@
 	__this_cpu_write(tasklet_hi_vec.tail, &__get_cpu_var(tasklet_hi_vec).head);
 	local_irq_enable();
 
-	while (list) {
-		struct tasklet_struct *t = list;
-
-		list = list->next;
-
-		if (tasklet_trylock(t)) {
-			if (!atomic_read(&t->count)) {
-				if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state))
-					BUG();
-				t->func(t->data);
-				tasklet_unlock(t);
-				continue;
-			}
-			tasklet_unlock(t);
-		}
-
-		local_irq_disable();
-		t->next = NULL;
-		*__this_cpu_read(tasklet_hi_vec.tail) = t;
-		__this_cpu_write(tasklet_hi_vec.tail, &(t->next));
-		__raise_softirq_irqoff(HI_SOFTIRQ);
-		local_irq_enable();
-	}
+	__tasklet_action(a, list);
 }
 
 
@@ -539,7 +929,7 @@
 
 	while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) {
 		do {
-			yield();
+			msleep(1);
 		} while (test_bit(TASKLET_STATE_SCHED, &t->state));
 	}
 	tasklet_unlock_wait(t);
@@ -745,31 +1135,40 @@
 	open_softirq(HI_SOFTIRQ, tasklet_hi_action);
 }
 
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL)
+void tasklet_unlock_wait(struct tasklet_struct *t)
+{
+	while (test_bit(TASKLET_STATE_RUN, &(t)->state)) {
+		/*
+		 * Hack for now to avoid this busy-loop:
+		 */
+#ifdef CONFIG_PREEMPT_RT_FULL
+		msleep(1);
+#else
+		barrier();
+#endif
+	}
+}
+EXPORT_SYMBOL(tasklet_unlock_wait);
+#endif
+
 static int run_ksoftirqd(void * __bind_cpu)
 {
+	ksoftirqd_set_sched_params();
+
 	set_current_state(TASK_INTERRUPTIBLE);
 
 	while (!kthread_should_stop()) {
 		preempt_disable();
-		if (!local_softirq_pending()) {
-			preempt_enable_no_resched();
-			schedule();
-			preempt_disable();
-		}
+		if (!local_softirq_pending())
+			schedule_preempt_disabled();
 
 		__set_current_state(TASK_RUNNING);
 
 		while (local_softirq_pending()) {
-			/* Preempt disable stops cpu going offline.
-			   If already offline, we'll be on wrong CPU:
-			   don't process */
-			if (cpu_is_offline((long)__bind_cpu))
+			if (ksoftirqd_do_softirq((long) __bind_cpu))
 				goto wait_to_die;
-			local_irq_disable();
-			if (local_softirq_pending())
-				__do_softirq();
-			local_irq_enable();
-			preempt_enable_no_resched();
+			__preempt_enable_no_resched();
 			cond_resched();
 			preempt_disable();
 			rcu_note_context_switch((long)__bind_cpu);
@@ -782,6 +1181,7 @@
 
 wait_to_die:
 	preempt_enable();
+	ksoftirqd_clr_sched_params();
 	/* Wait for kthread_stop */
 	set_current_state(TASK_INTERRUPTIBLE);
 	while (!kthread_should_stop()) {
@@ -858,9 +1258,8 @@
 	int hotcpu = (unsigned long)hcpu;
 	struct task_struct *p;
 
-	switch (action) {
+	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
 		p = kthread_create_on_node(run_ksoftirqd,
 					   hcpu,
 					   cpu_to_node(hotcpu),
@@ -873,19 +1272,16 @@
   		per_cpu(ksoftirqd, hotcpu) = p;
  		break;
 	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
 		wake_up_process(per_cpu(ksoftirqd, hotcpu));
 		break;
 #ifdef CONFIG_HOTPLUG_CPU
 	case CPU_UP_CANCELED:
-	case CPU_UP_CANCELED_FROZEN:
 		if (!per_cpu(ksoftirqd, hotcpu))
 			break;
 		/* Unbind so it can run.  Fall thru. */
 		kthread_bind(per_cpu(ksoftirqd, hotcpu),
 			     cpumask_any(cpu_online_mask));
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN: {
+	case CPU_POST_DEAD: {
 		static const struct sched_param param = {
 			.sched_priority = MAX_RT_PRIO-1
 		};
diff --git a/kernel/spinlock.c b/kernel/spinlock.c
index 84c7d96..47fd3cf 100644
--- a/kernel/spinlock.c
+++ b/kernel/spinlock.c
@@ -110,8 +110,11 @@
  *         __[spin|read|write]_lock_bh()
  */
 BUILD_LOCK_OPS(spin, raw_spinlock);
+
+#ifndef CONFIG_PREEMPT_RT_FULL
 BUILD_LOCK_OPS(read, rwlock);
 BUILD_LOCK_OPS(write, rwlock);
+#endif
 
 #endif
 
@@ -195,6 +198,8 @@
 EXPORT_SYMBOL(_raw_spin_unlock_bh);
 #endif
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+
 #ifndef CONFIG_INLINE_READ_TRYLOCK
 int __lockfunc _raw_read_trylock(rwlock_t *lock)
 {
@@ -339,6 +344,8 @@
 EXPORT_SYMBOL(_raw_write_unlock_bh);
 #endif
 
+#endif /* !PREEMPT_RT_FULL */
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
 void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass)
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 2f194e9..e98c70b 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -29,12 +29,12 @@
 	atomic_t		nr_todo;	/* nr left to execute */
 	bool			executed;	/* actually executed? */
 	int			ret;		/* collected return value */
-	struct completion	completion;	/* fired if nr_todo reaches 0 */
+	struct task_struct	*waiter;	/* woken when nr_todo reaches 0 */
 };
 
 /* the actual stopper, one per every possible cpu, enabled on online cpus */
 struct cpu_stopper {
-	spinlock_t		lock;
+	raw_spinlock_t		lock;
 	bool			enabled;	/* is this stopper enabled? */
 	struct list_head	works;		/* list of pending works */
 	struct task_struct	*thread;	/* stopper thread */
@@ -47,7 +47,7 @@
 {
 	memset(done, 0, sizeof(*done));
 	atomic_set(&done->nr_todo, nr_todo);
-	init_completion(&done->completion);
+	done->waiter = current;
 }
 
 /* signal completion unless @done is NULL */
@@ -56,8 +56,10 @@
 	if (done) {
 		if (executed)
 			done->executed = true;
-		if (atomic_dec_and_test(&done->nr_todo))
-			complete(&done->completion);
+		if (atomic_dec_and_test(&done->nr_todo)) {
+			wake_up_process(done->waiter);
+			done->waiter = NULL;
+		}
 	}
 }
 
@@ -67,7 +69,7 @@
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&stopper->lock, flags);
+	raw_spin_lock_irqsave(&stopper->lock, flags);
 
 	if (stopper->enabled) {
 		list_add_tail(&work->list, &stopper->works);
@@ -75,7 +77,23 @@
 	} else
 		cpu_stop_signal_done(work->done, false);
 
-	spin_unlock_irqrestore(&stopper->lock, flags);
+	raw_spin_unlock_irqrestore(&stopper->lock, flags);
+}
+
+static void wait_for_stop_done(struct cpu_stop_done *done)
+{
+	set_current_state(TASK_UNINTERRUPTIBLE);
+	while (atomic_read(&done->nr_todo)) {
+		schedule();
+		set_current_state(TASK_UNINTERRUPTIBLE);
+	}
+	/*
+	 * We need to wait until cpu_stop_signal_done() has cleared
+	 * done->waiter.
+	 */
+	while (done->waiter)
+		cpu_relax();
+	set_current_state(TASK_RUNNING);
 }
 
 /**
@@ -109,7 +127,7 @@
 
 	cpu_stop_init_done(&done, 1);
 	cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu), &work);
-	wait_for_completion(&done.completion);
+	wait_for_stop_done(&done);
 	return done.executed ? done.ret : -ENOENT;
 }
 
@@ -135,11 +153,12 @@
 
 /* static data for stop_cpus */
 static DEFINE_MUTEX(stop_cpus_mutex);
+static DEFINE_MUTEX(stopper_lock);
 static DEFINE_PER_CPU(struct cpu_stop_work, stop_cpus_work);
 
 static void queue_stop_cpus_work(const struct cpumask *cpumask,
 				 cpu_stop_fn_t fn, void *arg,
-				 struct cpu_stop_done *done)
+				 struct cpu_stop_done *done, bool inactive)
 {
 	struct cpu_stop_work *work;
 	unsigned int cpu;
@@ -153,15 +172,19 @@
 	}
 
 	/*
-	 * Disable preemption while queueing to avoid getting
-	 * preempted by a stopper which might wait for other stoppers
-	 * to enter @fn which can lead to deadlock.
+	 * Make sure that all work is queued on all cpus before we
+	 * any of the cpus can execute it.
 	 */
-	preempt_disable();
+	if (!inactive) {
+		mutex_lock(&stopper_lock);
+	} else {
+		while (!mutex_trylock(&stopper_lock))
+			cpu_relax();
+	}
 	for_each_cpu(cpu, cpumask)
 		cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu),
 				    &per_cpu(stop_cpus_work, cpu));
-	preempt_enable();
+	mutex_unlock(&stopper_lock);
 }
 
 static int __stop_cpus(const struct cpumask *cpumask,
@@ -170,8 +193,8 @@
 	struct cpu_stop_done done;
 
 	cpu_stop_init_done(&done, cpumask_weight(cpumask));
-	queue_stop_cpus_work(cpumask, fn, arg, &done);
-	wait_for_completion(&done.completion);
+	queue_stop_cpus_work(cpumask, fn, arg, &done, false);
+	wait_for_stop_done(&done);
 	return done.executed ? done.ret : -ENOENT;
 }
 
@@ -259,13 +282,13 @@
 	}
 
 	work = NULL;
-	spin_lock_irq(&stopper->lock);
+	raw_spin_lock_irq(&stopper->lock);
 	if (!list_empty(&stopper->works)) {
 		work = list_first_entry(&stopper->works,
 					struct cpu_stop_work, list);
 		list_del_init(&work->list);
 	}
-	spin_unlock_irq(&stopper->lock);
+	raw_spin_unlock_irq(&stopper->lock);
 
 	if (work) {
 		cpu_stop_fn_t fn = work->fn;
@@ -275,6 +298,16 @@
 
 		__set_current_state(TASK_RUNNING);
 
+		/*
+		 * Wait until the stopper finished scheduling on all
+		 * cpus
+		 */
+		mutex_lock(&stopper_lock);
+		/*
+		 * Let other cpu threads continue as well
+		 */
+		mutex_unlock(&stopper_lock);
+
 		/* cpu stop callbacks are not allowed to sleep */
 		preempt_disable();
 
@@ -289,7 +322,13 @@
 			  kallsyms_lookup((unsigned long)fn, NULL, NULL, NULL,
 					  ksym_buf), arg);
 
+		/*
+		 * Make sure that the wakeup and setting done->waiter
+		 * to NULL is atomic.
+		 */
+		local_irq_disable();
 		cpu_stop_signal_done(done, true);
+		local_irq_enable();
 	} else
 		schedule();
 
@@ -317,6 +356,7 @@
 		if (IS_ERR(p))
 			return notifier_from_errno(PTR_ERR(p));
 		get_task_struct(p);
+		p->flags |= PF_STOMPER;
 		kthread_bind(p, cpu);
 		sched_set_stop_task(cpu, p);
 		stopper->thread = p;
@@ -326,9 +366,9 @@
 		/* strictly unnecessary, as first user will wake it */
 		wake_up_process(stopper->thread);
 		/* mark enabled */
-		spin_lock_irq(&stopper->lock);
+		raw_spin_lock_irq(&stopper->lock);
 		stopper->enabled = true;
-		spin_unlock_irq(&stopper->lock);
+		raw_spin_unlock_irq(&stopper->lock);
 		break;
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -341,11 +381,11 @@
 		/* kill the stopper */
 		kthread_stop(stopper->thread);
 		/* drain remaining works */
-		spin_lock_irq(&stopper->lock);
+		raw_spin_lock_irq(&stopper->lock);
 		list_for_each_entry(work, &stopper->works, list)
 			cpu_stop_signal_done(work->done, false);
 		stopper->enabled = false;
-		spin_unlock_irq(&stopper->lock);
+		raw_spin_unlock_irq(&stopper->lock);
 		/* release the stopper */
 		put_task_struct(stopper->thread);
 		stopper->thread = NULL;
@@ -376,7 +416,7 @@
 	for_each_possible_cpu(cpu) {
 		struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
 
-		spin_lock_init(&stopper->lock);
+		raw_spin_lock_init(&stopper->lock);
 		INIT_LIST_HEAD(&stopper->works);
 	}
 
@@ -566,11 +606,11 @@
 	set_state(&smdata, STOPMACHINE_PREPARE);
 	cpu_stop_init_done(&done, num_active_cpus());
 	queue_stop_cpus_work(cpu_active_mask, stop_machine_cpu_stop, &smdata,
-			     &done);
+			     &done, true);
 	ret = stop_machine_cpu_stop(&smdata);
 
 	/* Busy wait for completion. */
-	while (!completion_done(&done.completion))
+	while (atomic_read(&done.nr_todo))
 		cpu_relax();
 
 	mutex_unlock(&stop_cpus_mutex);
diff --git a/kernel/time.c b/kernel/time.c
index f64e88b..0864d70 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -163,7 +163,6 @@
 		return error;
 
 	if (tz) {
-		/* SMP safe, global irq locking makes it work. */
 		sys_tz = *tz;
 		update_vsyscall_tz();
 		if (firsttime) {
@@ -173,12 +172,7 @@
 		}
 	}
 	if (tv)
-	{
-		/* SMP safe, again the code in arch/foo/time.c should
-		 * globally block out interrupts when it runs.
-		 */
 		return do_settimeofday(tv);
-	}
 	return 0;
 }
 
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 955560e..c84f1ce 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -80,9 +80,9 @@
 	u64 ret;
 
 	do {
-		seq = read_seqbegin(&xtime_lock);
+		seq = read_seqcount_begin(&xtime_seq);
 		ret = jiffies_64;
-	} while (read_seqretry(&xtime_lock, seq));
+	} while (read_seqcount_retry(&xtime_seq, seq));
 	return ret;
 }
 EXPORT_SYMBOL(get_jiffies_64);
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 34fd01e..fa8fc3c 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -10,6 +10,7 @@
 #include <linux/workqueue.h>
 #include <linux/hrtimer.h>
 #include <linux/jiffies.h>
+#include <linux/kthread.h>
 #include <linux/math64.h>
 #include <linux/timex.h>
 #include <linux/time.h>
@@ -402,7 +403,6 @@
 		break;
 	}
 
-
 	/* Bump the maxerror field */
 	time_maxerror += MAXFREQ / NSEC_PER_USEC;
 	if (time_maxerror > NTP_PHASE_LIMIT) {
@@ -491,11 +491,52 @@
 	schedule_delayed_work(&sync_cmos_work, timespec_to_jiffies(&next));
 }
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+/*
+ * RT can not call schedule_delayed_work from real interrupt context.
+ * Need to make a thread to do the real work.
+ */
+static struct task_struct *cmos_delay_thread;
+static bool do_cmos_delay;
+
+static int run_cmos_delay(void *ignore)
+{
+	while (!kthread_should_stop()) {
+		set_current_state(TASK_INTERRUPTIBLE);
+		if (do_cmos_delay) {
+			do_cmos_delay = false;
+			schedule_delayed_work(&sync_cmos_work, 0);
+		}
+		schedule();
+	}
+	__set_current_state(TASK_RUNNING);
+	return 0;
+}
+
+static void notify_cmos_timer(void)
+{
+	if (!no_sync_cmos_clock) {
+		do_cmos_delay = true;
+		/* Make visible before waking up process */
+		smp_wmb();
+		wake_up_process(cmos_delay_thread);
+	}
+}
+
+static __init int create_cmos_delay_thread(void)
+{
+	cmos_delay_thread = kthread_run(run_cmos_delay, NULL, "kcmosdelayd");
+	BUG_ON(!cmos_delay_thread);
+	return 0;
+}
+early_initcall(create_cmos_delay_thread);
+#else
 static void notify_cmos_timer(void)
 {
 	if (!no_sync_cmos_clock)
 		schedule_delayed_work(&sync_cmos_work, 0);
 }
+#endif /* CONFIG_PREEMPT_RT_FULL */
 
 #else
 static inline void notify_cmos_timer(void) { }
@@ -634,7 +675,8 @@
 
 	getnstimeofday(&ts);
 
-	write_seqlock_irq(&xtime_lock);
+	raw_spin_lock_irq(&xtime_lock);
+	write_seqcount_begin(&xtime_seq);
 
 	if (txc->modes & ADJ_ADJTIME) {
 		long save_adjust = time_adjust;
@@ -676,7 +718,8 @@
 	/* fill PPS status fields */
 	pps_fill_timex(txc);
 
-	write_sequnlock_irq(&xtime_lock);
+	write_seqcount_end(&xtime_seq);
+	raw_spin_unlock_irq(&xtime_lock);
 
 	txc->time.tv_sec = ts.tv_sec;
 	txc->time.tv_usec = ts.tv_nsec;
@@ -874,7 +917,8 @@
 
 	pts_norm = pps_normalize_ts(*phase_ts);
 
-	write_seqlock_irqsave(&xtime_lock, flags);
+	raw_spin_lock_irqsave(&xtime_lock, flags);
+	write_seqcount_begin(&xtime_seq);
 
 	/* clear the error bits, they will be set again if needed */
 	time_status &= ~(STA_PPSJITTER | STA_PPSWANDER | STA_PPSERROR);
@@ -887,7 +931,8 @@
 	 * just start the frequency interval */
 	if (unlikely(pps_fbase.tv_sec == 0)) {
 		pps_fbase = *raw_ts;
-		write_sequnlock_irqrestore(&xtime_lock, flags);
+		write_seqcount_end(&xtime_seq);
+		raw_spin_unlock_irqrestore(&xtime_lock, flags);
 		return;
 	}
 
@@ -902,7 +947,8 @@
 		time_status |= STA_PPSJITTER;
 		/* restart the frequency calibration interval */
 		pps_fbase = *raw_ts;
-		write_sequnlock_irqrestore(&xtime_lock, flags);
+		write_seqcount_end(&xtime_seq);
+		raw_spin_unlock_irqrestore(&xtime_lock, flags);
 		pr_err("hardpps: PPSJITTER: bad pulse\n");
 		return;
 	}
@@ -919,7 +965,8 @@
 
 	hardpps_update_phase(pts_norm.nsec);
 
-	write_sequnlock_irqrestore(&xtime_lock, flags);
+	write_seqcount_end(&xtime_seq);
+	raw_spin_unlock_irqrestore(&xtime_lock, flags);
 }
 EXPORT_SYMBOL(hardpps);
 
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index ead79bc..538d45a 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -63,13 +63,15 @@
 static void tick_periodic(int cpu)
 {
 	if (tick_do_timer_cpu == cpu) {
-		write_seqlock(&xtime_lock);
+		raw_spin_lock(&xtime_lock);
+		write_seqcount_begin(&xtime_seq);
 
 		/* Keep track of the next tick event */
 		tick_next_period = ktime_add(tick_next_period, tick_period);
 
 		do_timer(1);
-		write_sequnlock(&xtime_lock);
+		write_seqcount_end(&xtime_seq);
+		raw_spin_unlock(&xtime_lock);
 	}
 
 	update_process_times(user_mode(get_irq_regs()));
@@ -130,9 +132,9 @@
 		ktime_t next;
 
 		do {
-			seq = read_seqbegin(&xtime_lock);
+			seq = read_seqcount_begin(&xtime_seq);
 			next = tick_next_period;
-		} while (read_seqretry(&xtime_lock, seq));
+		} while (read_seqcount_retry(&xtime_seq, seq));
 
 		clockevents_set_mode(dev, CLOCK_EVT_MODE_ONESHOT);
 
diff --git a/kernel/time/tick-internal.h b/kernel/time/tick-internal.h
index 4e265b90..c91100d 100644
--- a/kernel/time/tick-internal.h
+++ b/kernel/time/tick-internal.h
@@ -141,4 +141,5 @@
 #endif
 
 extern void do_timer(unsigned long ticks);
-extern seqlock_t xtime_lock;
+extern raw_spinlock_t xtime_lock;
+extern seqcount_t xtime_seq;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 2695d72..9d1d982 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -56,7 +56,8 @@
 		return;
 
 	/* Reevalute with xtime_lock held */
-	write_seqlock(&xtime_lock);
+	raw_spin_lock(&xtime_lock);
+	write_seqcount_begin(&xtime_seq);
 
 	delta = ktime_sub(now, last_jiffies_update);
 	if (delta.tv64 >= tick_period.tv64) {
@@ -79,7 +80,8 @@
 		/* Keep the tick_next_period variable up to date */
 		tick_next_period = ktime_add(last_jiffies_update, tick_period);
 	}
-	write_sequnlock(&xtime_lock);
+	write_seqcount_end(&xtime_seq);
+	raw_spin_unlock(&xtime_lock);
 }
 
 /*
@@ -89,12 +91,14 @@
 {
 	ktime_t period;
 
-	write_seqlock(&xtime_lock);
+	raw_spin_lock(&xtime_lock);
+	write_seqcount_begin(&xtime_seq);
 	/* Did we start the jiffies update yet ? */
 	if (last_jiffies_update.tv64 == 0)
 		last_jiffies_update = tick_next_period;
 	period = last_jiffies_update;
-	write_sequnlock(&xtime_lock);
+	write_seqcount_end(&xtime_seq);
+	raw_spin_unlock(&xtime_lock);
 	return period;
 }
 
@@ -334,24 +338,18 @@
 		goto end;
 
 	if (unlikely(local_softirq_pending() && cpu_online(cpu))) {
-		static int ratelimit;
-
-		if (ratelimit < 10) {
-			printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
-			       (unsigned int) local_softirq_pending());
-			ratelimit++;
-		}
+		softirq_check_pending_idle();
 		goto end;
 	}
 
 	ts->idle_calls++;
 	/* Read jiffies and the time when jiffies were updated last */
 	do {
-		seq = read_seqbegin(&xtime_lock);
+		seq = read_seqcount_begin(&xtime_seq);
 		last_update = last_jiffies_update;
 		last_jiffies = jiffies;
 		time_delta = timekeeping_max_deferment();
-	} while (read_seqretry(&xtime_lock, seq));
+	} while (read_seqcount_retry(&xtime_seq, seq));
 
 	if (rcu_needs_cpu(cpu) || printk_needs_cpu(cpu) ||
 	    arch_needs_cpu(cpu)) {
@@ -803,6 +801,7 @@
 	 * Emulate tick processing via per-CPU hrtimers:
 	 */
 	hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+	ts->sched_timer.irqsafe = 1;
 	ts->sched_timer.function = tick_sched_timer;
 
 	/* Get the next period (per cpu) */
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 068c092..0d8f0ed 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -139,8 +139,8 @@
  * This read-write spinlock protects us from races in SMP while
  * playing with xtime.
  */
-__cacheline_aligned_in_smp DEFINE_SEQLOCK(xtime_lock);
-
+__cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(xtime_lock);
+seqcount_t xtime_seq;
 
 /*
  * The current time
@@ -242,7 +242,7 @@
 	WARN_ON(timekeeping_suspended);
 
 	do {
-		seq = read_seqbegin(&xtime_lock);
+		seq = read_seqcount_begin(&xtime_seq);
 
 		*ts = xtime;
 		nsecs = timekeeping_get_ns();
@@ -250,7 +250,7 @@
 		/* If arch requires, add in gettimeoffset() */
 		nsecs += arch_gettimeoffset();
 
-	} while (read_seqretry(&xtime_lock, seq));
+	} while (read_seqcount_retry(&xtime_seq, seq));
 
 	timespec_add_ns(ts, nsecs);
 }
@@ -265,14 +265,14 @@
 	WARN_ON(timekeeping_suspended);
 
 	do {
-		seq = read_seqbegin(&xtime_lock);
+		seq = read_seqcount_begin(&xtime_seq);
 		secs = xtime.tv_sec + wall_to_monotonic.tv_sec;
 		nsecs = xtime.tv_nsec + wall_to_monotonic.tv_nsec;
 		nsecs += timekeeping_get_ns();
 		/* If arch requires, add in gettimeoffset() */
 		nsecs += arch_gettimeoffset();
 
-	} while (read_seqretry(&xtime_lock, seq));
+	} while (read_seqcount_retry(&xtime_seq, seq));
 	/*
 	 * Use ktime_set/ktime_add_ns to create a proper ktime on
 	 * 32-bit architectures without CONFIG_KTIME_SCALAR.
@@ -298,14 +298,14 @@
 	WARN_ON(timekeeping_suspended);
 
 	do {
-		seq = read_seqbegin(&xtime_lock);
+		seq = read_seqcount_begin(&xtime_seq);
 		*ts = xtime;
 		tomono = wall_to_monotonic;
 		nsecs = timekeeping_get_ns();
 		/* If arch requires, add in gettimeoffset() */
 		nsecs += arch_gettimeoffset();
 
-	} while (read_seqretry(&xtime_lock, seq));
+	} while (read_seqcount_retry(&xtime_seq, seq));
 
 	set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec,
 				ts->tv_nsec + tomono.tv_nsec + nsecs);
@@ -333,7 +333,7 @@
 	do {
 		u32 arch_offset;
 
-		seq = read_seqbegin(&xtime_lock);
+		seq = read_seqcount_begin(&xtime_seq);
 
 		*ts_raw = raw_time;
 		*ts_real = xtime;
@@ -346,7 +346,7 @@
 		nsecs_raw += arch_offset;
 		nsecs_real += arch_offset;
 
-	} while (read_seqretry(&xtime_lock, seq));
+	} while (read_seqcount_retry(&xtime_seq, seq));
 
 	timespec_add_ns(ts_raw, nsecs_raw);
 	timespec_add_ns(ts_real, nsecs_real);
@@ -385,7 +385,8 @@
 	if (!timespec_valid_strict(tv))
 		return -EINVAL;
 
-	write_seqlock_irqsave(&xtime_lock, flags);
+	raw_spin_lock_irqsave(&xtime_lock, flags);
+	write_seqcount_begin(&xtime_seq);
 
 	timekeeping_forward_now();
 
@@ -397,7 +398,8 @@
 
 	timekeeping_update(true);
 
-	write_sequnlock_irqrestore(&xtime_lock, flags);
+	write_seqcount_end(&xtime_seq);
+	raw_spin_unlock_irqrestore(&xtime_lock, flags);
 
 	/* signal hrtimers about time change */
 	clock_was_set();
@@ -423,7 +425,8 @@
 	if ((unsigned long)ts->tv_nsec >= NSEC_PER_SEC)
 		return -EINVAL;
 
-	write_seqlock_irqsave(&xtime_lock, flags);
+	raw_spin_lock_irqsave(&xtime_lock, flags);
+	write_seqcount_begin(&xtime_seq);
 
 	timekeeping_forward_now();
 
@@ -439,7 +442,8 @@
 error: /* even if we error out, we forwarded the time, so call update */
 	timekeeping_update(true);
 
-	write_sequnlock_irqrestore(&xtime_lock, flags);
+	write_seqcount_end(&xtime_seq);
+	raw_spin_unlock_irqrestore(&xtime_lock, flags);
 
 	/* signal hrtimers about time change */
 	clock_was_set();
@@ -511,11 +515,11 @@
 	s64 nsecs;
 
 	do {
-		seq = read_seqbegin(&xtime_lock);
+		seq = read_seqcount_begin(&xtime_seq);
 		nsecs = timekeeping_get_ns_raw();
 		*ts = raw_time;
 
-	} while (read_seqretry(&xtime_lock, seq));
+	} while (read_seqcount_retry(&xtime_seq, seq));
 
 	timespec_add_ns(ts, nsecs);
 }
@@ -531,11 +535,11 @@
 	int ret;
 
 	do {
-		seq = read_seqbegin(&xtime_lock);
+		seq = read_seqcount_begin(&xtime_seq);
 
 		ret = timekeeper.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES;
 
-	} while (read_seqretry(&xtime_lock, seq));
+	} while (read_seqcount_retry(&xtime_seq, seq));
 
 	return ret;
 }
@@ -606,7 +610,8 @@
 		boot.tv_nsec = 0;
 	}
 
-	write_seqlock_irqsave(&xtime_lock, flags);
+	raw_spin_lock_irqsave(&xtime_lock, flags);
+	write_seqcount_begin(&xtime_seq);
 
 	ntp_init();
 
@@ -628,7 +633,8 @@
 	update_rt_offset();
 	total_sleep_time.tv_sec = 0;
 	total_sleep_time.tv_nsec = 0;
-	write_sequnlock_irqrestore(&xtime_lock, flags);
+	write_seqcount_end(&xtime_seq);
+	raw_spin_unlock_irqrestore(&xtime_lock, flags);
 }
 
 /* time in seconds when suspend began */
@@ -681,14 +687,16 @@
 	if (!(ts.tv_sec == 0 && ts.tv_nsec == 0))
 		return;
 
-	write_seqlock_irqsave(&xtime_lock, flags);
+	raw_spin_lock_irqsave(&xtime_lock, flags);
+	write_seqcount_begin(&xtime_seq);
 	timekeeping_forward_now();
 
 	__timekeeping_inject_sleeptime(delta);
 
 	timekeeping_update(true);
 
-	write_sequnlock_irqrestore(&xtime_lock, flags);
+	write_seqcount_end(&xtime_seq);
+	raw_spin_unlock_irqrestore(&xtime_lock, flags);
 
 	/* signal hrtimers about time change */
 	clock_was_set();
@@ -711,7 +719,8 @@
 
 	clocksource_resume();
 
-	write_seqlock_irqsave(&xtime_lock, flags);
+	raw_spin_lock_irqsave(&xtime_lock, flags);
+	write_seqcount_begin(&xtime_seq);
 
 	if (timespec_compare(&ts, &timekeeping_suspend_time) > 0) {
 		ts = timespec_sub(ts, timekeeping_suspend_time);
@@ -722,7 +731,8 @@
 	timekeeper.ntp_error = 0;
 	timekeeping_suspended = 0;
 	timekeeping_update(false);
-	write_sequnlock_irqrestore(&xtime_lock, flags);
+	write_seqcount_end(&xtime_seq);
+	raw_spin_unlock_irqrestore(&xtime_lock, flags);
 
 	touch_softlockup_watchdog();
 
@@ -740,7 +750,8 @@
 
 	read_persistent_clock(&timekeeping_suspend_time);
 
-	write_seqlock_irqsave(&xtime_lock, flags);
+	raw_spin_lock_irqsave(&xtime_lock, flags);
+	write_seqcount_begin(&xtime_seq);
 	timekeeping_forward_now();
 	timekeeping_suspended = 1;
 
@@ -763,7 +774,8 @@
 		timekeeping_suspend_time =
 			timespec_add(timekeeping_suspend_time, delta_delta);
 	}
-	write_sequnlock_irqrestore(&xtime_lock, flags);
+	write_seqcount_end(&xtime_seq);
+	raw_spin_unlock_irqrestore(&xtime_lock, flags);
 
 	clockevents_notify(CLOCK_EVT_NOTIFY_SUSPEND, NULL);
 	clocksource_suspend();
@@ -1152,13 +1164,13 @@
 	WARN_ON(timekeeping_suspended);
 
 	do {
-		seq = read_seqbegin(&xtime_lock);
+		seq = read_seqcount_begin(&xtime_seq);
 		*ts = xtime;
 		tomono = wall_to_monotonic;
 		sleep = total_sleep_time;
 		nsecs = timekeeping_get_ns();
 
-	} while (read_seqretry(&xtime_lock, seq));
+	} while (read_seqcount_retry(&xtime_seq, seq));
 
 	set_normalized_timespec(ts, ts->tv_sec + tomono.tv_sec + sleep.tv_sec,
 		(s64)ts->tv_nsec + tomono.tv_nsec + sleep.tv_nsec + nsecs);
@@ -1209,10 +1221,10 @@
 	unsigned long seq;
 
 	do {
-		seq = read_seqbegin(&xtime_lock);
+		seq = read_seqcount_begin(&xtime_seq);
 
 		now = xtime;
-	} while (read_seqretry(&xtime_lock, seq));
+	} while (read_seqcount_retry(&xtime_seq, seq));
 
 	return now;
 }
@@ -1224,11 +1236,11 @@
 	unsigned long seq;
 
 	do {
-		seq = read_seqbegin(&xtime_lock);
+		seq = read_seqcount_begin(&xtime_seq);
 
 		now = xtime;
 		mono = wall_to_monotonic;
-	} while (read_seqretry(&xtime_lock, seq));
+	} while (read_seqcount_retry(&xtime_seq, seq));
 
 	set_normalized_timespec(&now, now.tv_sec + mono.tv_sec,
 				now.tv_nsec + mono.tv_nsec);
@@ -1260,11 +1272,11 @@
 	unsigned long seq;
 
 	do {
-		seq = read_seqbegin(&xtime_lock);
+		seq = read_seqcount_begin(&xtime_seq);
 		*xtim = xtime;
 		*wtom = wall_to_monotonic;
 		*sleep = total_sleep_time;
-	} while (read_seqretry(&xtime_lock, seq));
+	} while (read_seqcount_retry(&xtime_seq, seq));
 }
 
 #ifdef CONFIG_HIGH_RES_TIMERS
@@ -1283,7 +1295,7 @@
 	u64 secs, nsecs;
 
 	do {
-		seq = read_seqbegin(&xtime_lock);
+		seq = read_seqcount_begin(&xtime_seq);
 
 		secs = xtime.tv_sec;
 		nsecs = xtime.tv_nsec;
@@ -1293,7 +1305,7 @@
 
 		*real = offs_real;
 		*boot = offs_boot;
-	} while (read_seqretry(&xtime_lock, seq));
+	} while (read_seqcount_retry(&xtime_seq, seq));
 
 	now = ktime_add_ns(ktime_set(secs, 0), nsecs);
 	now = ktime_sub(now, *real);
@@ -1310,9 +1322,9 @@
 	struct timespec wtom;
 
 	do {
-		seq = read_seqbegin(&xtime_lock);
+		seq = read_seqcount_begin(&xtime_seq);
 		wtom = wall_to_monotonic;
-	} while (read_seqretry(&xtime_lock, seq));
+	} while (read_seqcount_retry(&xtime_seq, seq));
 	return timespec_to_ktime(wtom);
 }
 
@@ -1324,7 +1336,9 @@
  */
 void xtime_update(unsigned long ticks)
 {
-	write_seqlock(&xtime_lock);
+	raw_spin_lock(&xtime_lock);
+	write_seqcount_begin(&xtime_seq);
 	do_timer(ticks);
-	write_sequnlock(&xtime_lock);
+	write_seqcount_end(&xtime_seq);
+	raw_spin_unlock(&xtime_lock);
 }
diff --git a/kernel/timer.c b/kernel/timer.c
index 349953e..badd2d2 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -76,6 +76,9 @@
 struct tvec_base {
 	spinlock_t lock;
 	struct timer_list *running_timer;
+#ifdef CONFIG_PREEMPT_RT_FULL
+	wait_queue_head_t wait_for_running_timer;
+#endif
 	unsigned long timer_jiffies;
 	unsigned long next_timer;
 	struct tvec_root tv1;
@@ -657,6 +660,36 @@
 	}
 }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+static inline struct tvec_base *switch_timer_base(struct timer_list *timer,
+						  struct tvec_base *old,
+						  struct tvec_base *new)
+{
+	/* See the comment in lock_timer_base() */
+	timer_set_base(timer, NULL);
+	spin_unlock(&old->lock);
+	spin_lock(&new->lock);
+	timer_set_base(timer, new);
+	return new;
+}
+#else
+static inline struct tvec_base *switch_timer_base(struct timer_list *timer,
+						  struct tvec_base *old,
+						  struct tvec_base *new)
+{
+	/*
+	 * We cannot do the above because we might be preempted and
+	 * then the preempter would see NULL and loop forever.
+	 */
+	if (spin_trylock(&new->lock)) {
+		timer_set_base(timer, new);
+		spin_unlock(&old->lock);
+		return new;
+	}
+	return old;
+}
+#endif
+
 static inline int
 __mod_timer(struct timer_list *timer, unsigned long expires,
 						bool pending_only, int pinned)
@@ -683,12 +716,15 @@
 
 	debug_activate(timer, expires);
 
+	preempt_disable_rt();
 	cpu = smp_processor_id();
 
 #if defined(CONFIG_NO_HZ) && defined(CONFIG_SMP)
 	if (!pinned && get_sysctl_timer_migration() && idle_cpu(cpu))
 		cpu = get_nohz_timer_target();
 #endif
+	preempt_enable_rt();
+
 	new_base = per_cpu(tvec_bases, cpu);
 
 	if (base != new_base) {
@@ -699,14 +735,8 @@
 		 * handler yet has not finished. This also guarantees that
 		 * the timer is serialized wrt itself.
 		 */
-		if (likely(base->running_timer != timer)) {
-			/* See the comment in lock_timer_base() */
-			timer_set_base(timer, NULL);
-			spin_unlock(&base->lock);
-			base = new_base;
-			spin_lock(&base->lock);
-			timer_set_base(timer, base);
-		}
+		if (likely(base->running_timer != timer))
+			base = switch_timer_base(timer, base, new_base);
 	}
 
 	timer->expires = expires;
@@ -889,6 +919,29 @@
 }
 EXPORT_SYMBOL_GPL(add_timer_on);
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+/*
+ * Wait for a running timer
+ */
+static void wait_for_running_timer(struct timer_list *timer)
+{
+	struct tvec_base *base = timer->base;
+
+	if (base->running_timer == timer)
+		wait_event(base->wait_for_running_timer,
+			   base->running_timer != timer);
+}
+
+# define wakeup_timer_waiters(b)	wake_up(&(b)->wait_for_running_timer)
+#else
+static inline void wait_for_running_timer(struct timer_list *timer)
+{
+	cpu_relax();
+}
+
+# define wakeup_timer_waiters(b)	do { } while (0)
+#endif
+
 /**
  * del_timer - deactive a timer.
  * @timer: the timer to be deactivated
@@ -957,7 +1010,7 @@
 }
 EXPORT_SYMBOL(try_to_del_timer_sync);
 
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL)
 /**
  * del_timer_sync - deactivate a timer and wait for the handler to finish.
  * @timer: the timer to be deactivated
@@ -1017,7 +1070,7 @@
 		int ret = try_to_del_timer_sync(timer);
 		if (ret >= 0)
 			return ret;
-		cpu_relax();
+		wait_for_running_timer(timer);
 	}
 }
 EXPORT_SYMBOL(del_timer_sync);
@@ -1128,10 +1181,11 @@
 
 			spin_unlock_irq(&base->lock);
 			call_timer_fn(timer, fn, data);
+			base->running_timer = NULL;
 			spin_lock_irq(&base->lock);
 		}
 	}
-	base->running_timer = NULL;
+	wakeup_timer_waiters(base);
 	spin_unlock_irq(&base->lock);
 }
 
@@ -1270,6 +1324,23 @@
 	 */
 	if (cpu_is_offline(smp_processor_id()))
 		return now + NEXT_TIMER_MAX_DELTA;
+
+#ifdef CONFIG_PREEMPT_RT_FULL
+	/*
+	 * On PREEMPT_RT we cannot sleep here. If the trylock does not
+	 * succeed then we return the worst-case 'expires in 1 tick'
+	 * value. We use the rt functions here directly to avoid a
+	 * migrate_disable() call.
+	 */
+	if (spin_do_trylock(&base->lock)) {
+		if (time_before_eq(base->next_timer, base->timer_jiffies))
+			base->next_timer = __next_timer_interrupt(base);
+		expires = base->next_timer;
+		rt_spin_unlock_after_trylock_in_irq(&base->lock);
+	} else {
+		expires = now + 1;
+	}
+#else
 	spin_lock(&base->lock);
 	if (time_before_eq(base->next_timer, base->timer_jiffies))
 		base->next_timer = __next_timer_interrupt(base);
@@ -1278,7 +1349,7 @@
 
 	if (time_before_eq(expires, now))
 		return now;
-
+#endif
 	return cmp_next_hrtimer_event(now, expires);
 }
 #endif
@@ -1294,14 +1365,13 @@
 
 	/* Note: this timer irq context must be accounted for as well. */
 	account_process_tick(p, user_tick);
+	scheduler_tick();
 	run_local_timers();
 	rcu_check_callbacks(cpu, user_tick);
-	printk_tick();
-#ifdef CONFIG_IRQ_WORK
+#if defined(CONFIG_IRQ_WORK) && !defined(CONFIG_PREEMPT_RT_FULL)
 	if (in_irq())
 		irq_work_run();
 #endif
-	scheduler_tick();
 	run_posix_cpu_timers(p);
 }
 
@@ -1312,6 +1382,11 @@
 {
 	struct tvec_base *base = __this_cpu_read(tvec_bases);
 
+#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL)
+	irq_work_run();
+#endif
+
+	printk_tick();
 	hrtimer_run_pending();
 
 	if (time_after_eq(jiffies, base->timer_jiffies))
@@ -1633,12 +1708,14 @@
 			base = &boot_tvec_bases;
 		}
 		spin_lock_init(&base->lock);
+#ifdef CONFIG_PREEMPT_RT_FULL
+		init_waitqueue_head(&base->wait_for_running_timer);
+#endif
 		tvec_base_done[cpu] = 1;
 	} else {
 		base = per_cpu(tvec_bases, cpu);
 	}
 
-
 	for (j = 0; j < TVN_SIZE; j++) {
 		INIT_LIST_HEAD(base->tv5.vec + j);
 		INIT_LIST_HEAD(base->tv4.vec + j);
@@ -1677,7 +1754,7 @@
 
 	BUG_ON(cpu_online(cpu));
 	old_base = per_cpu(tvec_bases, cpu);
-	new_base = get_cpu_var(tvec_bases);
+	new_base = get_local_var(tvec_bases);
 	/*
 	 * The caller is globally serialized and nobody else
 	 * takes two locks at once, deadlock is not possible.
@@ -1698,7 +1775,7 @@
 
 	spin_unlock(&old_base->lock);
 	spin_unlock_irq(&new_base->lock);
-	put_cpu_var(tvec_bases);
+	put_local_var(tvec_bases);
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 762264d..1e0f12c 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -192,6 +192,24 @@
 	  enabled. This option and the preempt-off timing option can be
 	  used together or separately.)
 
+config INTERRUPT_OFF_HIST
+	bool "Interrupts-off Latency Histogram"
+	depends on IRQSOFF_TRACER
+	help
+	  This option generates continuously updated histograms (one per cpu)
+	  of the duration of time periods with interrupts disabled. The
+	  histograms are disabled by default. To enable them, write a non-zero
+	  number to
+
+	      /sys/kernel/debug/tracing/latency_hist/enable/preemptirqsoff
+
+	  If PREEMPT_OFF_HIST is also selected, additional histograms (one
+	  per cpu) are generated that accumulate the duration of time periods
+	  when both interrupts and preemption are disabled. The histogram data
+	  will be located in the debug file system at
+
+	      /sys/kernel/debug/tracing/latency_hist/irqsoff
+
 config PREEMPT_TRACER
 	bool "Preemption-off Latency Tracer"
 	default n
@@ -214,6 +232,24 @@
 	  enabled. This option and the irqs-off timing option can be
 	  used together or separately.)
 
+config PREEMPT_OFF_HIST
+	bool "Preemption-off Latency Histogram"
+	depends on PREEMPT_TRACER
+	help
+	  This option generates continuously updated histograms (one per cpu)
+	  of the duration of time periods with preemption disabled. The
+	  histograms are disabled by default. To enable them, write a non-zero
+	  number to
+
+	      /sys/kernel/debug/tracing/latency_hist/enable/preemptirqsoff
+
+	  If INTERRUPT_OFF_HIST is also selected, additional histograms (one
+	  per cpu) are generated that accumulate the duration of time periods
+	  when both interrupts and preemption are disabled. The histogram data
+	  will be located in the debug file system at
+
+	      /sys/kernel/debug/tracing/latency_hist/preemptoff
+
 config SCHED_TRACER
 	bool "Scheduling Latency Tracer"
 	select GENERIC_TRACER
@@ -223,6 +259,74 @@
 	  This tracer tracks the latency of the highest priority task
 	  to be scheduled in, starting from the point it has woken up.
 
+config WAKEUP_LATENCY_HIST
+	bool "Scheduling Latency Histogram"
+	depends on SCHED_TRACER
+	help
+	  This option generates continuously updated histograms (one per cpu)
+	  of the scheduling latency of the highest priority task.
+	  The histograms are disabled by default. To enable them, write a
+	  non-zero number to
+
+	      /sys/kernel/debug/tracing/latency_hist/enable/wakeup
+
+	  Two different algorithms are used, one to determine the latency of
+	  processes that exclusively use the highest priority of the system and
+	  another one to determine the latency of processes that share the
+	  highest system priority with other processes. The former is used to
+	  improve hardware and system software, the latter to optimize the
+	  priority design of a given system. The histogram data will be
+	  located in the debug file system at
+
+	      /sys/kernel/debug/tracing/latency_hist/wakeup
+
+	  and
+
+	      /sys/kernel/debug/tracing/latency_hist/wakeup/sharedprio
+
+	  If both Scheduling Latency Histogram and Missed Timer Offsets
+	  Histogram are selected, additional histogram data will be collected
+	  that contain, in addition to the wakeup latency, the timer latency, in
+	  case the wakeup was triggered by an expired timer. These histograms
+	  are available in the
+
+	      /sys/kernel/debug/tracing/latency_hist/timerandwakeup
+
+	  directory. They reflect the apparent interrupt and scheduling latency
+	  and are best suitable to determine the worst-case latency of a given
+	  system. To enable these histograms, write a non-zero number to
+
+	      /sys/kernel/debug/tracing/latency_hist/enable/timerandwakeup
+
+config MISSED_TIMER_OFFSETS_HIST
+	depends on HIGH_RES_TIMERS
+	select GENERIC_TRACER
+	bool "Missed Timer Offsets Histogram"
+	help
+	  Generate a histogram of missed timer offsets in microseconds. The
+	  histograms are disabled by default. To enable them, write a non-zero
+	  number to
+
+	      /sys/kernel/debug/tracing/latency_hist/enable/missed_timer_offsets
+
+	  The histogram data will be located in the debug file system at
+
+	      /sys/kernel/debug/tracing/latency_hist/missed_timer_offsets
+
+	  If both Scheduling Latency Histogram and Missed Timer Offsets
+	  Histogram are selected, additional histogram data will be collected
+	  that contain, in addition to the wakeup latency, the timer latency, in
+	  case the wakeup was triggered by an expired timer. These histograms
+	  are available in the
+
+	      /sys/kernel/debug/tracing/latency_hist/timerandwakeup
+
+	  directory. They reflect the apparent interrupt and scheduling latency
+	  and are best suitable to determine the worst-case latency of a given
+	  system. To enable these histograms, write a non-zero number to
+
+	      /sys/kernel/debug/tracing/latency_hist/enable/timerandwakeup
+
 config ENABLE_DEFAULT_TRACERS
 	bool "Trace process context switches and events"
 	depends on !GENERIC_TRACER
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 5f39a07..108a387 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -36,6 +36,10 @@
 obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o
 obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o
 obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o
+obj-$(CONFIG_INTERRUPT_OFF_HIST) += latency_hist.o
+obj-$(CONFIG_PREEMPT_OFF_HIST) += latency_hist.o
+obj-$(CONFIG_WAKEUP_LATENCY_HIST) += latency_hist.o
+obj-$(CONFIG_MISSED_TIMER_OFFSETS_HIST) += latency_hist.o
 obj-$(CONFIG_NOP_TRACER) += trace_nop.o
 obj-$(CONFIG_STACK_TRACER) += trace_stack.o
 obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o
diff --git a/kernel/trace/latency_hist.c b/kernel/trace/latency_hist.c
new file mode 100644
index 0000000..6a4c869
--- /dev/null
+++ b/kernel/trace/latency_hist.c
@@ -0,0 +1,1176 @@
+/*
+ * kernel/trace/latency_hist.c
+ *
+ * Add support for histograms of preemption-off latency and
+ * interrupt-off latency and wakeup latency, it depends on
+ * Real-Time Preemption Support.
+ *
+ *  Copyright (C) 2005 MontaVista Software, Inc.
+ *  Yi Yang <yyang@ch.mvista.com>
+ *
+ *  Converted to work with the new latency tracer.
+ *  Copyright (C) 2008 Red Hat, Inc.
+ *    Steven Rostedt <srostedt@redhat.com>
+ *
+ */
+#include <linux/module.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/percpu.h>
+#include <linux/kallsyms.h>
+#include <linux/uaccess.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <asm/atomic.h>
+#include <asm/div64.h>
+
+#include "trace.h"
+#include <trace/events/sched.h>
+
+#define NSECS_PER_USECS 1000L
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/hist.h>
+
+enum {
+	IRQSOFF_LATENCY = 0,
+	PREEMPTOFF_LATENCY,
+	PREEMPTIRQSOFF_LATENCY,
+	WAKEUP_LATENCY,
+	WAKEUP_LATENCY_SHAREDPRIO,
+	MISSED_TIMER_OFFSETS,
+	TIMERANDWAKEUP_LATENCY,
+	MAX_LATENCY_TYPE,
+};
+
+#define MAX_ENTRY_NUM 10240
+
+struct hist_data {
+	atomic_t hist_mode; /* 0 log, 1 don't log */
+	long offset; /* set it to MAX_ENTRY_NUM/2 for a bipolar scale */
+	long min_lat;
+	long max_lat;
+	unsigned long long below_hist_bound_samples;
+	unsigned long long above_hist_bound_samples;
+	long long accumulate_lat;
+	unsigned long long total_samples;
+	unsigned long long hist_array[MAX_ENTRY_NUM];
+};
+
+struct enable_data {
+	int latency_type;
+	int enabled;
+};
+
+static char *latency_hist_dir_root = "latency_hist";
+
+#ifdef CONFIG_INTERRUPT_OFF_HIST
+static DEFINE_PER_CPU(struct hist_data, irqsoff_hist);
+static char *irqsoff_hist_dir = "irqsoff";
+static DEFINE_PER_CPU(cycles_t, hist_irqsoff_start);
+static DEFINE_PER_CPU(int, hist_irqsoff_counting);
+#endif
+
+#ifdef CONFIG_PREEMPT_OFF_HIST
+static DEFINE_PER_CPU(struct hist_data, preemptoff_hist);
+static char *preemptoff_hist_dir = "preemptoff";
+static DEFINE_PER_CPU(cycles_t, hist_preemptoff_start);
+static DEFINE_PER_CPU(int, hist_preemptoff_counting);
+#endif
+
+#if defined(CONFIG_PREEMPT_OFF_HIST) && defined(CONFIG_INTERRUPT_OFF_HIST)
+static DEFINE_PER_CPU(struct hist_data, preemptirqsoff_hist);
+static char *preemptirqsoff_hist_dir = "preemptirqsoff";
+static DEFINE_PER_CPU(cycles_t, hist_preemptirqsoff_start);
+static DEFINE_PER_CPU(int, hist_preemptirqsoff_counting);
+#endif
+
+#if defined(CONFIG_PREEMPT_OFF_HIST) || defined(CONFIG_INTERRUPT_OFF_HIST)
+static notrace void probe_preemptirqsoff_hist(void *v, int reason, int start);
+static struct enable_data preemptirqsoff_enabled_data = {
+	.latency_type = PREEMPTIRQSOFF_LATENCY,
+	.enabled = 0,
+};
+#endif
+
+#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
+    defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
+struct maxlatproc_data {
+	char comm[FIELD_SIZEOF(struct task_struct, comm)];
+	char current_comm[FIELD_SIZEOF(struct task_struct, comm)];
+	int pid;
+	int current_pid;
+	int prio;
+	int current_prio;
+	long latency;
+	long timeroffset;
+	cycle_t timestamp;
+};
+#endif
+
+#ifdef CONFIG_WAKEUP_LATENCY_HIST
+static DEFINE_PER_CPU(struct hist_data, wakeup_latency_hist);
+static DEFINE_PER_CPU(struct hist_data, wakeup_latency_hist_sharedprio);
+static char *wakeup_latency_hist_dir = "wakeup";
+static char *wakeup_latency_hist_dir_sharedprio = "sharedprio";
+static notrace void probe_wakeup_latency_hist_start(void *v,
+    struct task_struct *p, int success);
+static notrace void probe_wakeup_latency_hist_stop(void *v,
+    struct task_struct *prev, struct task_struct *next);
+static notrace void probe_sched_migrate_task(void *,
+    struct task_struct *task, int cpu);
+static struct enable_data wakeup_latency_enabled_data = {
+	.latency_type = WAKEUP_LATENCY,
+	.enabled = 0,
+};
+static DEFINE_PER_CPU(struct maxlatproc_data, wakeup_maxlatproc);
+static DEFINE_PER_CPU(struct maxlatproc_data, wakeup_maxlatproc_sharedprio);
+static DEFINE_PER_CPU(struct task_struct *, wakeup_task);
+static DEFINE_PER_CPU(int, wakeup_sharedprio);
+static unsigned long wakeup_pid;
+#endif
+
+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
+static DEFINE_PER_CPU(struct hist_data, missed_timer_offsets);
+static char *missed_timer_offsets_dir = "missed_timer_offsets";
+static notrace void probe_hrtimer_interrupt(void *v, int cpu,
+    long long offset, struct task_struct *curr, struct task_struct *task);
+static struct enable_data missed_timer_offsets_enabled_data = {
+	.latency_type = MISSED_TIMER_OFFSETS,
+	.enabled = 0,
+};
+static DEFINE_PER_CPU(struct maxlatproc_data, missed_timer_offsets_maxlatproc);
+static unsigned long missed_timer_offsets_pid;
+#endif
+
+#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \
+    defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
+static DEFINE_PER_CPU(struct hist_data, timerandwakeup_latency_hist);
+static char *timerandwakeup_latency_hist_dir = "timerandwakeup";
+static struct enable_data timerandwakeup_enabled_data = {
+	.latency_type = TIMERANDWAKEUP_LATENCY,
+	.enabled = 0,
+};
+static DEFINE_PER_CPU(struct maxlatproc_data, timerandwakeup_maxlatproc);
+#endif
+
+void notrace latency_hist(int latency_type, int cpu, long latency,
+			  long timeroffset, cycle_t stop,
+			  struct task_struct *p)
+{
+	struct hist_data *my_hist;
+#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
+    defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
+	struct maxlatproc_data *mp = NULL;
+#endif
+
+	if (cpu < 0 || cpu >= NR_CPUS || latency_type < 0 ||
+	    latency_type >= MAX_LATENCY_TYPE)
+		return;
+
+	switch (latency_type) {
+#ifdef CONFIG_INTERRUPT_OFF_HIST
+	case IRQSOFF_LATENCY:
+		my_hist = &per_cpu(irqsoff_hist, cpu);
+		break;
+#endif
+#ifdef CONFIG_PREEMPT_OFF_HIST
+	case PREEMPTOFF_LATENCY:
+		my_hist = &per_cpu(preemptoff_hist, cpu);
+		break;
+#endif
+#if defined(CONFIG_PREEMPT_OFF_HIST) && defined(CONFIG_INTERRUPT_OFF_HIST)
+	case PREEMPTIRQSOFF_LATENCY:
+		my_hist = &per_cpu(preemptirqsoff_hist, cpu);
+		break;
+#endif
+#ifdef CONFIG_WAKEUP_LATENCY_HIST
+	case WAKEUP_LATENCY:
+		my_hist = &per_cpu(wakeup_latency_hist, cpu);
+		mp = &per_cpu(wakeup_maxlatproc, cpu);
+		break;
+	case WAKEUP_LATENCY_SHAREDPRIO:
+		my_hist = &per_cpu(wakeup_latency_hist_sharedprio, cpu);
+		mp = &per_cpu(wakeup_maxlatproc_sharedprio, cpu);
+		break;
+#endif
+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
+	case MISSED_TIMER_OFFSETS:
+		my_hist = &per_cpu(missed_timer_offsets, cpu);
+		mp = &per_cpu(missed_timer_offsets_maxlatproc, cpu);
+		break;
+#endif
+#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \
+    defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
+	case TIMERANDWAKEUP_LATENCY:
+		my_hist = &per_cpu(timerandwakeup_latency_hist, cpu);
+		mp = &per_cpu(timerandwakeup_maxlatproc, cpu);
+		break;
+#endif
+
+	default:
+		return;
+	}
+
+	latency += my_hist->offset;
+
+	if (atomic_read(&my_hist->hist_mode) == 0)
+		return;
+
+	if (latency < 0 || latency >= MAX_ENTRY_NUM) {
+		if (latency < 0)
+			my_hist->below_hist_bound_samples++;
+		else
+			my_hist->above_hist_bound_samples++;
+	} else
+		my_hist->hist_array[latency]++;
+
+	if (unlikely(latency > my_hist->max_lat ||
+	    my_hist->min_lat == LONG_MAX)) {
+#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
+    defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
+		if (latency_type == WAKEUP_LATENCY ||
+		    latency_type == WAKEUP_LATENCY_SHAREDPRIO ||
+		    latency_type == MISSED_TIMER_OFFSETS ||
+		    latency_type == TIMERANDWAKEUP_LATENCY) {
+			strncpy(mp->comm, p->comm, sizeof(mp->comm));
+			strncpy(mp->current_comm, current->comm,
+			    sizeof(mp->current_comm));
+			mp->pid = task_pid_nr(p);
+			mp->current_pid = task_pid_nr(current);
+			mp->prio = p->prio;
+			mp->current_prio = current->prio;
+			mp->latency = latency;
+			mp->timeroffset = timeroffset;
+			mp->timestamp = stop;
+		}
+#endif
+		my_hist->max_lat = latency;
+	}
+	if (unlikely(latency < my_hist->min_lat))
+		my_hist->min_lat = latency;
+	my_hist->total_samples++;
+	my_hist->accumulate_lat += latency;
+}
+
+static void *l_start(struct seq_file *m, loff_t *pos)
+{
+	loff_t *index_ptr = NULL;
+	loff_t index = *pos;
+	struct hist_data *my_hist = m->private;
+
+	if (index == 0) {
+		char minstr[32], avgstr[32], maxstr[32];
+
+		atomic_dec(&my_hist->hist_mode);
+
+		if (likely(my_hist->total_samples)) {
+			long avg = (long) div64_s64(my_hist->accumulate_lat,
+			    my_hist->total_samples);
+			snprintf(minstr, sizeof(minstr), "%ld",
+			    my_hist->min_lat - my_hist->offset);
+			snprintf(avgstr, sizeof(avgstr), "%ld",
+			    avg - my_hist->offset);
+			snprintf(maxstr, sizeof(maxstr), "%ld",
+			    my_hist->max_lat - my_hist->offset);
+		} else {
+			strcpy(minstr, "<undef>");
+			strcpy(avgstr, minstr);
+			strcpy(maxstr, minstr);
+		}
+
+		seq_printf(m, "#Minimum latency: %s microseconds\n"
+			   "#Average latency: %s microseconds\n"
+			   "#Maximum latency: %s microseconds\n"
+			   "#Total samples: %llu\n"
+			   "#There are %llu samples lower than %ld"
+			   " microseconds.\n"
+			   "#There are %llu samples greater or equal"
+			   " than %ld microseconds.\n"
+			   "#usecs\t%16s\n",
+			   minstr, avgstr, maxstr,
+			   my_hist->total_samples,
+			   my_hist->below_hist_bound_samples,
+			   -my_hist->offset,
+			   my_hist->above_hist_bound_samples,
+			   MAX_ENTRY_NUM - my_hist->offset,
+			   "samples");
+	}
+	if (index < MAX_ENTRY_NUM) {
+		index_ptr = kmalloc(sizeof(loff_t), GFP_KERNEL);
+		if (index_ptr)
+			*index_ptr = index;
+	}
+
+	return index_ptr;
+}
+
+static void *l_next(struct seq_file *m, void *p, loff_t *pos)
+{
+	loff_t *index_ptr = p;
+	struct hist_data *my_hist = m->private;
+
+	if (++*pos >= MAX_ENTRY_NUM) {
+		atomic_inc(&my_hist->hist_mode);
+		return NULL;
+	}
+	*index_ptr = *pos;
+	return index_ptr;
+}
+
+static void l_stop(struct seq_file *m, void *p)
+{
+	kfree(p);
+}
+
+static int l_show(struct seq_file *m, void *p)
+{
+	int index = *(loff_t *) p;
+	struct hist_data *my_hist = m->private;
+
+	seq_printf(m, "%6ld\t%16llu\n", index - my_hist->offset,
+	    my_hist->hist_array[index]);
+	return 0;
+}
+
+static struct seq_operations latency_hist_seq_op = {
+	.start = l_start,
+	.next  = l_next,
+	.stop  = l_stop,
+	.show  = l_show
+};
+
+static int latency_hist_open(struct inode *inode, struct file *file)
+{
+	int ret;
+
+	ret = seq_open(file, &latency_hist_seq_op);
+	if (!ret) {
+		struct seq_file *seq = file->private_data;
+		seq->private = inode->i_private;
+	}
+	return ret;
+}
+
+static struct file_operations latency_hist_fops = {
+	.open = latency_hist_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = seq_release,
+};
+
+#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
+    defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
+static void clear_maxlatprocdata(struct maxlatproc_data *mp)
+{
+	mp->comm[0] = mp->current_comm[0] = '\0';
+	mp->prio = mp->current_prio = mp->pid = mp->current_pid =
+	    mp->latency = mp->timeroffset = -1;
+	mp->timestamp = 0;
+}
+#endif
+
+static void hist_reset(struct hist_data *hist)
+{
+	atomic_dec(&hist->hist_mode);
+
+	memset(hist->hist_array, 0, sizeof(hist->hist_array));
+	hist->below_hist_bound_samples = 0ULL;
+	hist->above_hist_bound_samples = 0ULL;
+	hist->min_lat = LONG_MAX;
+	hist->max_lat = LONG_MIN;
+	hist->total_samples = 0ULL;
+	hist->accumulate_lat = 0LL;
+
+	atomic_inc(&hist->hist_mode);
+}
+
+static ssize_t
+latency_hist_reset(struct file *file, const char __user *a,
+		   size_t size, loff_t *off)
+{
+	int cpu;
+	struct hist_data *hist = NULL;
+#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
+    defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
+	struct maxlatproc_data *mp = NULL;
+#endif
+	off_t latency_type = (off_t) file->private_data;
+
+	for_each_online_cpu(cpu) {
+
+		switch (latency_type) {
+#ifdef CONFIG_PREEMPT_OFF_HIST
+		case PREEMPTOFF_LATENCY:
+			hist = &per_cpu(preemptoff_hist, cpu);
+			break;
+#endif
+#ifdef CONFIG_INTERRUPT_OFF_HIST
+		case IRQSOFF_LATENCY:
+			hist = &per_cpu(irqsoff_hist, cpu);
+			break;
+#endif
+#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST)
+		case PREEMPTIRQSOFF_LATENCY:
+			hist = &per_cpu(preemptirqsoff_hist, cpu);
+			break;
+#endif
+#ifdef CONFIG_WAKEUP_LATENCY_HIST
+		case WAKEUP_LATENCY:
+			hist = &per_cpu(wakeup_latency_hist, cpu);
+			mp = &per_cpu(wakeup_maxlatproc, cpu);
+			break;
+		case WAKEUP_LATENCY_SHAREDPRIO:
+			hist = &per_cpu(wakeup_latency_hist_sharedprio, cpu);
+			mp = &per_cpu(wakeup_maxlatproc_sharedprio, cpu);
+			break;
+#endif
+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
+		case MISSED_TIMER_OFFSETS:
+			hist = &per_cpu(missed_timer_offsets, cpu);
+			mp = &per_cpu(missed_timer_offsets_maxlatproc, cpu);
+			break;
+#endif
+#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \
+    defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
+		case TIMERANDWAKEUP_LATENCY:
+			hist = &per_cpu(timerandwakeup_latency_hist, cpu);
+			mp = &per_cpu(timerandwakeup_maxlatproc, cpu);
+			break;
+#endif
+		}
+
+		hist_reset(hist);
+#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
+    defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
+		if (latency_type == WAKEUP_LATENCY ||
+		    latency_type == WAKEUP_LATENCY_SHAREDPRIO ||
+		    latency_type == MISSED_TIMER_OFFSETS ||
+		    latency_type == TIMERANDWAKEUP_LATENCY)
+			clear_maxlatprocdata(mp);
+#endif
+	}
+
+	return size;
+}
+
+#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
+    defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
+static ssize_t
+show_pid(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos)
+{
+	char buf[64];
+	int r;
+	unsigned long *this_pid = file->private_data;
+
+	r = snprintf(buf, sizeof(buf), "%lu\n", *this_pid);
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static ssize_t do_pid(struct file *file, const char __user *ubuf,
+		      size_t cnt, loff_t *ppos)
+{
+	char buf[64];
+	unsigned long pid;
+	unsigned long *this_pid = file->private_data;
+
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	buf[cnt] = '\0';
+
+	if (strict_strtoul(buf, 10, &pid))
+		return(-EINVAL);
+
+	*this_pid = pid;
+
+	return cnt;
+}
+#endif
+
+#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
+    defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
+static ssize_t
+show_maxlatproc(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos)
+{
+	int r;
+	struct maxlatproc_data *mp = file->private_data;
+	int strmaxlen = (TASK_COMM_LEN * 2) + (8 * 8);
+	unsigned long long t;
+	unsigned long usecs, secs;
+	char *buf;
+
+	if (mp->pid == -1 || mp->current_pid == -1) {
+		buf = "(none)\n";
+		return simple_read_from_buffer(ubuf, cnt, ppos, buf,
+		    strlen(buf));
+	}
+
+	buf = kmalloc(strmaxlen, GFP_KERNEL);
+	if (buf == NULL)
+		return -ENOMEM;
+
+	t = ns2usecs(mp->timestamp);
+	usecs = do_div(t, USEC_PER_SEC);
+	secs = (unsigned long) t;
+	r = snprintf(buf, strmaxlen,
+	    "%d %d %ld (%ld) %s <- %d %d %s %lu.%06lu\n", mp->pid,
+	    MAX_RT_PRIO-1 - mp->prio, mp->latency, mp->timeroffset, mp->comm,
+	    mp->current_pid, MAX_RT_PRIO-1 - mp->current_prio, mp->current_comm,
+	    secs, usecs);
+	r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+	kfree(buf);
+	return r;
+}
+#endif
+
+static ssize_t
+show_enable(struct file *file, char __user *ubuf, size_t cnt, loff_t *ppos)
+{
+	char buf[64];
+	struct enable_data *ed = file->private_data;
+	int r;
+
+	r = snprintf(buf, sizeof(buf), "%d\n", ed->enabled);
+	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static ssize_t
+do_enable(struct file *file, const char __user *ubuf, size_t cnt, loff_t *ppos)
+{
+	char buf[64];
+	long enable;
+	struct enable_data *ed = file->private_data;
+
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
+
+	if (copy_from_user(&buf, ubuf, cnt))
+		return -EFAULT;
+
+	buf[cnt] = 0;
+
+	if (strict_strtol(buf, 10, &enable))
+		return(-EINVAL);
+
+	if ((enable && ed->enabled) || (!enable && !ed->enabled))
+		return cnt;
+
+	if (enable) {
+		int ret;
+
+		switch (ed->latency_type) {
+#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST)
+		case PREEMPTIRQSOFF_LATENCY:
+			ret = register_trace_preemptirqsoff_hist(
+			    probe_preemptirqsoff_hist, NULL);
+			if (ret) {
+				pr_info("wakeup trace: Couldn't assign "
+				    "probe_preemptirqsoff_hist "
+				    "to trace_preemptirqsoff_hist\n");
+				return ret;
+			}
+			break;
+#endif
+#ifdef CONFIG_WAKEUP_LATENCY_HIST
+		case WAKEUP_LATENCY:
+			ret = register_trace_sched_wakeup(
+			    probe_wakeup_latency_hist_start, NULL);
+			if (ret) {
+				pr_info("wakeup trace: Couldn't assign "
+				    "probe_wakeup_latency_hist_start "
+				    "to trace_sched_wakeup\n");
+				return ret;
+			}
+			ret = register_trace_sched_wakeup_new(
+			    probe_wakeup_latency_hist_start, NULL);
+			if (ret) {
+				pr_info("wakeup trace: Couldn't assign "
+				    "probe_wakeup_latency_hist_start "
+				    "to trace_sched_wakeup_new\n");
+				unregister_trace_sched_wakeup(
+				    probe_wakeup_latency_hist_start, NULL);
+				return ret;
+			}
+			ret = register_trace_sched_switch(
+			    probe_wakeup_latency_hist_stop, NULL);
+			if (ret) {
+				pr_info("wakeup trace: Couldn't assign "
+				    "probe_wakeup_latency_hist_stop "
+				    "to trace_sched_switch\n");
+				unregister_trace_sched_wakeup(
+				    probe_wakeup_latency_hist_start, NULL);
+				unregister_trace_sched_wakeup_new(
+				    probe_wakeup_latency_hist_start, NULL);
+				return ret;
+			}
+			ret = register_trace_sched_migrate_task(
+			    probe_sched_migrate_task, NULL);
+			if (ret) {
+				pr_info("wakeup trace: Couldn't assign "
+				    "probe_sched_migrate_task "
+				    "to trace_sched_migrate_task\n");
+				unregister_trace_sched_wakeup(
+				    probe_wakeup_latency_hist_start, NULL);
+				unregister_trace_sched_wakeup_new(
+				    probe_wakeup_latency_hist_start, NULL);
+				unregister_trace_sched_switch(
+				    probe_wakeup_latency_hist_stop, NULL);
+				return ret;
+			}
+			break;
+#endif
+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
+		case MISSED_TIMER_OFFSETS:
+			ret = register_trace_hrtimer_interrupt(
+			    probe_hrtimer_interrupt, NULL);
+			if (ret) {
+				pr_info("wakeup trace: Couldn't assign "
+				    "probe_hrtimer_interrupt "
+				    "to trace_hrtimer_interrupt\n");
+				return ret;
+			}
+			break;
+#endif
+#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \
+    defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
+		case TIMERANDWAKEUP_LATENCY:
+			if (!wakeup_latency_enabled_data.enabled ||
+			    !missed_timer_offsets_enabled_data.enabled)
+				return -EINVAL;
+			break;
+#endif
+		default:
+			break;
+		}
+	} else {
+		switch (ed->latency_type) {
+#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST)
+		case PREEMPTIRQSOFF_LATENCY:
+			{
+				int cpu;
+
+				unregister_trace_preemptirqsoff_hist(
+				    probe_preemptirqsoff_hist, NULL);
+				for_each_online_cpu(cpu) {
+#ifdef CONFIG_INTERRUPT_OFF_HIST
+					per_cpu(hist_irqsoff_counting,
+					    cpu) = 0;
+#endif
+#ifdef CONFIG_PREEMPT_OFF_HIST
+					per_cpu(hist_preemptoff_counting,
+					    cpu) = 0;
+#endif
+#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST)
+					per_cpu(hist_preemptirqsoff_counting,
+					    cpu) = 0;
+#endif
+				}
+			}
+			break;
+#endif
+#ifdef CONFIG_WAKEUP_LATENCY_HIST
+		case WAKEUP_LATENCY:
+			{
+				int cpu;
+
+				unregister_trace_sched_wakeup(
+				    probe_wakeup_latency_hist_start, NULL);
+				unregister_trace_sched_wakeup_new(
+				    probe_wakeup_latency_hist_start, NULL);
+				unregister_trace_sched_switch(
+				    probe_wakeup_latency_hist_stop, NULL);
+				unregister_trace_sched_migrate_task(
+				    probe_sched_migrate_task, NULL);
+
+				for_each_online_cpu(cpu) {
+					per_cpu(wakeup_task, cpu) = NULL;
+					per_cpu(wakeup_sharedprio, cpu) = 0;
+				}
+			}
+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
+			timerandwakeup_enabled_data.enabled = 0;
+#endif
+			break;
+#endif
+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
+		case MISSED_TIMER_OFFSETS:
+			unregister_trace_hrtimer_interrupt(
+			    probe_hrtimer_interrupt, NULL);
+#ifdef CONFIG_WAKEUP_LATENCY_HIST
+			timerandwakeup_enabled_data.enabled = 0;
+#endif
+			break;
+#endif
+		default:
+			break;
+		}
+	}
+	ed->enabled = enable;
+	return cnt;
+}
+
+static const struct file_operations latency_hist_reset_fops = {
+	.open = tracing_open_generic,
+	.write = latency_hist_reset,
+};
+
+static const struct file_operations enable_fops = {
+	.open = tracing_open_generic,
+	.read = show_enable,
+	.write = do_enable,
+};
+
+#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
+    defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
+static const struct file_operations pid_fops = {
+	.open = tracing_open_generic,
+	.read = show_pid,
+	.write = do_pid,
+};
+
+static const struct file_operations maxlatproc_fops = {
+	.open = tracing_open_generic,
+	.read = show_maxlatproc,
+};
+#endif
+
+#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST)
+static notrace void probe_preemptirqsoff_hist(void *v, int reason,
+    int starthist)
+{
+	int cpu = raw_smp_processor_id();
+	int time_set = 0;
+
+	if (starthist) {
+		cycle_t uninitialized_var(start);
+
+		if (!preempt_count() && !irqs_disabled())
+			return;
+
+#ifdef CONFIG_INTERRUPT_OFF_HIST
+		if ((reason == IRQS_OFF || reason == TRACE_START) &&
+		    !per_cpu(hist_irqsoff_counting, cpu)) {
+			per_cpu(hist_irqsoff_counting, cpu) = 1;
+			start = ftrace_now(cpu);
+			time_set++;
+			per_cpu(hist_irqsoff_start, cpu) = start;
+		}
+#endif
+
+#ifdef CONFIG_PREEMPT_OFF_HIST
+		if ((reason == PREEMPT_OFF || reason == TRACE_START) &&
+		    !per_cpu(hist_preemptoff_counting, cpu)) {
+			per_cpu(hist_preemptoff_counting, cpu) = 1;
+			if (!(time_set++))
+				start = ftrace_now(cpu);
+			per_cpu(hist_preemptoff_start, cpu) = start;
+		}
+#endif
+
+#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST)
+		if (per_cpu(hist_irqsoff_counting, cpu) &&
+		    per_cpu(hist_preemptoff_counting, cpu) &&
+		    !per_cpu(hist_preemptirqsoff_counting, cpu)) {
+			per_cpu(hist_preemptirqsoff_counting, cpu) = 1;
+			if (!time_set)
+				start = ftrace_now(cpu);
+			per_cpu(hist_preemptirqsoff_start, cpu) = start;
+		}
+#endif
+	} else {
+		cycle_t uninitialized_var(stop);
+
+#ifdef CONFIG_INTERRUPT_OFF_HIST
+		if ((reason == IRQS_ON || reason == TRACE_STOP) &&
+		    per_cpu(hist_irqsoff_counting, cpu)) {
+			cycle_t start = per_cpu(hist_irqsoff_start, cpu);
+
+			stop = ftrace_now(cpu);
+			time_set++;
+			if (start) {
+				long latency = ((long) (stop - start)) /
+				    NSECS_PER_USECS;
+
+				latency_hist(IRQSOFF_LATENCY, cpu, latency, 0,
+				    stop, NULL);
+			}
+			per_cpu(hist_irqsoff_counting, cpu) = 0;
+		}
+#endif
+
+#ifdef CONFIG_PREEMPT_OFF_HIST
+		if ((reason == PREEMPT_ON || reason == TRACE_STOP) &&
+		    per_cpu(hist_preemptoff_counting, cpu)) {
+			cycle_t start = per_cpu(hist_preemptoff_start, cpu);
+
+			if (!(time_set++))
+				stop = ftrace_now(cpu);
+			if (start) {
+				long latency = ((long) (stop - start)) /
+				    NSECS_PER_USECS;
+
+				latency_hist(PREEMPTOFF_LATENCY, cpu, latency,
+				    0, stop, NULL);
+			}
+			per_cpu(hist_preemptoff_counting, cpu) = 0;
+		}
+#endif
+
+#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST)
+		if ((!per_cpu(hist_irqsoff_counting, cpu) ||
+		     !per_cpu(hist_preemptoff_counting, cpu)) &&
+		   per_cpu(hist_preemptirqsoff_counting, cpu)) {
+			cycle_t start = per_cpu(hist_preemptirqsoff_start, cpu);
+
+			if (!time_set)
+				stop = ftrace_now(cpu);
+			if (start) {
+				long latency = ((long) (stop - start)) /
+				    NSECS_PER_USECS;
+
+				latency_hist(PREEMPTIRQSOFF_LATENCY, cpu,
+				    latency, 0, stop, NULL);
+			}
+			per_cpu(hist_preemptirqsoff_counting, cpu) = 0;
+		}
+#endif
+	}
+}
+#endif
+
+#ifdef CONFIG_WAKEUP_LATENCY_HIST
+static DEFINE_RAW_SPINLOCK(wakeup_lock);
+static notrace void probe_sched_migrate_task(void *v, struct task_struct *task,
+    int cpu)
+{
+	int old_cpu = task_cpu(task);
+
+	if (cpu != old_cpu) {
+		unsigned long flags;
+		struct task_struct *cpu_wakeup_task;
+
+		raw_spin_lock_irqsave(&wakeup_lock, flags);
+
+		cpu_wakeup_task = per_cpu(wakeup_task, old_cpu);
+		if (task == cpu_wakeup_task) {
+			put_task_struct(cpu_wakeup_task);
+			per_cpu(wakeup_task, old_cpu) = NULL;
+			cpu_wakeup_task = per_cpu(wakeup_task, cpu) = task;
+			get_task_struct(cpu_wakeup_task);
+		}
+
+		raw_spin_unlock_irqrestore(&wakeup_lock, flags);
+	}
+}
+
+static notrace void probe_wakeup_latency_hist_start(void *v,
+    struct task_struct *p, int success)
+{
+	unsigned long flags;
+	struct task_struct *curr = current;
+	int cpu = task_cpu(p);
+	struct task_struct *cpu_wakeup_task;
+
+	raw_spin_lock_irqsave(&wakeup_lock, flags);
+
+	cpu_wakeup_task = per_cpu(wakeup_task, cpu);
+
+	if (wakeup_pid) {
+		if ((cpu_wakeup_task && p->prio == cpu_wakeup_task->prio) ||
+		    p->prio == curr->prio)
+			per_cpu(wakeup_sharedprio, cpu) = 1;
+		if (likely(wakeup_pid != task_pid_nr(p)))
+			goto out;
+	} else {
+		if (likely(!rt_task(p)) ||
+		    (cpu_wakeup_task && p->prio > cpu_wakeup_task->prio) ||
+		    p->prio > curr->prio)
+			goto out;
+		if ((cpu_wakeup_task && p->prio == cpu_wakeup_task->prio) ||
+		    p->prio == curr->prio)
+			per_cpu(wakeup_sharedprio, cpu) = 1;
+	}
+
+	if (cpu_wakeup_task)
+		put_task_struct(cpu_wakeup_task);
+	cpu_wakeup_task = per_cpu(wakeup_task, cpu) = p;
+	get_task_struct(cpu_wakeup_task);
+	cpu_wakeup_task->preempt_timestamp_hist =
+		ftrace_now(raw_smp_processor_id());
+out:
+	raw_spin_unlock_irqrestore(&wakeup_lock, flags);
+}
+
+static notrace void probe_wakeup_latency_hist_stop(void *v,
+    struct task_struct *prev, struct task_struct *next)
+{
+	unsigned long flags;
+	int cpu = task_cpu(next);
+	long latency;
+	cycle_t stop;
+	struct task_struct *cpu_wakeup_task;
+
+	raw_spin_lock_irqsave(&wakeup_lock, flags);
+
+	cpu_wakeup_task = per_cpu(wakeup_task, cpu);
+
+	if (cpu_wakeup_task == NULL)
+		goto out;
+
+	/* Already running? */
+	if (unlikely(current == cpu_wakeup_task))
+		goto out_reset;
+
+	if (next != cpu_wakeup_task) {
+		if (next->prio < cpu_wakeup_task->prio)
+			goto out_reset;
+
+		if (next->prio == cpu_wakeup_task->prio)
+			per_cpu(wakeup_sharedprio, cpu) = 1;
+
+		goto out;
+	}
+
+	if (current->prio == cpu_wakeup_task->prio)
+		per_cpu(wakeup_sharedprio, cpu) = 1;
+
+	/*
+	 * The task we are waiting for is about to be switched to.
+	 * Calculate latency and store it in histogram.
+	 */
+	stop = ftrace_now(raw_smp_processor_id());
+
+	latency = ((long) (stop - next->preempt_timestamp_hist)) /
+	    NSECS_PER_USECS;
+
+	if (per_cpu(wakeup_sharedprio, cpu)) {
+		latency_hist(WAKEUP_LATENCY_SHAREDPRIO, cpu, latency, 0, stop,
+		    next);
+		per_cpu(wakeup_sharedprio, cpu) = 0;
+	} else {
+		latency_hist(WAKEUP_LATENCY, cpu, latency, 0, stop, next);
+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
+		if (timerandwakeup_enabled_data.enabled) {
+			latency_hist(TIMERANDWAKEUP_LATENCY, cpu,
+			    next->timer_offset + latency, next->timer_offset,
+			    stop, next);
+		}
+#endif
+	}
+
+out_reset:
+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
+	next->timer_offset = 0;
+#endif
+	put_task_struct(cpu_wakeup_task);
+	per_cpu(wakeup_task, cpu) = NULL;
+out:
+	raw_spin_unlock_irqrestore(&wakeup_lock, flags);
+}
+#endif
+
+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
+static notrace void probe_hrtimer_interrupt(void *v, int cpu,
+    long long latency_ns, struct task_struct *curr, struct task_struct *task)
+{
+	if (latency_ns <= 0 && task != NULL && rt_task(task) &&
+	    (task->prio < curr->prio ||
+	    (task->prio == curr->prio &&
+	    !cpumask_test_cpu(cpu, &task->cpus_allowed)))) {
+		long latency;
+		cycle_t now;
+
+		if (missed_timer_offsets_pid) {
+			if (likely(missed_timer_offsets_pid !=
+			    task_pid_nr(task)))
+				return;
+		}
+
+		now = ftrace_now(cpu);
+		latency = (long) div_s64(-latency_ns, NSECS_PER_USECS);
+		latency_hist(MISSED_TIMER_OFFSETS, cpu, latency, latency, now,
+		    task);
+#ifdef CONFIG_WAKEUP_LATENCY_HIST
+		task->timer_offset = latency;
+#endif
+	}
+}
+#endif
+
+static __init int latency_hist_init(void)
+{
+	struct dentry *latency_hist_root = NULL;
+	struct dentry *dentry;
+#ifdef CONFIG_WAKEUP_LATENCY_HIST
+	struct dentry *dentry_sharedprio;
+#endif
+	struct dentry *entry;
+	struct dentry *enable_root;
+	int i = 0;
+	struct hist_data *my_hist;
+	char name[64];
+	char *cpufmt = "CPU%d";
+#if defined(CONFIG_WAKEUP_LATENCY_HIST) || \
+    defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
+	char *cpufmt_maxlatproc = "max_latency-CPU%d";
+	struct maxlatproc_data *mp = NULL;
+#endif
+
+	dentry = tracing_init_dentry();
+	latency_hist_root = debugfs_create_dir(latency_hist_dir_root, dentry);
+	enable_root = debugfs_create_dir("enable", latency_hist_root);
+
+#ifdef CONFIG_INTERRUPT_OFF_HIST
+	dentry = debugfs_create_dir(irqsoff_hist_dir, latency_hist_root);
+	for_each_possible_cpu(i) {
+		sprintf(name, cpufmt, i);
+		entry = debugfs_create_file(name, 0444, dentry,
+		    &per_cpu(irqsoff_hist, i), &latency_hist_fops);
+		my_hist = &per_cpu(irqsoff_hist, i);
+		atomic_set(&my_hist->hist_mode, 1);
+		my_hist->min_lat = LONG_MAX;
+	}
+	entry = debugfs_create_file("reset", 0644, dentry,
+	    (void *)IRQSOFF_LATENCY, &latency_hist_reset_fops);
+#endif
+
+#ifdef CONFIG_PREEMPT_OFF_HIST
+	dentry = debugfs_create_dir(preemptoff_hist_dir,
+	    latency_hist_root);
+	for_each_possible_cpu(i) {
+		sprintf(name, cpufmt, i);
+		entry = debugfs_create_file(name, 0444, dentry,
+		    &per_cpu(preemptoff_hist, i), &latency_hist_fops);
+		my_hist = &per_cpu(preemptoff_hist, i);
+		atomic_set(&my_hist->hist_mode, 1);
+		my_hist->min_lat = LONG_MAX;
+	}
+	entry = debugfs_create_file("reset", 0644, dentry,
+	    (void *)PREEMPTOFF_LATENCY, &latency_hist_reset_fops);
+#endif
+
+#if defined(CONFIG_INTERRUPT_OFF_HIST) && defined(CONFIG_PREEMPT_OFF_HIST)
+	dentry = debugfs_create_dir(preemptirqsoff_hist_dir,
+	    latency_hist_root);
+	for_each_possible_cpu(i) {
+		sprintf(name, cpufmt, i);
+		entry = debugfs_create_file(name, 0444, dentry,
+		    &per_cpu(preemptirqsoff_hist, i), &latency_hist_fops);
+		my_hist = &per_cpu(preemptirqsoff_hist, i);
+		atomic_set(&my_hist->hist_mode, 1);
+		my_hist->min_lat = LONG_MAX;
+	}
+	entry = debugfs_create_file("reset", 0644, dentry,
+	    (void *)PREEMPTIRQSOFF_LATENCY, &latency_hist_reset_fops);
+#endif
+
+#if defined(CONFIG_INTERRUPT_OFF_HIST) || defined(CONFIG_PREEMPT_OFF_HIST)
+	entry = debugfs_create_file("preemptirqsoff", 0644,
+	    enable_root, (void *)&preemptirqsoff_enabled_data,
+	    &enable_fops);
+#endif
+
+#ifdef CONFIG_WAKEUP_LATENCY_HIST
+	dentry = debugfs_create_dir(wakeup_latency_hist_dir,
+	    latency_hist_root);
+	dentry_sharedprio = debugfs_create_dir(
+	    wakeup_latency_hist_dir_sharedprio, dentry);
+	for_each_possible_cpu(i) {
+		sprintf(name, cpufmt, i);
+
+		entry = debugfs_create_file(name, 0444, dentry,
+		    &per_cpu(wakeup_latency_hist, i),
+		    &latency_hist_fops);
+		my_hist = &per_cpu(wakeup_latency_hist, i);
+		atomic_set(&my_hist->hist_mode, 1);
+		my_hist->min_lat = LONG_MAX;
+
+		entry = debugfs_create_file(name, 0444, dentry_sharedprio,
+		    &per_cpu(wakeup_latency_hist_sharedprio, i),
+		    &latency_hist_fops);
+		my_hist = &per_cpu(wakeup_latency_hist_sharedprio, i);
+		atomic_set(&my_hist->hist_mode, 1);
+		my_hist->min_lat = LONG_MAX;
+
+		sprintf(name, cpufmt_maxlatproc, i);
+
+		mp = &per_cpu(wakeup_maxlatproc, i);
+		entry = debugfs_create_file(name, 0444, dentry, mp,
+		    &maxlatproc_fops);
+		clear_maxlatprocdata(mp);
+
+		mp = &per_cpu(wakeup_maxlatproc_sharedprio, i);
+		entry = debugfs_create_file(name, 0444, dentry_sharedprio, mp,
+		    &maxlatproc_fops);
+		clear_maxlatprocdata(mp);
+	}
+	entry = debugfs_create_file("pid", 0644, dentry,
+	    (void *)&wakeup_pid, &pid_fops);
+	entry = debugfs_create_file("reset", 0644, dentry,
+	    (void *)WAKEUP_LATENCY, &latency_hist_reset_fops);
+	entry = debugfs_create_file("reset", 0644, dentry_sharedprio,
+	    (void *)WAKEUP_LATENCY_SHAREDPRIO, &latency_hist_reset_fops);
+	entry = debugfs_create_file("wakeup", 0644,
+	    enable_root, (void *)&wakeup_latency_enabled_data,
+	    &enable_fops);
+#endif
+
+#ifdef CONFIG_MISSED_TIMER_OFFSETS_HIST
+	dentry = debugfs_create_dir(missed_timer_offsets_dir,
+	    latency_hist_root);
+	for_each_possible_cpu(i) {
+		sprintf(name, cpufmt, i);
+		entry = debugfs_create_file(name, 0444, dentry,
+		    &per_cpu(missed_timer_offsets, i), &latency_hist_fops);
+		my_hist = &per_cpu(missed_timer_offsets, i);
+		atomic_set(&my_hist->hist_mode, 1);
+		my_hist->min_lat = LONG_MAX;
+
+		sprintf(name, cpufmt_maxlatproc, i);
+		mp = &per_cpu(missed_timer_offsets_maxlatproc, i);
+		entry = debugfs_create_file(name, 0444, dentry, mp,
+		    &maxlatproc_fops);
+		clear_maxlatprocdata(mp);
+	}
+	entry = debugfs_create_file("pid", 0644, dentry,
+	    (void *)&missed_timer_offsets_pid, &pid_fops);
+	entry = debugfs_create_file("reset", 0644, dentry,
+	    (void *)MISSED_TIMER_OFFSETS, &latency_hist_reset_fops);
+	entry = debugfs_create_file("missed_timer_offsets", 0644,
+	    enable_root, (void *)&missed_timer_offsets_enabled_data,
+	    &enable_fops);
+#endif
+
+#if defined(CONFIG_WAKEUP_LATENCY_HIST) && \
+    defined(CONFIG_MISSED_TIMER_OFFSETS_HIST)
+	dentry = debugfs_create_dir(timerandwakeup_latency_hist_dir,
+	    latency_hist_root);
+	for_each_possible_cpu(i) {
+		sprintf(name, cpufmt, i);
+		entry = debugfs_create_file(name, 0444, dentry,
+		    &per_cpu(timerandwakeup_latency_hist, i),
+		    &latency_hist_fops);
+		my_hist = &per_cpu(timerandwakeup_latency_hist, i);
+		atomic_set(&my_hist->hist_mode, 1);
+		my_hist->min_lat = LONG_MAX;
+
+		sprintf(name, cpufmt_maxlatproc, i);
+		mp = &per_cpu(timerandwakeup_maxlatproc, i);
+		entry = debugfs_create_file(name, 0444, dentry, mp,
+		    &maxlatproc_fops);
+		clear_maxlatprocdata(mp);
+	}
+	entry = debugfs_create_file("reset", 0644, dentry,
+	    (void *)TIMERANDWAKEUP_LATENCY, &latency_hist_reset_fops);
+	entry = debugfs_create_file("timerandwakeup", 0644,
+	    enable_root, (void *)&timerandwakeup_enabled_data,
+	    &enable_fops);
+#endif
+	return 0;
+}
+
+__initcall(latency_hist_init);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index b252661..f3856c2 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -478,7 +478,7 @@
 	int				cpu;
 	atomic_t			record_disabled;
 	struct ring_buffer		*buffer;
-	raw_spinlock_t			reader_lock;	/* serialize readers */
+	spinlock_t			reader_lock;	/* serialize readers */
 	arch_spinlock_t			lock;
 	struct lock_class_key		lock_key;
 	struct list_head		*pages;
@@ -1049,6 +1049,44 @@
 	return -ENOMEM;
 }
 
+static inline int ok_to_lock(void)
+{
+	if (in_nmi())
+		return 0;
+#ifdef CONFIG_PREEMPT_RT_FULL
+	if (in_atomic() || irqs_disabled())
+		return 0;
+#endif
+	return 1;
+}
+
+static int
+read_buffer_lock(struct ring_buffer_per_cpu *cpu_buffer,
+		 unsigned long *flags)
+{
+	/*
+	 * If an NMI die dumps out the content of the ring buffer
+	 * do not grab locks. We also permanently disable the ring
+	 * buffer too. A one time deal is all you get from reading
+	 * the ring buffer from an NMI.
+	 */
+	if (!ok_to_lock()) {
+		if (spin_trylock_irqsave(&cpu_buffer->reader_lock, *flags))
+			return 1;
+		tracing_off_permanent();
+		return 0;
+	}
+	spin_lock_irqsave(&cpu_buffer->reader_lock, *flags);
+	return 1;
+}
+
+static void
+read_buffer_unlock(struct ring_buffer_per_cpu *cpu_buffer,
+		   unsigned long flags, int locked)
+{
+	if (locked)
+		spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+}
 static struct ring_buffer_per_cpu *
 rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
 {
@@ -1064,7 +1102,7 @@
 
 	cpu_buffer->cpu = cpu;
 	cpu_buffer->buffer = buffer;
-	raw_spin_lock_init(&cpu_buffer->reader_lock);
+	spin_lock_init(&cpu_buffer->reader_lock);
 	lockdep_set_class(&cpu_buffer->reader_lock, buffer->reader_lock_key);
 	cpu_buffer->lock = (arch_spinlock_t)__ARCH_SPIN_LOCK_UNLOCKED;
 
@@ -1259,9 +1297,11 @@
 {
 	struct buffer_page *bpage;
 	struct list_head *p;
+	unsigned long flags;
 	unsigned i;
+	int locked;
 
-	raw_spin_lock_irq(&cpu_buffer->reader_lock);
+	locked = read_buffer_lock(cpu_buffer, &flags);
 	rb_head_page_deactivate(cpu_buffer);
 
 	for (i = 0; i < nr_pages; i++) {
@@ -1279,7 +1319,7 @@
 	rb_check_pages(cpu_buffer);
 
 out:
-	raw_spin_unlock_irq(&cpu_buffer->reader_lock);
+	read_buffer_unlock(cpu_buffer, flags, locked);
 }
 
 static void
@@ -1288,9 +1328,11 @@
 {
 	struct buffer_page *bpage;
 	struct list_head *p;
+	unsigned long flags;
 	unsigned i;
+	int locked;
 
-	raw_spin_lock_irq(&cpu_buffer->reader_lock);
+	locked = read_buffer_lock(cpu_buffer, &flags);
 	rb_head_page_deactivate(cpu_buffer);
 
 	for (i = 0; i < nr_pages; i++) {
@@ -1305,7 +1347,7 @@
 	rb_check_pages(cpu_buffer);
 
 out:
-	raw_spin_unlock_irq(&cpu_buffer->reader_lock);
+	read_buffer_unlock(cpu_buffer, flags, locked);
 }
 
 /**
@@ -2696,7 +2738,7 @@
 		return 0;
 
 	cpu_buffer = buffer->buffers[cpu];
-	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
 	/*
 	 * if the tail is on reader_page, oldest time stamp is on the reader
 	 * page
@@ -2707,7 +2749,7 @@
 		bpage = rb_set_head_page(cpu_buffer);
 	if (bpage)
 		ret = bpage->page->time_stamp;
-	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+	spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
 
 	return ret;
 }
@@ -2866,15 +2908,16 @@
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	unsigned long flags;
+	int locked;
 
 	if (!iter)
 		return;
 
 	cpu_buffer = iter->cpu_buffer;
 
-	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	locked = read_buffer_lock(cpu_buffer, &flags);
 	rb_iter_reset(iter);
-	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+	read_buffer_unlock(cpu_buffer, flags, locked);
 }
 EXPORT_SYMBOL_GPL(ring_buffer_iter_reset);
 
@@ -3296,21 +3339,6 @@
 }
 EXPORT_SYMBOL_GPL(ring_buffer_iter_peek);
 
-static inline int rb_ok_to_lock(void)
-{
-	/*
-	 * If an NMI die dumps out the content of the ring buffer
-	 * do not grab locks. We also permanently disable the ring
-	 * buffer too. A one time deal is all you get from reading
-	 * the ring buffer from an NMI.
-	 */
-	if (likely(!in_nmi()))
-		return 1;
-
-	tracing_off_permanent();
-	return 0;
-}
-
 /**
  * ring_buffer_peek - peek at the next event to be read
  * @buffer: The ring buffer to read
@@ -3328,22 +3356,17 @@
 	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
 	struct ring_buffer_event *event;
 	unsigned long flags;
-	int dolock;
+	int locked;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return NULL;
 
-	dolock = rb_ok_to_lock();
  again:
-	local_irq_save(flags);
-	if (dolock)
-		raw_spin_lock(&cpu_buffer->reader_lock);
+	locked = read_buffer_lock(cpu_buffer, &flags);
 	event = rb_buffer_peek(cpu_buffer, ts, lost_events);
 	if (event && event->type_len == RINGBUF_TYPE_PADDING)
 		rb_advance_reader(cpu_buffer);
-	if (dolock)
-		raw_spin_unlock(&cpu_buffer->reader_lock);
-	local_irq_restore(flags);
+	read_buffer_unlock(cpu_buffer, flags, locked);
 
 	if (event && event->type_len == RINGBUF_TYPE_PADDING)
 		goto again;
@@ -3365,11 +3388,12 @@
 	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
 	struct ring_buffer_event *event;
 	unsigned long flags;
+	int locked;
 
  again:
-	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	locked = read_buffer_lock(cpu_buffer, &flags);
 	event = rb_iter_peek(iter, ts);
-	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+	read_buffer_unlock(cpu_buffer, flags, locked);
 
 	if (event && event->type_len == RINGBUF_TYPE_PADDING)
 		goto again;
@@ -3395,9 +3419,7 @@
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct ring_buffer_event *event = NULL;
 	unsigned long flags;
-	int dolock;
-
-	dolock = rb_ok_to_lock();
+	int locked;
 
  again:
 	/* might be called in atomic */
@@ -3407,9 +3429,7 @@
 		goto out;
 
 	cpu_buffer = buffer->buffers[cpu];
-	local_irq_save(flags);
-	if (dolock)
-		raw_spin_lock(&cpu_buffer->reader_lock);
+	locked = read_buffer_lock(cpu_buffer, &flags);
 
 	event = rb_buffer_peek(cpu_buffer, ts, lost_events);
 	if (event) {
@@ -3417,9 +3437,8 @@
 		rb_advance_reader(cpu_buffer);
 	}
 
-	if (dolock)
-		raw_spin_unlock(&cpu_buffer->reader_lock);
-	local_irq_restore(flags);
+	read_buffer_unlock(cpu_buffer, flags, locked);
+
 
  out:
 	preempt_enable();
@@ -3504,17 +3523,18 @@
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	unsigned long flags;
+	int locked;
 
 	if (!iter)
 		return;
 
 	cpu_buffer = iter->cpu_buffer;
 
-	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	locked = read_buffer_lock(cpu_buffer, &flags);
 	arch_spin_lock(&cpu_buffer->lock);
 	rb_iter_reset(iter);
 	arch_spin_unlock(&cpu_buffer->lock);
-	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+	read_buffer_unlock(cpu_buffer, flags, locked);
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read_start);
 
@@ -3548,8 +3568,9 @@
 	struct ring_buffer_event *event;
 	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
 	unsigned long flags;
+	int locked;
 
-	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	locked = read_buffer_lock(cpu_buffer, &flags);
  again:
 	event = rb_iter_peek(iter, ts);
 	if (!event)
@@ -3560,7 +3581,7 @@
 
 	rb_advance_iter(iter);
  out:
-	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+	read_buffer_unlock(cpu_buffer, flags, locked);
 
 	return event;
 }
@@ -3625,13 +3646,14 @@
 {
 	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
 	unsigned long flags;
+	int locked;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return;
 
 	atomic_inc(&cpu_buffer->record_disabled);
 
-	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	locked = read_buffer_lock(cpu_buffer, &flags);
 
 	if (RB_WARN_ON(cpu_buffer, local_read(&cpu_buffer->committing)))
 		goto out;
@@ -3643,7 +3665,7 @@
 	arch_spin_unlock(&cpu_buffer->lock);
 
  out:
-	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+	read_buffer_unlock(cpu_buffer, flags, locked);
 
 	atomic_dec(&cpu_buffer->record_disabled);
 }
@@ -3670,22 +3692,16 @@
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	unsigned long flags;
-	int dolock;
+	int locked;
 	int cpu;
 	int ret;
 
-	dolock = rb_ok_to_lock();
-
 	/* yes this is racy, but if you don't like the race, lock the buffer */
 	for_each_buffer_cpu(buffer, cpu) {
 		cpu_buffer = buffer->buffers[cpu];
-		local_irq_save(flags);
-		if (dolock)
-			raw_spin_lock(&cpu_buffer->reader_lock);
+		locked = read_buffer_lock(cpu_buffer, &flags);
 		ret = rb_per_cpu_empty(cpu_buffer);
-		if (dolock)
-			raw_spin_unlock(&cpu_buffer->reader_lock);
-		local_irq_restore(flags);
+		read_buffer_unlock(cpu_buffer, flags, locked);
 
 		if (!ret)
 			return 0;
@@ -3704,22 +3720,16 @@
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	unsigned long flags;
-	int dolock;
+	int locked;
 	int ret;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
 		return 1;
 
-	dolock = rb_ok_to_lock();
-
 	cpu_buffer = buffer->buffers[cpu];
-	local_irq_save(flags);
-	if (dolock)
-		raw_spin_lock(&cpu_buffer->reader_lock);
+	locked = read_buffer_lock(cpu_buffer, &flags);
 	ret = rb_per_cpu_empty(cpu_buffer);
-	if (dolock)
-		raw_spin_unlock(&cpu_buffer->reader_lock);
-	local_irq_restore(flags);
+	read_buffer_unlock(cpu_buffer, flags, locked);
 
 	return ret;
 }
@@ -3894,6 +3904,7 @@
 	unsigned int commit;
 	unsigned int read;
 	u64 save_timestamp;
+	int locked;
 	int ret = -1;
 
 	if (!cpumask_test_cpu(cpu, buffer->cpumask))
@@ -3915,7 +3926,7 @@
 	if (!bpage)
 		goto out;
 
-	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	locked = read_buffer_lock(cpu_buffer, &flags);
 
 	reader = rb_get_reader_page(cpu_buffer);
 	if (!reader)
@@ -4039,7 +4050,7 @@
 		memset(&bpage->data[commit], 0, BUF_PAGE_SIZE - commit);
 
  out_unlock:
-	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+	read_buffer_unlock(cpu_buffer, flags, locked);
 
  out:
 	return ret;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 0c348a6..6b42a96 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -359,11 +359,13 @@
  */
 void trace_wake_up(void)
 {
+#ifndef CONFIG_PREEMPT_RT_FULL
 	const unsigned long delay = msecs_to_jiffies(2);
 
 	if (trace_flags & TRACE_ITER_BLOCK)
 		return;
 	schedule_delayed_work(&wakeup_work, delay);
+#endif
 }
 
 static int __init set_buf_size(char *str)
@@ -731,6 +733,12 @@
 }
 #endif /* CONFIG_TRACER_MAX_TRACE */
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+static void default_wait_pipe(struct trace_iterator *iter);
+#else
+#define default_wait_pipe	poll_wait_pipe
+#endif
+
 /**
  * register_tracer - register a tracer with the ftrace system.
  * @type - the plugin for the tracer
@@ -1135,6 +1143,8 @@
 		((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) |
 		((pc & SOFTIRQ_MASK) ? TRACE_FLAG_SOFTIRQ : 0) |
 		(need_resched() ? TRACE_FLAG_NEED_RESCHED : 0);
+
+	entry->migrate_disable	= (tsk) ? __migrate_disabled(tsk) & 0xFF : 0;
 }
 EXPORT_SYMBOL_GPL(tracing_generic_entry_update);
 
@@ -1866,9 +1876,10 @@
 	seq_puts(m, "#                | / _----=> need-resched    \n");
 	seq_puts(m, "#                || / _---=> hardirq/softirq \n");
 	seq_puts(m, "#                ||| / _--=> preempt-depth   \n");
-	seq_puts(m, "#                |||| /     delay             \n");
-	seq_puts(m, "#  cmd     pid   ||||| time  |   caller      \n");
-	seq_puts(m, "#     \\   /      |||||  \\    |   /           \n");
+	seq_puts(m, "#                |||| / _--=> migrate-disable\n");
+	seq_puts(m, "#                ||||| /     delay           \n");
+	seq_puts(m, "#  cmd     pid   |||||| time  |   caller     \n");
+	seq_puts(m, "#     \\   /      |||||  \\   |   /          \n");
 }
 
 static void print_func_help_header(struct seq_file *m)
@@ -3233,6 +3244,7 @@
 	return 0;
 }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 static unsigned int
 tracing_poll_pipe(struct file *filp, poll_table *poll_table)
 {
@@ -3252,8 +3264,7 @@
 	}
 }
 
-
-void default_wait_pipe(struct trace_iterator *iter)
+static void default_wait_pipe(struct trace_iterator *iter)
 {
 	DEFINE_WAIT(wait);
 
@@ -3264,6 +3275,20 @@
 
 	finish_wait(&trace_wait, &wait);
 }
+#else
+static unsigned int
+tracing_poll_pipe(struct file *filp, poll_table *poll_table)
+{
+	struct trace_iterator *iter = filp->private_data;
+
+	if ((trace_flags & TRACE_ITER_BLOCK) || !trace_empty(iter))
+		return POLLIN | POLLRDNORM;
+	poll_wait_pipe(iter);
+	if (!trace_empty(iter))
+		return POLLIN | POLLRDNORM;
+	return 0;
+}
+#endif
 
 /*
  * This is a make-shift waitqueue.
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index c3c3f6b..776e43d 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -349,7 +349,6 @@
 
 void tracing_iter_reset(struct trace_iterator *iter, int cpu);
 
-void default_wait_pipe(struct trace_iterator *iter);
 void poll_wait_pipe(struct trace_iterator *iter);
 
 void ftrace(struct trace_array *tr,
diff --git a/kernel/trace/trace_clock.c b/kernel/trace/trace_clock.c
index 3947835..1bbb1b2 100644
--- a/kernel/trace/trace_clock.c
+++ b/kernel/trace/trace_clock.c
@@ -44,6 +44,7 @@
 
 	return clock;
 }
+EXPORT_SYMBOL_GPL(trace_clock_local);
 
 /*
  * trace_clock(): 'between' trace clock. Not completely serialized,
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 875fed4..b203aae 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -116,7 +116,8 @@
 	__common_field(unsigned char, flags);
 	__common_field(unsigned char, preempt_count);
 	__common_field(int, pid);
-	__common_field(int, padding);
+	__common_field(unsigned short, migrate_disable);
+	__common_field(unsigned short, padding);
 
 	return ret;
 }
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 1626e1a..35882e7 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -17,6 +17,7 @@
 #include <linux/fs.h>
 
 #include "trace.h"
+#include <trace/events/hist.h>
 
 static struct trace_array		*irqsoff_trace __read_mostly;
 static int				tracer_enabled __read_mostly;
@@ -426,11 +427,13 @@
 {
 	if (preempt_trace() || irq_trace())
 		start_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
+	trace_preemptirqsoff_hist(TRACE_START, 1);
 }
 EXPORT_SYMBOL_GPL(start_critical_timings);
 
 void stop_critical_timings(void)
 {
+	trace_preemptirqsoff_hist(TRACE_STOP, 0);
 	if (preempt_trace() || irq_trace())
 		stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
 }
@@ -440,6 +443,7 @@
 #ifdef CONFIG_PROVE_LOCKING
 void time_hardirqs_on(unsigned long a0, unsigned long a1)
 {
+	trace_preemptirqsoff_hist(IRQS_ON, 0);
 	if (!preempt_trace() && irq_trace())
 		stop_critical_timing(a0, a1);
 }
@@ -448,6 +452,7 @@
 {
 	if (!preempt_trace() && irq_trace())
 		start_critical_timing(a0, a1);
+	trace_preemptirqsoff_hist(IRQS_OFF, 1);
 }
 
 #else /* !CONFIG_PROVE_LOCKING */
@@ -473,6 +478,7 @@
  */
 void trace_hardirqs_on(void)
 {
+	trace_preemptirqsoff_hist(IRQS_ON, 0);
 	if (!preempt_trace() && irq_trace())
 		stop_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
 }
@@ -482,11 +488,13 @@
 {
 	if (!preempt_trace() && irq_trace())
 		start_critical_timing(CALLER_ADDR0, CALLER_ADDR1);
+	trace_preemptirqsoff_hist(IRQS_OFF, 1);
 }
 EXPORT_SYMBOL(trace_hardirqs_off);
 
 void trace_hardirqs_on_caller(unsigned long caller_addr)
 {
+	trace_preemptirqsoff_hist(IRQS_ON, 0);
 	if (!preempt_trace() && irq_trace())
 		stop_critical_timing(CALLER_ADDR0, caller_addr);
 }
@@ -496,6 +504,7 @@
 {
 	if (!preempt_trace() && irq_trace())
 		start_critical_timing(CALLER_ADDR0, caller_addr);
+	trace_preemptirqsoff_hist(IRQS_OFF, 1);
 }
 EXPORT_SYMBOL(trace_hardirqs_off_caller);
 
@@ -505,12 +514,14 @@
 #ifdef CONFIG_PREEMPT_TRACER
 void trace_preempt_on(unsigned long a0, unsigned long a1)
 {
+	trace_preemptirqsoff_hist(PREEMPT_ON, 0);
 	if (preempt_trace() && !irq_trace())
 		stop_critical_timing(a0, a1);
 }
 
 void trace_preempt_off(unsigned long a0, unsigned long a1)
 {
+	trace_preemptirqsoff_hist(PREEMPT_ON, 1);
 	if (preempt_trace() && !irq_trace())
 		start_critical_timing(a0, a1);
 }
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 1dcf253..bb9a58d 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -591,6 +591,11 @@
 	else
 		ret = trace_seq_putc(s, '.');
 
+	if (entry->migrate_disable)
+		ret = trace_seq_printf(s, "%x", entry->migrate_disable);
+	else
+		ret = trace_seq_putc(s, '.');
+
 	return ret;
 }
 
diff --git a/kernel/user.c b/kernel/user.c
index 71dd236..b831e51 100644
--- a/kernel/user.c
+++ b/kernel/user.c
@@ -129,11 +129,11 @@
 	if (!up)
 		return;
 
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 	if (atomic_dec_and_lock(&up->__count, &uidhash_lock))
 		free_user(up, flags);
 	else
-		local_irq_restore(flags);
+		local_irq_restore_nort(flags);
 }
 
 struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid)
diff --git a/kernel/wait-simple.c b/kernel/wait-simple.c
new file mode 100644
index 0000000..c35ec78
--- /dev/null
+++ b/kernel/wait-simple.c
@@ -0,0 +1,119 @@
+/*
+ * Simple waitqueues without fancy flags and callbacks
+ *
+ * (C) 2011 Thomas Gleixner <tglx@linutronix.de>
+ *
+ * Based on kernel/wait.c
+ *
+ * For licencing details see kernel-base/COPYING
+ */
+#include <linux/init.h>
+#include <linux/export.h>
+#include <linux/sched.h>
+#include <linux/wait-simple.h>
+
+/* Adds w to head->list. Must be called with head->lock locked. */
+static inline void __swait_enqueue(struct swait_head *head, struct swaiter *w)
+{
+	list_add(&w->node, &head->list);
+}
+
+/* Removes w from head->list. Must be called with head->lock locked. */
+static inline void __swait_dequeue(struct swaiter *w)
+{
+	list_del_init(&w->node);
+}
+
+/* Check whether a head has waiters enqueued */
+static inline bool swait_head_has_waiters(struct swait_head *h)
+{
+	return !list_empty(&h->list);
+}
+
+void __init_swait_head(struct swait_head *head, struct lock_class_key *key)
+{
+	raw_spin_lock_init(&head->lock);
+	lockdep_set_class(&head->lock, key);
+	INIT_LIST_HEAD(&head->list);
+}
+EXPORT_SYMBOL_GPL(__init_swait_head);
+
+void swait_prepare_locked(struct swait_head *head, struct swaiter *w)
+{
+	w->task = current;
+	if (list_empty(&w->node))
+		__swait_enqueue(head, w);
+}
+
+void swait_prepare(struct swait_head *head, struct swaiter *w, int state)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&head->lock, flags);
+	swait_prepare_locked(head, w);
+	__set_current_state(state);
+	raw_spin_unlock_irqrestore(&head->lock, flags);
+}
+EXPORT_SYMBOL_GPL(swait_prepare);
+
+void swait_finish_locked(struct swait_head *head, struct swaiter *w)
+{
+	__set_current_state(TASK_RUNNING);
+	if (w->task)
+		__swait_dequeue(w);
+}
+
+void swait_finish(struct swait_head *head, struct swaiter *w)
+{
+	unsigned long flags;
+
+	__set_current_state(TASK_RUNNING);
+	if (w->task) {
+		raw_spin_lock_irqsave(&head->lock, flags);
+		__swait_dequeue(w);
+		raw_spin_unlock_irqrestore(&head->lock, flags);
+	}
+}
+EXPORT_SYMBOL_GPL(swait_finish);
+
+unsigned int
+__swait_wake_locked(struct swait_head *head, unsigned int state, unsigned int num)
+{
+	struct swaiter *curr, *next;
+	int woken = 0;
+
+	list_for_each_entry_safe(curr, next, &head->list, node) {
+		if (wake_up_state(curr->task, state)) {
+			__swait_dequeue(curr);
+			/*
+			 * The waiting task can free the waiter as
+			 * soon as curr->task = NULL is written,
+			 * without taking any locks. A memory barrier
+			 * is required here to prevent the following
+			 * store to curr->task from getting ahead of
+			 * the dequeue operation.
+			 */
+			smp_wmb();
+			curr->task = NULL;
+			if (++woken == num)
+				break;
+		}
+	}
+	return woken;
+}
+
+unsigned int
+__swait_wake(struct swait_head *head, unsigned int state, unsigned int num)
+{
+	unsigned long flags;
+	int woken;
+
+	if (!swait_head_has_waiters(head))
+		return 0;
+
+	raw_spin_lock_irqsave(&head->lock, flags);
+	woken = __swait_wake_locked(head, state, num);
+	raw_spin_unlock_irqrestore(&head->lock, flags);
+	return woken;
+}
+EXPORT_SYMBOL_GPL(__swait_wake);
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index a8bc4d9..3a4d0bc 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -201,6 +201,8 @@
 
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
 
+static DEFINE_RAW_SPINLOCK(watchdog_output_lock);
+
 static struct perf_event_attr wd_hw_attr = {
 	.type		= PERF_TYPE_HARDWARE,
 	.config		= PERF_COUNT_HW_CPU_CYCLES,
@@ -235,10 +237,19 @@
 		if (__this_cpu_read(hard_watchdog_warn) == true)
 			return;
 
-		if (hardlockup_panic)
+		/*
+		 * If early-printk is enabled then make sure we do not
+		 * lock up in printk() and kill console logging:
+		 */
+		printk_kill();
+
+		if (hardlockup_panic) {
 			panic("Watchdog detected hard LOCKUP on cpu %d", this_cpu);
-		else
+		} else {
+			raw_spin_lock(&watchdog_output_lock);
 			WARN(1, "Watchdog detected hard LOCKUP on cpu %d", this_cpu);
+			raw_spin_unlock(&watchdog_output_lock);
+		}
 
 		__this_cpu_write(hard_watchdog_warn, true);
 		return;
@@ -425,6 +436,7 @@
 	WARN_ON(per_cpu(softlockup_watchdog, cpu));
 	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	hrtimer->function = watchdog_timer_fn;
+	hrtimer->irqsafe = 1;
 }
 
 static int watchdog_enable(int cpu)
diff --git a/kernel/work-simple.c b/kernel/work-simple.c
new file mode 100644
index 0000000..c996f75
--- /dev/null
+++ b/kernel/work-simple.c
@@ -0,0 +1,172 @@
+/*
+ * Copyright (C) 2014 BMW Car IT GmbH, Daniel Wagner daniel.wagner@bmw-carit.de
+ *
+ * Provides a framework for enqueuing callbacks from irq context
+ * PREEMPT_RT_FULL safe. The callbacks are executed in kthread context.
+ */
+
+#include <linux/wait-simple.h>
+#include <linux/work-simple.h>
+#include <linux/kthread.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#define SWORK_EVENT_PENDING     (1 << 0)
+
+static DEFINE_MUTEX(worker_mutex);
+static struct sworker *glob_worker;
+
+struct sworker {
+	struct list_head events;
+	struct swait_head wq;
+
+	raw_spinlock_t lock;
+
+	struct task_struct *task;
+	int refs;
+};
+
+static bool swork_readable(struct sworker *worker)
+{
+	bool r;
+
+	if (kthread_should_stop())
+		return true;
+
+	raw_spin_lock_irq(&worker->lock);
+	r = !list_empty(&worker->events);
+	raw_spin_unlock_irq(&worker->lock);
+
+	return r;
+}
+
+static int swork_kthread(void *arg)
+{
+	struct sworker *worker = arg;
+
+	for (;;) {
+		swait_event_interruptible(worker->wq,
+					swork_readable(worker));
+		if (kthread_should_stop())
+			break;
+
+		raw_spin_lock_irq(&worker->lock);
+		while (!list_empty(&worker->events)) {
+			struct swork_event *sev;
+
+			sev = list_first_entry(&worker->events,
+					struct swork_event, item);
+			list_del(&sev->item);
+			raw_spin_unlock_irq(&worker->lock);
+
+			WARN_ON_ONCE(!test_and_clear_bit(SWORK_EVENT_PENDING,
+							 &sev->flags));
+			sev->func(sev);
+			raw_spin_lock_irq(&worker->lock);
+		}
+		raw_spin_unlock_irq(&worker->lock);
+	}
+	return 0;
+}
+
+static struct sworker *swork_create(void)
+{
+	struct sworker *worker;
+
+	worker = kzalloc(sizeof(*worker), GFP_KERNEL);
+	if (!worker)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_LIST_HEAD(&worker->events);
+	raw_spin_lock_init(&worker->lock);
+	init_swait_head(&worker->wq);
+
+	worker->task = kthread_run(swork_kthread, worker, "kswork");
+	if (IS_ERR(worker->task)) {
+		kfree(worker);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	return worker;
+}
+
+static void swork_destroy(struct sworker *worker)
+{
+	kthread_stop(worker->task);
+
+	WARN_ON(!list_empty(&worker->events));
+	kfree(worker);
+}
+
+/**
+ * swork_queue - queue swork
+ *
+ * Returns %false if @work was already on a queue, %true otherwise.
+ *
+ * The work is queued and processed on a random CPU
+ */
+bool swork_queue(struct swork_event *sev)
+{
+	unsigned long flags;
+
+	if (test_and_set_bit(SWORK_EVENT_PENDING, &sev->flags))
+		return false;
+
+	raw_spin_lock_irqsave(&glob_worker->lock, flags);
+	list_add_tail(&sev->item, &glob_worker->events);
+	raw_spin_unlock_irqrestore(&glob_worker->lock, flags);
+
+	swait_wake(&glob_worker->wq);
+	return true;
+}
+EXPORT_SYMBOL_GPL(swork_queue);
+
+/**
+ * swork_get - get an instance of the sworker
+ *
+ * Returns an negative error code if the initialization if the worker did not
+ * work, %0 otherwise.
+ *
+ */
+int swork_get(void)
+{
+	struct sworker *worker;
+
+	mutex_lock(&worker_mutex);
+	if (!glob_worker) {
+		worker = swork_create();
+		if (IS_ERR(worker)) {
+			mutex_unlock(&worker_mutex);
+			return -ENOMEM;
+		}
+
+		glob_worker = worker;
+	}
+
+	glob_worker->refs++;
+	mutex_unlock(&worker_mutex);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(swork_get);
+
+/**
+ * swork_put - puts an instance of the sworker
+ *
+ * Will destroy the sworker thread. This function must not be called until all
+ * queued events have been completed.
+ */
+void swork_put(void)
+{
+	mutex_lock(&worker_mutex);
+
+	glob_worker->refs--;
+	if (glob_worker->refs > 0)
+		goto out;
+
+	swork_destroy(glob_worker);
+	glob_worker = NULL;
+out:
+	mutex_unlock(&worker_mutex);
+}
+EXPORT_SYMBOL_GPL(swork_put);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 563820c..505b50d 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -138,6 +138,7 @@
 	unsigned int		flags;		/* X: flags */
 	int			id;		/* I: worker id */
 	struct work_struct	rebind_work;	/* L: rebind worker to cpu */
+	int			sleeping;	/* None */
 };
 
 /*
@@ -318,6 +319,31 @@
 	     (cpu) < WORK_CPU_NONE;					\
 	     (cpu) = __next_wq_cpu((cpu), cpu_possible_mask, (wq)))
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+static inline void rt_lock_idle_list(struct global_cwq *gcwq)
+{
+	preempt_disable();
+}
+static inline void rt_unlock_idle_list(struct global_cwq *gcwq)
+{
+	preempt_enable();
+}
+static inline void sched_lock_idle_list(struct global_cwq *gcwq) { }
+static inline void sched_unlock_idle_list(struct global_cwq *gcwq) { }
+#else
+static inline void rt_lock_idle_list(struct global_cwq *gcwq) { }
+static inline void rt_unlock_idle_list(struct global_cwq *gcwq) { }
+static inline void sched_lock_idle_list(struct global_cwq *gcwq)
+{
+	spin_lock_irq(&gcwq->lock);
+}
+static inline void sched_unlock_idle_list(struct global_cwq *gcwq)
+{
+	spin_unlock_irq(&gcwq->lock);
+}
+#endif
+
+
 #ifdef CONFIG_DEBUG_OBJECTS_WORK
 
 static struct debug_obj_descr work_debug_descr;
@@ -654,73 +680,69 @@
  */
 static void wake_up_worker(struct global_cwq *gcwq)
 {
-	struct worker *worker = first_worker(gcwq);
+	struct worker *worker;
+
+	rt_lock_idle_list(gcwq);
+
+	worker = first_worker(gcwq);
 
 	if (likely(worker))
 		wake_up_process(worker->task);
+
+	rt_unlock_idle_list(gcwq);
 }
 
 /**
- * wq_worker_waking_up - a worker is waking up
- * @task: task waking up
- * @cpu: CPU @task is waking up to
+ * wq_worker_running - a worker is running again
+ * @task: task returning from sleep
  *
- * This function is called during try_to_wake_up() when a worker is
- * being awoken.
- *
- * CONTEXT:
- * spin_lock_irq(rq->lock)
+ * This function is called when a worker returns from schedule()
  */
-void wq_worker_waking_up(struct task_struct *task, unsigned int cpu)
+void wq_worker_running(struct task_struct *task)
 {
 	struct worker *worker = kthread_data(task);
 
+	if (!worker->sleeping)
+		return;
 	if (!(worker->flags & WORKER_NOT_RUNNING))
-		atomic_inc(get_gcwq_nr_running(cpu));
+		atomic_inc(get_gcwq_nr_running(smp_processor_id()));
+	worker->sleeping = 0;
 }
 
 /**
  * wq_worker_sleeping - a worker is going to sleep
  * @task: task going to sleep
- * @cpu: CPU in question, must be the current CPU number
  *
- * This function is called during schedule() when a busy worker is
- * going to sleep.  Worker on the same cpu can be woken up by
- * returning pointer to its task.
- *
- * CONTEXT:
- * spin_lock_irq(rq->lock)
- *
- * RETURNS:
- * Worker task on @cpu to wake up, %NULL if none.
+ * This function is called from schedule() when a busy worker is
+ * going to sleep.
  */
-struct task_struct *wq_worker_sleeping(struct task_struct *task,
-				       unsigned int cpu)
+void wq_worker_sleeping(struct task_struct *task)
 {
-	struct worker *worker = kthread_data(task), *to_wakeup = NULL;
-	struct global_cwq *gcwq = get_gcwq(cpu);
-	atomic_t *nr_running = get_gcwq_nr_running(cpu);
+	struct worker *worker = kthread_data(task);
+	struct global_cwq *gcwq;
+	int cpu;
 
 	if (worker->flags & WORKER_NOT_RUNNING)
-		return NULL;
+		return;
 
-	/* this can only happen on the local cpu */
-	BUG_ON(cpu != raw_smp_processor_id());
+	if (WARN_ON_ONCE(worker->sleeping))
+		return;
 
+	worker->sleeping = 1;
+
+	cpu = smp_processor_id();
+	gcwq = get_gcwq(cpu);
 	/*
 	 * The counterpart of the following dec_and_test, implied mb,
 	 * worklist not empty test sequence is in insert_work().
 	 * Please read comment there.
-	 *
-	 * NOT_RUNNING is clear.  This means that trustee is not in
-	 * charge and we're running on the local cpu w/ rq lock held
-	 * and preemption disabled, which in turn means that none else
-	 * could be manipulating idle_list, so dereferencing idle_list
-	 * without gcwq lock is safe.
 	 */
-	if (atomic_dec_and_test(nr_running) && !list_empty(&gcwq->worklist))
-		to_wakeup = first_worker(gcwq);
-	return to_wakeup ? to_wakeup->task : NULL;
+	if (atomic_dec_and_test(get_gcwq_nr_running(cpu)) &&
+	    !list_empty(&gcwq->worklist)) {
+		sched_lock_idle_list(gcwq);
+		wake_up_worker(gcwq);
+		sched_unlock_idle_list(gcwq);
+	}
 }
 
 /**
@@ -1090,8 +1112,8 @@
 {
 	int ret;
 
-	ret = queue_work_on(get_cpu(), wq, work);
-	put_cpu();
+	ret = queue_work_on(get_cpu_light(), wq, work);
+	put_cpu_light();
 
 	return ret;
 }
@@ -1235,13 +1257,8 @@
 	} else
 		wake_up_all(&gcwq->trustee_wait);
 
-	/*
-	 * Sanity check nr_running.  Because trustee releases gcwq->lock
-	 * between setting %WORKER_ROGUE and zapping nr_running, the
-	 * warning may trigger spuriously.  Check iff trustee is idle.
-	 */
-	WARN_ON_ONCE(gcwq->trustee_state == TRUSTEE_DONE &&
-		     gcwq->nr_workers == gcwq->nr_idle &&
+	/* sanity check nr_running */
+	WARN_ON_ONCE(gcwq->nr_workers == gcwq->nr_idle &&
 		     atomic_read(get_gcwq_nr_running(gcwq->cpu)));
 }
 
@@ -3583,6 +3600,25 @@
 				kthread_stop(new_trustee);
 			return NOTIFY_BAD;
 		}
+		break;
+	case CPU_POST_DEAD:
+	case CPU_UP_CANCELED:
+	case CPU_DOWN_FAILED:
+	case CPU_ONLINE:
+		break;
+	case CPU_DYING:
+		/*
+		 * We access this lockless. We are on the dying CPU
+		 * and called from stomp machine.
+		 *
+		 * Before this, the trustee and all workers except for
+		 * the ones which are still executing works from
+		 * before the last CPU down must be on the cpu.  After
+		 * this, they'll all be diasporas.
+		 */
+		gcwq->flags |= GCWQ_DISASSOCIATED;
+	default:
+		goto out;
 	}
 
 	/* some are called w/ irq disabled, don't disturb irq status */
@@ -3602,16 +3638,6 @@
 		gcwq->first_idle = new_worker;
 		break;
 
-	case CPU_DYING:
-		/*
-		 * Before this, the trustee and all workers except for
-		 * the ones which are still executing works from
-		 * before the last CPU down must be on the cpu.  After
-		 * this, they'll all be diasporas.
-		 */
-		gcwq->flags |= GCWQ_DISASSOCIATED;
-		break;
-
 	case CPU_POST_DEAD:
 		gcwq->trustee_state = TRUSTEE_BUTCHER;
 		/* fall through */
@@ -3645,6 +3671,7 @@
 
 	spin_unlock_irqrestore(&gcwq->lock, flags);
 
+out:
 	return notifier_from_errno(0);
 }
 
diff --git a/kernel/workqueue_sched.h b/kernel/workqueue_sched.h
index 2d10fc9..3bf73e2 100644
--- a/kernel/workqueue_sched.h
+++ b/kernel/workqueue_sched.h
@@ -4,6 +4,5 @@
  * Scheduler hooks for concurrency managed workqueue.  Only to be
  * included from sched.c and workqueue.c.
  */
-void wq_worker_waking_up(struct task_struct *task, unsigned int cpu);
-struct task_struct *wq_worker_sleeping(struct task_struct *task,
-				       unsigned int cpu);
+void wq_worker_running(struct task_struct *task);
+void wq_worker_sleeping(struct task_struct *task);
diff --git a/lib/Kconfig b/lib/Kconfig
index 32f3e5a..63d81e8 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -231,6 +231,7 @@
 
 config CPUMASK_OFFSTACK
 	bool "Force CPU masks off stack" if DEBUG_PER_CPU_MAPS
+	depends on !PREEMPT_RT_FULL
 	help
 	  Use dynamic allocation for cpumask_var_t, instead of putting
 	  them on the stack.  This is a bit more expensive, but avoids
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 82928f5..c347db3 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -151,7 +151,7 @@
 
 config DEBUG_SHIRQ
 	bool "Debug shared IRQ handlers"
-	depends on DEBUG_KERNEL && GENERIC_HARDIRQS
+	depends on DEBUG_KERNEL && GENERIC_HARDIRQS && !PREEMPT_RT_BASE
 	help
 	  Enable this to generate a spurious interrupt as soon as a shared
 	  interrupt handler is registered, and just before one is deregistered.
diff --git a/lib/Makefile b/lib/Makefile
index c06efca..ad29d0c 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -37,8 +37,11 @@
 obj-$(CONFIG_CHECK_SIGNATURE) += check_signature.o
 obj-$(CONFIG_DEBUG_LOCKING_API_SELFTESTS) += locking-selftest.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
+
+ifneq ($(CONFIG_PREEMPT_RT_FULL),y)
 lib-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
 lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
+endif
 
 GCOV_PROFILE_hweight.o := n
 CFLAGS_hweight.o = $(subst $(quote),,$(CONFIG_ARCH_HWEIGHT_CFLAGS))
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index a78b7c6..9b622c9 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -306,7 +306,10 @@
 	struct debug_obj *obj;
 	unsigned long flags;
 
-	fill_pool();
+#ifdef CONFIG_PREEMPT_RT_FULL
+	if (preempt_count() == 0 && !irqs_disabled())
+#endif
+		fill_pool();
 
 	db = get_bucket((unsigned long) addr);
 
@@ -1015,9 +1018,9 @@
 		}
 	}
 
+	local_irq_enable();
 	printk(KERN_DEBUG "ODEBUG: %d of %d active objects replaced\n", cnt,
 	       obj_pool_used);
-	local_irq_enable();
 	return 0;
 free:
 	hlist_for_each_entry_safe(obj, node, tmp, &objects, node) {
diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c
index 507a22f..51e558f 100644
--- a/lib/locking-selftest.c
+++ b/lib/locking-selftest.c
@@ -570,6 +570,8 @@
 #include "locking-selftest-spin-hardirq.h"
 GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_spin)
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+
 #include "locking-selftest-rlock-hardirq.h"
 GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_rlock)
 
@@ -585,9 +587,12 @@
 #include "locking-selftest-wlock-softirq.h"
 GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_soft_wlock)
 
+#endif
+
 #undef E1
 #undef E2
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /*
  * Enabling hardirqs with a softirq-safe lock held:
  */
@@ -620,6 +625,8 @@
 #undef E1
 #undef E2
 
+#endif
+
 /*
  * Enabling irqs with an irq-safe lock held:
  */
@@ -643,6 +650,8 @@
 #include "locking-selftest-spin-hardirq.h"
 GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_spin)
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+
 #include "locking-selftest-rlock-hardirq.h"
 GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_rlock)
 
@@ -658,6 +667,8 @@
 #include "locking-selftest-wlock-softirq.h"
 GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_wlock)
 
+#endif
+
 #undef E1
 #undef E2
 
@@ -689,6 +700,8 @@
 #include "locking-selftest-spin-hardirq.h"
 GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_spin)
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+
 #include "locking-selftest-rlock-hardirq.h"
 GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_rlock)
 
@@ -704,6 +717,8 @@
 #include "locking-selftest-wlock-softirq.h"
 GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_wlock)
 
+#endif
+
 #undef E1
 #undef E2
 #undef E3
@@ -737,6 +752,8 @@
 #include "locking-selftest-spin-hardirq.h"
 GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_hard_spin)
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+
 #include "locking-selftest-rlock-hardirq.h"
 GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_hard_rlock)
 
@@ -752,10 +769,14 @@
 #include "locking-selftest-wlock-softirq.h"
 GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_soft_wlock)
 
+#endif
+
 #undef E1
 #undef E2
 #undef E3
 
+#ifndef CONFIG_PREEMPT_RT_FULL
+
 /*
  * read-lock / write-lock irq inversion.
  *
@@ -818,6 +839,10 @@
 #undef E2
 #undef E3
 
+#endif
+
+#ifndef CONFIG_PREEMPT_RT_FULL
+
 /*
  * read-lock / write-lock recursion that is actually safe.
  */
@@ -856,6 +881,8 @@
 #undef E2
 #undef E3
 
+#endif
+
 /*
  * read-lock / write-lock recursion that is unsafe.
  */
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index d9df745..770453a 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -166,12 +166,13 @@
 		 * succeed in getting a node here (and never reach
 		 * kmem_cache_alloc)
 		 */
-		rtp = &__get_cpu_var(radix_tree_preloads);
+		rtp = &get_cpu_var(radix_tree_preloads);
 		if (rtp->nr) {
 			ret = rtp->nodes[rtp->nr - 1];
 			rtp->nodes[rtp->nr - 1] = NULL;
 			rtp->nr--;
 		}
+		put_cpu_var(radix_tree_preloads);
 	}
 	if (ret == NULL)
 		ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask);
@@ -206,6 +207,7 @@
 	call_rcu(&node->rcu_head, radix_tree_node_rcu_free);
 }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 /*
  * Load up this CPU's radix_tree_node buffer with sufficient objects to
  * ensure that the addition of a single element in the tree cannot fail.  On
@@ -240,6 +242,7 @@
 	return ret;
 }
 EXPORT_SYMBOL(radix_tree_preload);
+#endif
 
 /*
  *	Return the maximum key which can be store into a
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index 2ffcb3c..7a594cd 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -424,7 +424,7 @@
 			flush_kernel_dcache_page(miter->page);
 
 		if (miter->__flags & SG_MITER_ATOMIC) {
-			WARN_ON(!irqs_disabled());
+			WARN_ON_NONRT(!irqs_disabled());
 			kunmap_atomic(miter->addr, KM_BIO_SRC_IRQ);
 		} else
 			kunmap(miter->page);
@@ -464,7 +464,7 @@
 
 	sg_miter_start(&miter, sgl, nents, sg_flags);
 
-	local_irq_save(flags);
+	local_irq_save_nort(flags);
 
 	while (sg_miter_next(&miter) && offset < buflen) {
 		unsigned int len;
@@ -481,7 +481,7 @@
 
 	sg_miter_stop(&miter);
 
-	local_irq_restore(flags);
+	local_irq_restore_nort(flags);
 	return offset;
 }
 
diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c
index 503f087..b5e9241 100644
--- a/lib/smp_processor_id.c
+++ b/lib/smp_processor_id.c
@@ -39,9 +39,9 @@
 	if (!printk_ratelimit())
 		goto out_enable;
 
-	printk(KERN_ERR "BUG: using smp_processor_id() in preemptible [%08x] "
-			"code: %s/%d\n",
-			preempt_count() - 1, current->comm, current->pid);
+	printk(KERN_ERR "BUG: using smp_processor_id() in preemptible [%08x %08x] "
+	       "code: %s/%d\n", preempt_count() - 1,
+	       __migrate_disabled(current), current->comm, current->pid);
 	print_symbol("caller is %s\n", (long)__builtin_return_address(0));
 	dump_stack();
 
diff --git a/lib/spinlock_debug.c b/lib/spinlock_debug.c
index 5f3eacdd..f824704 100644
--- a/lib/spinlock_debug.c
+++ b/lib/spinlock_debug.c
@@ -31,6 +31,7 @@
 
 EXPORT_SYMBOL(__raw_spin_lock_init);
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 void __rwlock_init(rwlock_t *lock, const char *name,
 		   struct lock_class_key *key)
 {
@@ -48,6 +49,7 @@
 }
 
 EXPORT_SYMBOL(__rwlock_init);
+#endif
 
 static void spin_dump(raw_spinlock_t *lock, const char *msg)
 {
@@ -155,6 +157,7 @@
 	arch_spin_unlock(&lock->raw_lock);
 }
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 static void rwlock_bug(rwlock_t *lock, const char *msg)
 {
 	if (!debug_locks_off())
@@ -296,3 +299,5 @@
 	debug_write_unlock(lock);
 	arch_write_unlock(&lock->raw_lock);
 }
+
+#endif
diff --git a/localversion-rt b/localversion-rt
new file mode 100644
index 0000000..e0a0b11
--- /dev/null
+++ b/localversion-rt
@@ -0,0 +1 @@
+-rt103
diff --git a/mm/Kconfig b/mm/Kconfig
index 011b110..0526445 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -307,7 +307,7 @@
 
 config TRANSPARENT_HUGEPAGE
 	bool "Transparent Hugepage Support"
-	depends on X86 && MMU
+	depends on X86 && MMU && !PREEMPT_RT_FULL
 	select COMPACTION
 	help
 	  Transparent Hugepages allows the kernel to use huge pages and
diff --git a/mm/filemap.c b/mm/filemap.c
index 6c009c2..c32314c 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2047,7 +2047,7 @@
 	char *kaddr;
 	size_t copied;
 
-	BUG_ON(!in_atomic());
+	BUG_ON(!pagefault_disabled());
 	kaddr = kmap_atomic(page, KM_USER0);
 	if (likely(i->nr_segs == 1)) {
 		int left;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 204de6a..663f1a0 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -683,37 +683,32 @@
 	return total;
 }
 
-static bool __memcg_event_check(struct mem_cgroup *memcg, int target)
+static bool mem_cgroup_event_ratelimit(struct mem_cgroup *memcg,
+				       enum mem_cgroup_events_target target)
 {
 	unsigned long val, next;
 
 	val = __this_cpu_read(memcg->stat->events[MEM_CGROUP_EVENTS_COUNT]);
 	next = __this_cpu_read(memcg->stat->targets[target]);
 	/* from time_after() in jiffies.h */
-	return ((long)next - (long)val < 0);
-}
-
-static void __mem_cgroup_target_update(struct mem_cgroup *memcg, int target)
-{
-	unsigned long val, next;
-
-	val = __this_cpu_read(memcg->stat->events[MEM_CGROUP_EVENTS_COUNT]);
-
-	switch (target) {
-	case MEM_CGROUP_TARGET_THRESH:
-		next = val + THRESHOLDS_EVENTS_TARGET;
-		break;
-	case MEM_CGROUP_TARGET_SOFTLIMIT:
-		next = val + SOFTLIMIT_EVENTS_TARGET;
-		break;
-	case MEM_CGROUP_TARGET_NUMAINFO:
-		next = val + NUMAINFO_EVENTS_TARGET;
-		break;
-	default:
-		return;
+	if ((long)next - (long)val < 0) {
+		switch (target) {
+		case MEM_CGROUP_TARGET_THRESH:
+			next = val + THRESHOLDS_EVENTS_TARGET;
+			break;
+		case MEM_CGROUP_TARGET_SOFTLIMIT:
+			next = val + SOFTLIMIT_EVENTS_TARGET;
+			break;
+		case MEM_CGROUP_TARGET_NUMAINFO:
+			next = val + NUMAINFO_EVENTS_TARGET;
+			break;
+		default:
+			break;
+		}
+		__this_cpu_write(memcg->stat->targets[target], next);
+		return true;
 	}
-
-	__this_cpu_write(memcg->stat->targets[target], next);
+	return false;
 }
 
 /*
@@ -724,25 +719,27 @@
 {
 	preempt_disable();
 	/* threshold event is triggered in finer grain than soft limit */
-	if (unlikely(__memcg_event_check(memcg, MEM_CGROUP_TARGET_THRESH))) {
-		mem_cgroup_threshold(memcg);
-		__mem_cgroup_target_update(memcg, MEM_CGROUP_TARGET_THRESH);
-		if (unlikely(__memcg_event_check(memcg,
-			     MEM_CGROUP_TARGET_SOFTLIMIT))) {
-			mem_cgroup_update_tree(memcg, page);
-			__mem_cgroup_target_update(memcg,
-						   MEM_CGROUP_TARGET_SOFTLIMIT);
-		}
+	if (unlikely(mem_cgroup_event_ratelimit(memcg,
+						MEM_CGROUP_TARGET_THRESH))) {
+		bool do_softlimit, do_numainfo;
+
+		do_softlimit = mem_cgroup_event_ratelimit(memcg,
+						MEM_CGROUP_TARGET_SOFTLIMIT);
 #if MAX_NUMNODES > 1
-		if (unlikely(__memcg_event_check(memcg,
-			MEM_CGROUP_TARGET_NUMAINFO))) {
-			atomic_inc(&memcg->numainfo_events);
-			__mem_cgroup_target_update(memcg,
-				MEM_CGROUP_TARGET_NUMAINFO);
-		}
+		do_numainfo = mem_cgroup_event_ratelimit(memcg,
+						MEM_CGROUP_TARGET_NUMAINFO);
 #endif
-	}
-	preempt_enable();
+		preempt_enable();
+
+		mem_cgroup_threshold(memcg);
+		if (unlikely(do_softlimit))
+			mem_cgroup_update_tree(memcg, page);
+#if MAX_NUMNODES > 1
+		if (unlikely(do_numainfo))
+			atomic_inc(&memcg->numainfo_events);
+#endif
+	} else
+		preempt_enable();
 }
 
 static struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont)
@@ -2059,14 +2056,17 @@
  */
 static void refill_stock(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
-	struct memcg_stock_pcp *stock = &get_cpu_var(memcg_stock);
+	struct memcg_stock_pcp *stock;
+	int cpu = get_cpu_light();
+
+	stock = &per_cpu(memcg_stock, cpu);
 
 	if (stock->cached != memcg) { /* reset if necessary */
 		drain_stock(stock);
 		stock->cached = memcg;
 	}
 	stock->nr_pages += nr_pages;
-	put_cpu_var(memcg_stock);
+	put_cpu_light();
 }
 
 /*
@@ -2080,7 +2080,7 @@
 
 	/* Notify other cpus that system-wide "drain" is running */
 	get_online_cpus();
-	curcpu = get_cpu();
+	curcpu = get_cpu_light();
 	for_each_online_cpu(cpu) {
 		struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
 		struct mem_cgroup *memcg;
@@ -2097,7 +2097,7 @@
 				schedule_work_on(cpu, &stock->work);
 		}
 	}
-	put_cpu();
+	put_cpu_light();
 
 	if (!sync)
 		goto out;
diff --git a/mm/memory.c b/mm/memory.c
index 7762b1d..eb62438 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3518,6 +3518,32 @@
 	return 0;
 }
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+void pagefault_disable(void)
+{
+	migrate_disable();
+	current->pagefault_disabled++;
+	/*
+	 * make sure to have issued the store before a pagefault
+	 * can hit.
+	 */
+	barrier();
+}
+EXPORT_SYMBOL_GPL(pagefault_disable);
+
+void pagefault_enable(void)
+{
+	/*
+	 * make sure to issue those last loads/stores before enabling
+	 * the pagefault handler again.
+	 */
+	barrier();
+	current->pagefault_disabled--;
+	migrate_enable();
+}
+EXPORT_SYMBOL_GPL(pagefault_enable);
+#endif
+
 /*
  * By the time we get here, we already hold the mm semaphore
  */
@@ -4078,3 +4104,35 @@
 	}
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
+
+#if defined(CONFIG_PREEMPT_RT_FULL) && (USE_SPLIT_PTLOCKS > 0)
+/*
+ * Heinous hack, relies on the caller doing something like:
+ *
+ *   pte = alloc_pages(PGALLOC_GFP, 0);
+ *   if (pte)
+ *     pgtable_page_ctor(pte);
+ *   return pte;
+ *
+ * This ensures we release the page and return NULL when the
+ * lock allocation fails.
+ */
+struct page *pte_lock_init(struct page *page)
+{
+	page->ptl = kmalloc(sizeof(spinlock_t), GFP_KERNEL);
+	if (page->ptl) {
+		spin_lock_init(__pte_lockptr(page));
+	} else {
+		__free_page(page);
+		page = NULL;
+	}
+	return page;
+}
+
+void pte_lock_deinit(struct page *page)
+{
+	kfree(page->ptl);
+	page->mapping = NULL;
+}
+
+#endif
diff --git a/mm/mmu_context.c b/mm/mmu_context.c
index cf332bc..64ce279 100644
--- a/mm/mmu_context.c
+++ b/mm/mmu_context.c
@@ -26,6 +26,7 @@
 	struct task_struct *tsk = current;
 
 	task_lock(tsk);
+	local_irq_disable_rt();
 	active_mm = tsk->active_mm;
 	if (active_mm != mm) {
 		atomic_inc(&mm->mm_count);
@@ -33,6 +34,7 @@
 	}
 	tsk->mm = mm;
 	switch_mm(active_mm, mm, tsk);
+	local_irq_enable_rt();
 	task_unlock(tsk);
 
 	if (active_mm != mm)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 62a7fa23..bd02179 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -57,6 +57,7 @@
 #include <linux/ftrace_event.h>
 #include <linux/memcontrol.h>
 #include <linux/prefetch.h>
+#include <linux/locallock.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -222,6 +223,18 @@
 EXPORT_SYMBOL(nr_online_nodes);
 #endif
 
+static DEFINE_LOCAL_IRQ_LOCK(pa_lock);
+
+#ifdef CONFIG_PREEMPT_RT_BASE
+# define cpu_lock_irqsave(cpu, flags)		\
+	local_lock_irqsave_on(pa_lock, flags, cpu)
+# define cpu_unlock_irqrestore(cpu, flags)		\
+	local_unlock_irqrestore_on(pa_lock, flags, cpu)
+#else
+# define cpu_lock_irqsave(cpu, flags)		local_irq_save(flags)
+# define cpu_unlock_irqrestore(cpu, flags)	local_irq_restore(flags)
+#endif
+
 int page_group_by_mobility_disabled __read_mostly;
 
 static void set_pageblock_migratetype(struct page *page, int migratetype)
@@ -581,7 +594,7 @@
 }
 
 /*
- * Frees a number of pages from the PCP lists
+ * Frees a number of pages which have been collected from the pcp lists.
  * Assumes all pages on list are in same zone, and of same order.
  * count is the number of pages to free.
  *
@@ -592,16 +605,42 @@
  * pinned" detection logic.
  */
 static void free_pcppages_bulk(struct zone *zone, int count,
-					struct per_cpu_pages *pcp)
+			       struct list_head *list)
 {
-	int migratetype = 0;
-	int batch_free = 0;
 	int to_free = count;
+	unsigned long flags;
 
-	spin_lock(&zone->lock);
+	spin_lock_irqsave(&zone->lock, flags);
 	zone->all_unreclaimable = 0;
 	zone->pages_scanned = 0;
 
+	while (!list_empty(list)) {
+		struct page *page = list_first_entry(list, struct page, lru);
+
+		/* must delete as __free_one_page list manipulates */
+		list_del(&page->lru);
+		/* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */
+		__free_one_page(page, zone, 0, page_private(page));
+		trace_mm_page_pcpu_drain(page, 0, page_private(page));
+		to_free--;
+	}
+	WARN_ON(to_free != 0);
+	__mod_zone_page_state(zone, NR_FREE_PAGES, count);
+	spin_unlock_irqrestore(&zone->lock, flags);
+}
+
+/*
+ * Moves a number of pages from the PCP lists to free list which
+ * is freed outside of the locked region.
+ *
+ * Assumes all pages on list are in same zone, and of same order.
+ * count is the number of pages to free.
+ */
+static void isolate_pcp_pages(int to_free, struct per_cpu_pages *src,
+			      struct list_head *dst)
+{
+	int migratetype = 0, batch_free = 0;
+
 	while (to_free) {
 		struct page *page;
 		struct list_head *list;
@@ -617,7 +656,7 @@
 			batch_free++;
 			if (++migratetype == MIGRATE_PCPTYPES)
 				migratetype = 0;
-			list = &pcp->lists[migratetype];
+			list = &src->lists[migratetype];
 		} while (list_empty(list));
 
 		/* This is the only non-empty list. Free them all. */
@@ -625,28 +664,25 @@
 			batch_free = to_free;
 
 		do {
-			page = list_entry(list->prev, struct page, lru);
-			/* must delete as __free_one_page list manipulates */
+			page = list_last_entry(list, struct page, lru);
 			list_del(&page->lru);
-			/* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */
-			__free_one_page(page, zone, 0, page_private(page));
-			trace_mm_page_pcpu_drain(page, 0, page_private(page));
+			list_add(&page->lru, dst);
 		} while (--to_free && --batch_free && !list_empty(list));
 	}
-	__mod_zone_page_state(zone, NR_FREE_PAGES, count);
-	spin_unlock(&zone->lock);
 }
 
 static void free_one_page(struct zone *zone, struct page *page, int order,
 				int migratetype)
 {
-	spin_lock(&zone->lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&zone->lock, flags);
 	zone->all_unreclaimable = 0;
 	zone->pages_scanned = 0;
 
 	__free_one_page(page, zone, order, migratetype);
 	__mod_zone_page_state(zone, NR_FREE_PAGES, 1 << order);
-	spin_unlock(&zone->lock);
+	spin_unlock_irqrestore(&zone->lock, flags);
 }
 
 static bool free_pages_prepare(struct page *page, unsigned int order)
@@ -683,13 +719,13 @@
 	if (!free_pages_prepare(page, order))
 		return;
 
-	local_irq_save(flags);
+	local_lock_irqsave(pa_lock, flags);
 	if (unlikely(wasMlocked))
 		free_page_mlock(page);
 	__count_vm_events(PGFREE, 1 << order);
 	free_one_page(page_zone(page), page, order,
 					get_pageblock_migratetype(page));
-	local_irq_restore(flags);
+	local_unlock_irqrestore(pa_lock, flags);
 }
 
 /*
@@ -1065,16 +1101,18 @@
 void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
 {
 	unsigned long flags;
+	LIST_HEAD(dst);
 	int to_drain;
 
-	local_irq_save(flags);
+	local_lock_irqsave(pa_lock, flags);
 	if (pcp->count >= pcp->batch)
 		to_drain = pcp->batch;
 	else
 		to_drain = pcp->count;
-	free_pcppages_bulk(zone, to_drain, pcp);
+	isolate_pcp_pages(to_drain, pcp, &dst);
 	pcp->count -= to_drain;
-	local_irq_restore(flags);
+	local_unlock_irqrestore(pa_lock, flags);
+	free_pcppages_bulk(zone, to_drain, &dst);
 }
 #endif
 
@@ -1093,16 +1131,21 @@
 	for_each_populated_zone(zone) {
 		struct per_cpu_pageset *pset;
 		struct per_cpu_pages *pcp;
+		LIST_HEAD(dst);
+		int count;
 
-		local_irq_save(flags);
+		cpu_lock_irqsave(cpu, flags);
 		pset = per_cpu_ptr(zone->pageset, cpu);
 
 		pcp = &pset->pcp;
-		if (pcp->count) {
-			free_pcppages_bulk(zone, pcp->count, pcp);
+		count = pcp->count;
+		if (count) {
+			isolate_pcp_pages(count, pcp, &dst);
 			pcp->count = 0;
 		}
-		local_irq_restore(flags);
+		cpu_unlock_irqrestore(cpu, flags);
+		if (count)
+			free_pcppages_bulk(zone, count, &dst);
 	}
 }
 
@@ -1119,7 +1162,14 @@
  */
 void drain_all_pages(void)
 {
+#ifndef CONFIG_PREEMPT_RT_BASE
 	on_each_cpu(drain_local_pages, NULL, 1);
+#else
+	int i;
+
+	for_each_online_cpu(i)
+		drain_pages(i);
+#endif
 }
 
 #ifdef CONFIG_HIBERNATION
@@ -1175,7 +1225,7 @@
 
 	migratetype = get_pageblock_migratetype(page);
 	set_page_private(page, migratetype);
-	local_irq_save(flags);
+	local_lock_irqsave(pa_lock, flags);
 	if (unlikely(wasMlocked))
 		free_page_mlock(page);
 	__count_vm_event(PGFREE);
@@ -1202,12 +1252,19 @@
 		list_add(&page->lru, &pcp->lists[migratetype]);
 	pcp->count++;
 	if (pcp->count >= pcp->high) {
-		free_pcppages_bulk(zone, pcp->batch, pcp);
+		LIST_HEAD(dst);
+		int count;
+
+		isolate_pcp_pages(pcp->batch, pcp, &dst);
 		pcp->count -= pcp->batch;
+		count = pcp->batch;
+		local_unlock_irqrestore(pa_lock, flags);
+		free_pcppages_bulk(zone, count, &dst);
+		return;
 	}
 
 out:
-	local_irq_restore(flags);
+	local_unlock_irqrestore(pa_lock, flags);
 }
 
 /*
@@ -1302,7 +1359,7 @@
 		struct per_cpu_pages *pcp;
 		struct list_head *list;
 
-		local_irq_save(flags);
+		local_lock_irqsave(pa_lock, flags);
 		pcp = &this_cpu_ptr(zone->pageset)->pcp;
 		list = &pcp->lists[migratetype];
 		if (list_empty(list)) {
@@ -1334,17 +1391,19 @@
 			 */
 			WARN_ON_ONCE(order > 1);
 		}
-		spin_lock_irqsave(&zone->lock, flags);
+		local_spin_lock_irqsave(pa_lock, &zone->lock, flags);
 		page = __rmqueue(zone, order, migratetype);
-		spin_unlock(&zone->lock);
-		if (!page)
+		if (!page) {
+			spin_unlock(&zone->lock);
 			goto failed;
+		}
 		__mod_zone_page_state(zone, NR_FREE_PAGES, -(1 << order));
+		spin_unlock(&zone->lock);
 	}
 
 	__count_zone_vm_events(PGALLOC, zone, 1 << order);
 	zone_statistics(preferred_zone, zone, gfp_flags);
-	local_irq_restore(flags);
+	local_unlock_irqrestore(pa_lock, flags);
 
 	VM_BUG_ON(bad_range(zone, page));
 	if (prep_new_page(page, order, gfp_flags))
@@ -1352,7 +1411,7 @@
 	return page;
 
 failed:
-	local_irq_restore(flags);
+	local_unlock_irqrestore(pa_lock, flags);
 	return NULL;
 }
 
@@ -1914,8 +1973,8 @@
 	if (*did_some_progress != COMPACT_SKIPPED) {
 
 		/* Page migration frees to the PCP lists but we want merging */
-		drain_pages(get_cpu());
-		put_cpu();
+		drain_pages(get_cpu_light());
+		put_cpu_light();
 
 		page = get_page_from_freelist(gfp_mask, nodemask,
 				order, zonelist, high_zoneidx,
@@ -3733,14 +3792,16 @@
 	for_each_possible_cpu(cpu) {
 		struct per_cpu_pageset *pset;
 		struct per_cpu_pages *pcp;
+		LIST_HEAD(dst);
 
 		pset = per_cpu_ptr(zone->pageset, cpu);
 		pcp = &pset->pcp;
 
-		local_irq_save(flags);
-		free_pcppages_bulk(zone, pcp->count, pcp);
+		cpu_lock_irqsave(cpu, flags);
+		isolate_pcp_pages(pcp->count, pcp, &dst);
+		free_pcppages_bulk(zone, pcp->count, &dst);
 		setup_pageset(pset, batch);
-		local_irq_restore(flags);
+		cpu_unlock_irqrestore(cpu, flags);
 	}
 	return 0;
 }
@@ -5106,6 +5167,7 @@
 void __init page_alloc_init(void)
 {
 	hotcpu_notifier(page_alloc_cpu_notify, 0);
+	local_irq_lock_init(pa_lock);
 }
 
 /*
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index 6f4ef53..8e854bf 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -17,6 +17,7 @@
 	set_page_cgroup_array_id(pc, id);
 	pc->mem_cgroup = NULL;
 	INIT_LIST_HEAD(&pc->lru);
+	page_cgroup_lock_init(pc);
 }
 static unsigned long total_usage;
 
diff --git a/mm/slab.c b/mm/slab.c
index aea5e42..c23c4dc 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -116,6 +116,7 @@
 #include	<linux/kmemcheck.h>
 #include	<linux/memory.h>
 #include	<linux/prefetch.h>
+#include	<linux/locallock.h>
 
 #include	<asm/cacheflush.h>
 #include	<asm/tlbflush.h>
@@ -607,6 +608,12 @@
 	return g_cpucache_up >= EARLY;
 }
 
+/*
+ * Guard access to the cache-chain.
+ */
+static DEFINE_MUTEX(cache_chain_mutex);
+static struct list_head cache_chain;
+
 #ifdef CONFIG_LOCKDEP
 
 /*
@@ -668,38 +675,41 @@
 		slab_set_debugobj_lock_classes_node(cachep, node);
 }
 
-static void init_node_lock_keys(int q)
+static void init_lock_keys(struct kmem_cache *cachep, int node)
 {
-	struct cache_sizes *s = malloc_sizes;
+	struct kmem_list3 *l3;
 
 	if (g_cpucache_up < LATE)
 		return;
 
-	for (s = malloc_sizes; s->cs_size != ULONG_MAX; s++) {
-		struct kmem_list3 *l3;
+	l3 = cachep->nodelists[node];
+	if (!l3 || OFF_SLAB(cachep))
+		return;
 
-		l3 = s->cs_cachep->nodelists[q];
-		if (!l3 || OFF_SLAB(s->cs_cachep))
-			continue;
-
-		slab_set_lock_classes(s->cs_cachep, &on_slab_l3_key,
-				&on_slab_alc_key, q);
-	}
+	slab_set_lock_classes(cachep, &on_slab_l3_key, &on_slab_alc_key, node);
 }
 
-static inline void init_lock_keys(void)
+static void init_node_lock_keys(int node)
+{
+	struct kmem_cache *cachep;
+
+	list_for_each_entry(cachep, &cache_chain, next)
+		init_lock_keys(cachep, node);
+}
+
+static inline void init_cachep_lock_keys(struct kmem_cache *cachep)
 {
 	int node;
 
 	for_each_node(node)
-		init_node_lock_keys(node);
+		init_lock_keys(cachep, node);
 }
 #else
-static void init_node_lock_keys(int q)
+static void init_node_lock_keys(int node)
 {
 }
 
-static inline void init_lock_keys(void)
+static void init_cachep_lock_keys(struct kmem_cache *cachep)
 {
 }
 
@@ -712,19 +722,79 @@
 }
 #endif
 
-/*
- * Guard access to the cache-chain.
- */
-static DEFINE_MUTEX(cache_chain_mutex);
-static struct list_head cache_chain;
-
 static DEFINE_PER_CPU(struct delayed_work, slab_reap_work);
+static DEFINE_PER_CPU(struct list_head, slab_free_list);
+static DEFINE_LOCAL_IRQ_LOCK(slab_lock);
+
+#ifndef CONFIG_PREEMPT_RT_BASE
+# define slab_on_each_cpu(func, cp)	on_each_cpu(func, cp, 1)
+#else
+/*
+ * execute func() for all CPUs. On PREEMPT_RT we dont actually have
+ * to run on the remote CPUs - we only have to take their CPU-locks.
+ * (This is a rare operation, so cacheline bouncing is not an issue.)
+ */
+static void
+slab_on_each_cpu(void (*func)(void *arg, int this_cpu), void *arg)
+{
+	unsigned int i;
+
+	get_cpu_light();
+	for_each_online_cpu(i)
+		func(arg, i);
+	put_cpu_light();
+}
+
+static void lock_slab_on(unsigned int cpu)
+{
+	local_lock_irq_on(slab_lock, cpu);
+}
+
+static void unlock_slab_on(unsigned int cpu)
+{
+	local_unlock_irq_on(slab_lock, cpu);
+}
+#endif
+
+static void free_delayed(struct list_head *h)
+{
+	while(!list_empty(h)) {
+		struct page *page = list_first_entry(h, struct page, lru);
+
+		list_del(&page->lru);
+		__free_pages(page, page->index);
+	}
+}
+
+static void unlock_l3_and_free_delayed(spinlock_t *list_lock)
+{
+	LIST_HEAD(tmp);
+
+	list_splice_init(&__get_cpu_var(slab_free_list), &tmp);
+	local_spin_unlock_irq(slab_lock, list_lock);
+	free_delayed(&tmp);
+}
+
+static void unlock_slab_and_free_delayed(unsigned long flags)
+{
+	LIST_HEAD(tmp);
+
+	list_splice_init(&__get_cpu_var(slab_free_list), &tmp);
+	local_unlock_irqrestore(slab_lock, flags);
+	free_delayed(&tmp);
+}
 
 static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
 {
 	return cachep->array[smp_processor_id()];
 }
 
+static inline struct array_cache *cpu_cache_get_on_cpu(struct kmem_cache *cachep,
+						       int cpu)
+{
+	return cachep->array[cpu];
+}
+
 static inline struct kmem_cache *__find_general_cachep(size_t size,
 							gfp_t gfpflags)
 {
@@ -1062,9 +1132,10 @@
 	if (l3->alien) {
 		struct array_cache *ac = l3->alien[node];
 
-		if (ac && ac->avail && spin_trylock_irq(&ac->lock)) {
+		if (ac && ac->avail &&
+		    local_spin_trylock_irq(slab_lock, &ac->lock)) {
 			__drain_alien_cache(cachep, ac, node);
-			spin_unlock_irq(&ac->lock);
+			local_spin_unlock_irq(slab_lock, &ac->lock);
 		}
 	}
 }
@@ -1079,9 +1150,9 @@
 	for_each_online_node(i) {
 		ac = alien[i];
 		if (ac) {
-			spin_lock_irqsave(&ac->lock, flags);
+			local_spin_lock_irqsave(slab_lock, &ac->lock, flags);
 			__drain_alien_cache(cachep, ac, i);
-			spin_unlock_irqrestore(&ac->lock, flags);
+			local_spin_unlock_irqrestore(slab_lock, &ac->lock, flags);
 		}
 	}
 }
@@ -1160,11 +1231,11 @@
 			cachep->nodelists[node] = l3;
 		}
 
-		spin_lock_irq(&cachep->nodelists[node]->list_lock);
+		local_spin_lock_irq(slab_lock, &cachep->nodelists[node]->list_lock);
 		cachep->nodelists[node]->free_limit =
 			(1 + nr_cpus_node(node)) *
 			cachep->batchcount + cachep->num;
-		spin_unlock_irq(&cachep->nodelists[node]->list_lock);
+		local_spin_unlock_irq(slab_lock, &cachep->nodelists[node]->list_lock);
 	}
 	return 0;
 }
@@ -1189,7 +1260,7 @@
 		if (!l3)
 			goto free_array_cache;
 
-		spin_lock_irq(&l3->list_lock);
+		local_spin_lock_irq(slab_lock, &l3->list_lock);
 
 		/* Free limit for this kmem_list3 */
 		l3->free_limit -= cachep->batchcount;
@@ -1197,7 +1268,7 @@
 			free_block(cachep, nc->entry, nc->avail, node);
 
 		if (!cpumask_empty(mask)) {
-			spin_unlock_irq(&l3->list_lock);
+			unlock_l3_and_free_delayed(&l3->list_lock);
 			goto free_array_cache;
 		}
 
@@ -1211,7 +1282,7 @@
 		alien = l3->alien;
 		l3->alien = NULL;
 
-		spin_unlock_irq(&l3->list_lock);
+		unlock_l3_and_free_delayed(&l3->list_lock);
 
 		kfree(shared);
 		if (alien) {
@@ -1285,7 +1356,7 @@
 		l3 = cachep->nodelists[node];
 		BUG_ON(!l3);
 
-		spin_lock_irq(&l3->list_lock);
+		local_spin_lock_irq(slab_lock, &l3->list_lock);
 		if (!l3->shared) {
 			/*
 			 * We are serialised from CPU_DEAD or
@@ -1300,7 +1371,7 @@
 			alien = NULL;
 		}
 #endif
-		spin_unlock_irq(&l3->list_lock);
+		local_spin_unlock_irq(slab_lock, &l3->list_lock);
 		kfree(shared);
 		free_alien_cache(alien);
 		if (cachep->flags & SLAB_DEBUG_OBJECTS)
@@ -1491,6 +1562,10 @@
 	if (num_possible_nodes() == 1)
 		use_alien_caches = 0;
 
+	local_irq_lock_init(slab_lock);
+	for_each_possible_cpu(i)
+		INIT_LIST_HEAD(&per_cpu(slab_free_list, i));
+
 	for (i = 0; i < NUM_INIT_LISTS; i++) {
 		kmem_list3_init(&initkmem_list3[i]);
 		if (i < MAX_NUMNODES)
@@ -1671,14 +1746,13 @@
 
 	/* 6) resize the head arrays to their final sizes */
 	mutex_lock(&cache_chain_mutex);
-	list_for_each_entry(cachep, &cache_chain, next)
+	list_for_each_entry(cachep, &cache_chain, next) {
 		if (enable_cpucache(cachep, GFP_NOWAIT))
 			BUG();
+		init_cachep_lock_keys(cachep);
+	}
 	mutex_unlock(&cache_chain_mutex);
 
-	/* Annotate slab for lockdep -- annotate the malloc caches */
-	init_lock_keys();
-
 	/* Done! */
 	g_cpucache_up = FULL;
 
@@ -1769,12 +1843,14 @@
 /*
  * Interface to system's page release.
  */
-static void kmem_freepages(struct kmem_cache *cachep, void *addr)
+static void kmem_freepages(struct kmem_cache *cachep, void *addr, bool delayed)
 {
 	unsigned long i = (1 << cachep->gfporder);
-	struct page *page = virt_to_page(addr);
+	struct page *page, *basepage = virt_to_page(addr);
 	const unsigned long nr_freed = i;
 
+	page = basepage;
+
 	kmemcheck_free_shadow(page, cachep->gfporder);
 
 	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
@@ -1790,7 +1866,13 @@
 	}
 	if (current->reclaim_state)
 		current->reclaim_state->reclaimed_slab += nr_freed;
-	free_pages((unsigned long)addr, cachep->gfporder);
+
+	if (!delayed) {
+		free_pages((unsigned long)addr, cachep->gfporder);
+	} else {
+		basepage->index = cachep->gfporder;
+		list_add(&basepage->lru, &__get_cpu_var(slab_free_list));
+	}
 }
 
 static void kmem_rcu_free(struct rcu_head *head)
@@ -1798,7 +1880,7 @@
 	struct slab_rcu *slab_rcu = (struct slab_rcu *)head;
 	struct kmem_cache *cachep = slab_rcu->cachep;
 
-	kmem_freepages(cachep, slab_rcu->addr);
+	kmem_freepages(cachep, slab_rcu->addr, false);
 	if (OFF_SLAB(cachep))
 		kmem_cache_free(cachep->slabp_cache, slab_rcu);
 }
@@ -2017,7 +2099,8 @@
  * Before calling the slab must have been unlinked from the cache.  The
  * cache-lock is not held/needed.
  */
-static void slab_destroy(struct kmem_cache *cachep, struct slab *slabp)
+static void slab_destroy(struct kmem_cache *cachep, struct slab *slabp,
+			 bool delayed)
 {
 	void *addr = slabp->s_mem - slabp->colouroff;
 
@@ -2030,7 +2113,7 @@
 		slab_rcu->addr = addr;
 		call_rcu(&slab_rcu->head, kmem_rcu_free);
 	} else {
-		kmem_freepages(cachep, addr);
+		kmem_freepages(cachep, addr, delayed);
 		if (OFF_SLAB(cachep))
 			kmem_cache_free(cachep->slabp_cache, slabp);
 	}
@@ -2479,6 +2562,8 @@
 		slab_set_debugobj_lock_classes(cachep);
 	}
 
+	init_cachep_lock_keys(cachep);
+
 	/* cache setup completed, link it into the list */
 	list_add(&cachep->next, &cache_chain);
 oops:
@@ -2496,7 +2581,7 @@
 #if DEBUG
 static void check_irq_off(void)
 {
-	BUG_ON(!irqs_disabled());
+	BUG_ON_NONRT(!irqs_disabled());
 }
 
 static void check_irq_on(void)
@@ -2531,26 +2616,43 @@
 			struct array_cache *ac,
 			int force, int node);
 
-static void do_drain(void *arg)
+static void __do_drain(void *arg, unsigned int cpu)
 {
 	struct kmem_cache *cachep = arg;
 	struct array_cache *ac;
-	int node = numa_mem_id();
+	int node = cpu_to_mem(cpu);
 
-	check_irq_off();
-	ac = cpu_cache_get(cachep);
+	ac = cpu_cache_get_on_cpu(cachep, cpu);
 	spin_lock(&cachep->nodelists[node]->list_lock);
 	free_block(cachep, ac->entry, ac->avail, node);
 	spin_unlock(&cachep->nodelists[node]->list_lock);
 	ac->avail = 0;
 }
 
+#ifndef CONFIG_PREEMPT_RT_BASE
+static void do_drain(void *arg)
+{
+	__do_drain(arg, smp_processor_id());
+}
+#else
+static void do_drain(void *arg, int cpu)
+{
+	LIST_HEAD(tmp);
+
+	lock_slab_on(cpu);
+	__do_drain(arg, cpu);
+	list_splice_init(&per_cpu(slab_free_list, cpu), &tmp);
+	unlock_slab_on(cpu);
+	free_delayed(&tmp);
+}
+#endif
+
 static void drain_cpu_caches(struct kmem_cache *cachep)
 {
 	struct kmem_list3 *l3;
 	int node;
 
-	on_each_cpu(do_drain, cachep, 1);
+	slab_on_each_cpu(do_drain, cachep);
 	check_irq_on();
 	for_each_online_node(node) {
 		l3 = cachep->nodelists[node];
@@ -2581,10 +2683,10 @@
 	nr_freed = 0;
 	while (nr_freed < tofree && !list_empty(&l3->slabs_free)) {
 
-		spin_lock_irq(&l3->list_lock);
+		local_spin_lock_irq(slab_lock, &l3->list_lock);
 		p = l3->slabs_free.prev;
 		if (p == &l3->slabs_free) {
-			spin_unlock_irq(&l3->list_lock);
+			local_spin_unlock_irq(slab_lock, &l3->list_lock);
 			goto out;
 		}
 
@@ -2598,8 +2700,8 @@
 		 * to the cache.
 		 */
 		l3->free_objects -= cache->num;
-		spin_unlock_irq(&l3->list_lock);
-		slab_destroy(cache, slabp);
+		local_spin_unlock_irq(slab_lock, &l3->list_lock);
+		slab_destroy(cache, slabp, false);
 		nr_freed++;
 	}
 out:
@@ -2893,7 +2995,7 @@
 	offset *= cachep->colour_off;
 
 	if (local_flags & __GFP_WAIT)
-		local_irq_enable();
+		local_unlock_irq(slab_lock);
 
 	/*
 	 * The test for missing atomic flag is performed here, rather than
@@ -2923,7 +3025,7 @@
 	cache_init_objs(cachep, slabp);
 
 	if (local_flags & __GFP_WAIT)
-		local_irq_disable();
+		local_lock_irq(slab_lock);
 	check_irq_off();
 	spin_lock(&l3->list_lock);
 
@@ -2934,10 +3036,10 @@
 	spin_unlock(&l3->list_lock);
 	return 1;
 opps1:
-	kmem_freepages(cachep, objp);
+	kmem_freepages(cachep, objp, false);
 failed:
 	if (local_flags & __GFP_WAIT)
-		local_irq_disable();
+		local_lock_irq(slab_lock);
 	return 0;
 }
 
@@ -3330,11 +3432,11 @@
 		 * set and go into memory reserves if necessary.
 		 */
 		if (local_flags & __GFP_WAIT)
-			local_irq_enable();
+			local_unlock_irq(slab_lock);
 		kmem_flagcheck(cache, flags);
 		obj = kmem_getpages(cache, local_flags, numa_mem_id());
 		if (local_flags & __GFP_WAIT)
-			local_irq_disable();
+			local_lock_irq(slab_lock);
 		if (obj) {
 			/*
 			 * Insert into the appropriate per node queues
@@ -3452,7 +3554,7 @@
 		return NULL;
 
 	cache_alloc_debugcheck_before(cachep, flags);
-	local_irq_save(save_flags);
+	local_lock_irqsave(slab_lock, save_flags);
 
 	if (nodeid == NUMA_NO_NODE)
 		nodeid = slab_node;
@@ -3477,7 +3579,7 @@
 	/* ___cache_alloc_node can fall back to other nodes */
 	ptr = ____cache_alloc_node(cachep, flags, nodeid);
   out:
-	local_irq_restore(save_flags);
+	local_unlock_irqrestore(slab_lock, save_flags);
 	ptr = cache_alloc_debugcheck_after(cachep, flags, ptr, caller);
 	kmemleak_alloc_recursive(ptr, obj_size(cachep), 1, cachep->flags,
 				 flags);
@@ -3537,9 +3639,9 @@
 		return NULL;
 
 	cache_alloc_debugcheck_before(cachep, flags);
-	local_irq_save(save_flags);
+	local_lock_irqsave(slab_lock, save_flags);
 	objp = __do_cache_alloc(cachep, flags);
-	local_irq_restore(save_flags);
+	local_unlock_irqrestore(slab_lock, save_flags);
 	objp = cache_alloc_debugcheck_after(cachep, flags, objp, caller);
 	kmemleak_alloc_recursive(objp, obj_size(cachep), 1, cachep->flags,
 				 flags);
@@ -3587,7 +3689,7 @@
 				 * a different cache, refer to comments before
 				 * alloc_slabmgmt.
 				 */
-				slab_destroy(cachep, slabp);
+				slab_destroy(cachep, slabp, true);
 			} else {
 				list_add(&slabp->list, &l3->slabs_free);
 			}
@@ -3850,12 +3952,12 @@
 {
 	unsigned long flags;
 
-	local_irq_save(flags);
 	debug_check_no_locks_freed(objp, obj_size(cachep));
 	if (!(cachep->flags & SLAB_DEBUG_OBJECTS))
 		debug_check_no_obj_freed(objp, obj_size(cachep));
+	local_lock_irqsave(slab_lock, flags);
 	__cache_free(cachep, objp, __builtin_return_address(0));
-	local_irq_restore(flags);
+	unlock_slab_and_free_delayed(flags);
 
 	trace_kmem_cache_free(_RET_IP_, objp);
 }
@@ -3879,13 +3981,13 @@
 
 	if (unlikely(ZERO_OR_NULL_PTR(objp)))
 		return;
-	local_irq_save(flags);
 	kfree_debugcheck(objp);
 	c = virt_to_cache(objp);
 	debug_check_no_locks_freed(objp, obj_size(c));
 	debug_check_no_obj_freed(objp, obj_size(c));
+	local_lock_irqsave(slab_lock, flags);
 	__cache_free(c, (void *)objp, __builtin_return_address(0));
-	local_irq_restore(flags);
+	unlock_slab_and_free_delayed(flags);
 }
 EXPORT_SYMBOL(kfree);
 
@@ -3928,7 +4030,7 @@
 		if (l3) {
 			struct array_cache *shared = l3->shared;
 
-			spin_lock_irq(&l3->list_lock);
+			local_spin_lock_irq(slab_lock, &l3->list_lock);
 
 			if (shared)
 				free_block(cachep, shared->entry,
@@ -3941,7 +4043,8 @@
 			}
 			l3->free_limit = (1 + nr_cpus_node(node)) *
 					cachep->batchcount + cachep->num;
-			spin_unlock_irq(&l3->list_lock);
+			unlock_l3_and_free_delayed(&l3->list_lock);
+
 			kfree(shared);
 			free_alien_cache(new_alien);
 			continue;
@@ -3988,18 +4091,31 @@
 	struct array_cache *new[0];
 };
 
-static void do_ccupdate_local(void *info)
+static void __do_ccupdate_local(void *info, int cpu)
 {
 	struct ccupdate_struct *new = info;
 	struct array_cache *old;
 
-	check_irq_off();
-	old = cpu_cache_get(new->cachep);
+	old = cpu_cache_get_on_cpu(new->cachep, cpu);
 
-	new->cachep->array[smp_processor_id()] = new->new[smp_processor_id()];
-	new->new[smp_processor_id()] = old;
+	new->cachep->array[cpu] = new->new[cpu];
+	new->new[cpu] = old;
 }
 
+#ifndef CONFIG_PREEMPT_RT_BASE
+static void do_ccupdate_local(void *info)
+{
+	__do_ccupdate_local(info, smp_processor_id());
+}
+#else
+static void do_ccupdate_local(void *info, int cpu)
+{
+	lock_slab_on(cpu);
+	__do_ccupdate_local(info, cpu);
+	unlock_slab_on(cpu);
+}
+#endif
+
 /* Always called with the cache_chain_mutex held */
 static int do_tune_cpucache(struct kmem_cache *cachep, int limit,
 				int batchcount, int shared, gfp_t gfp)
@@ -4024,7 +4140,7 @@
 	}
 	new->cachep = cachep;
 
-	on_each_cpu(do_ccupdate_local, (void *)new, 1);
+	slab_on_each_cpu(do_ccupdate_local, (void *)new);
 
 	check_irq_on();
 	cachep->batchcount = batchcount;
@@ -4035,9 +4151,11 @@
 		struct array_cache *ccold = new->new[i];
 		if (!ccold)
 			continue;
-		spin_lock_irq(&cachep->nodelists[cpu_to_mem(i)]->list_lock);
+		local_spin_lock_irq(slab_lock,
+				    &cachep->nodelists[cpu_to_mem(i)]->list_lock);
 		free_block(cachep, ccold->entry, ccold->avail, cpu_to_mem(i));
-		spin_unlock_irq(&cachep->nodelists[cpu_to_mem(i)]->list_lock);
+
+		unlock_l3_and_free_delayed(&cachep->nodelists[cpu_to_mem(i)]->list_lock);
 		kfree(ccold);
 	}
 	kfree(new);
@@ -4113,7 +4231,7 @@
 	if (ac->touched && !force) {
 		ac->touched = 0;
 	} else {
-		spin_lock_irq(&l3->list_lock);
+		local_spin_lock_irq(slab_lock, &l3->list_lock);
 		if (ac->avail) {
 			tofree = force ? ac->avail : (ac->limit + 4) / 5;
 			if (tofree > ac->avail)
@@ -4123,7 +4241,7 @@
 			memmove(ac->entry, &(ac->entry[tofree]),
 				sizeof(void *) * ac->avail);
 		}
-		spin_unlock_irq(&l3->list_lock);
+		local_spin_unlock_irq(slab_lock, &l3->list_lock);
 	}
 }
 
@@ -4262,7 +4380,7 @@
 			continue;
 
 		check_irq_on();
-		spin_lock_irq(&l3->list_lock);
+		local_spin_lock_irq(slab_lock, &l3->list_lock);
 
 		list_for_each_entry(slabp, &l3->slabs_full, list) {
 			if (slabp->inuse != cachep->num && !error)
@@ -4287,7 +4405,7 @@
 		if (l3->shared)
 			shared_avail += l3->shared->avail;
 
-		spin_unlock_irq(&l3->list_lock);
+		local_spin_unlock_irq(slab_lock, &l3->list_lock);
 	}
 	num_slabs += active_slabs;
 	num_objs = num_slabs * cachep->num;
@@ -4516,13 +4634,13 @@
 			continue;
 
 		check_irq_on();
-		spin_lock_irq(&l3->list_lock);
+		local_spin_lock_irq(slab_lock, &l3->list_lock);
 
 		list_for_each_entry(slabp, &l3->slabs_full, list)
 			handle_slab(n, cachep, slabp);
 		list_for_each_entry(slabp, &l3->slabs_partial, list)
 			handle_slab(n, cachep, slabp);
-		spin_unlock_irq(&l3->list_lock);
+		local_spin_unlock_irq(slab_lock, &l3->list_lock);
 	}
 	name = cachep->name;
 	if (n[0] == n[1]) {
diff --git a/mm/slub.c b/mm/slub.c
index 60c69696..9948315 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1258,6 +1258,14 @@
 
 #endif /* CONFIG_SLUB_DEBUG */
 
+static void setup_object(struct kmem_cache *s, struct page *page,
+				void *object)
+{
+	setup_object_debug(s, page, object);
+	if (unlikely(s->ctor))
+		s->ctor(object);
+}
+
 /*
  * Slab allocation and freeing
  */
@@ -1279,6 +1287,8 @@
 	struct page *page;
 	struct kmem_cache_order_objects oo = s->oo;
 	gfp_t alloc_gfp;
+	void *start, *last, *p;
+	int idx, order;
 
 	flags &= gfp_allowed_mask;
 
@@ -1301,17 +1311,11 @@
 		 * Try a lower order alloc if possible
 		 */
 		page = alloc_slab_page(flags, node, oo);
-
-		if (page)
-			stat(s, ORDER_FALLBACK);
+		if (unlikely(!page))
+			goto out;
+		stat(s, ORDER_FALLBACK);
 	}
 
-	if (flags & __GFP_WAIT)
-		local_irq_disable();
-
-	if (!page)
-		return NULL;
-
 	if (kmemcheck_enabled
 		&& !(s->flags & (SLAB_NOTRACK | DEBUG_DEFAULT_FLAGS))) {
 		int pages = 1 << oo_order(oo);
@@ -1329,37 +1333,6 @@
 	}
 
 	page->objects = oo_objects(oo);
-	mod_zone_page_state(page_zone(page),
-		(s->flags & SLAB_RECLAIM_ACCOUNT) ?
-		NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
-		1 << oo_order(oo));
-
-	return page;
-}
-
-static void setup_object(struct kmem_cache *s, struct page *page,
-				void *object)
-{
-	setup_object_debug(s, page, object);
-	if (unlikely(s->ctor))
-		s->ctor(object);
-}
-
-static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
-{
-	struct page *page;
-	void *start;
-	void *last;
-	void *p;
-
-	BUG_ON(flags & GFP_SLAB_BUG_MASK);
-
-	page = allocate_slab(s,
-		flags & (GFP_RECLAIM_MASK | GFP_CONSTRAINT_MASK), node);
-	if (!page)
-		goto out;
-
-	inc_slabs_node(s, page_to_nid(page), page->objects);
 	page->slab = s;
 	page->flags |= 1 << PG_slab;
 
@@ -1380,10 +1353,34 @@
 	page->freelist = start;
 	page->inuse = page->objects;
 	page->frozen = 1;
+
 out:
+	if (flags & __GFP_WAIT)
+		local_irq_disable();
+	if (!page)
+		return NULL;
+
+	mod_zone_page_state(page_zone(page),
+		(s->flags & SLAB_RECLAIM_ACCOUNT) ?
+		NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
+		1 << oo_order(oo));
+
+	inc_slabs_node(s, page_to_nid(page), page->objects);
+
 	return page;
 }
 
+static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node)
+{
+	if (unlikely(flags & GFP_SLAB_BUG_MASK)) {
+		pr_emerg("gfp: %u\n", flags & GFP_SLAB_BUG_MASK);
+		BUG();
+	}
+
+	return allocate_slab(s,
+		flags & (GFP_RECLAIM_MASK | GFP_CONSTRAINT_MASK), node);
+}
+
 static void __free_slab(struct kmem_cache *s, struct page *page)
 {
 	int order = compound_order(page);
diff --git a/mm/swap.c b/mm/swap.c
index a4b9016..66a3874 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -32,6 +32,7 @@
 #include <linux/memcontrol.h>
 #include <linux/gfp.h>
 #include <linux/hugetlb.h>
+#include <linux/locallock.h>
 
 #include "internal.h"
 
@@ -42,6 +43,9 @@
 static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs);
 static DEFINE_PER_CPU(struct pagevec, lru_deactivate_pvecs);
 
+static DEFINE_LOCAL_IRQ_LOCK(rotate_lock);
+static DEFINE_LOCAL_IRQ_LOCK(swapvec_lock);
+
 /*
  * This path almost never happens for VM activity - pages are normally
  * freed via pagevecs.  But it gets used by networking.
@@ -343,11 +347,11 @@
 		unsigned long flags;
 
 		page_cache_get(page);
-		local_irq_save(flags);
+		local_lock_irqsave(rotate_lock, flags);
 		pvec = &__get_cpu_var(lru_rotate_pvecs);
 		if (!pagevec_add(pvec, page))
 			pagevec_move_tail(pvec);
-		local_irq_restore(flags);
+		local_unlock_irqrestore(rotate_lock, flags);
 	}
 }
 
@@ -403,12 +407,13 @@
 void activate_page(struct page *page)
 {
 	if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
-		struct pagevec *pvec = &get_cpu_var(activate_page_pvecs);
+		struct pagevec *pvec = &get_locked_var(swapvec_lock,
+						       activate_page_pvecs);
 
 		page_cache_get(page);
 		if (!pagevec_add(pvec, page))
 			pagevec_lru_move_fn(pvec, __activate_page, NULL);
-		put_cpu_var(activate_page_pvecs);
+		put_locked_var(swapvec_lock, activate_page_pvecs);
 	}
 }
 
@@ -449,12 +454,12 @@
 
 void __lru_cache_add(struct page *page, enum lru_list lru)
 {
-	struct pagevec *pvec = &get_cpu_var(lru_add_pvecs)[lru];
+	struct pagevec *pvec = &get_locked_var(swapvec_lock, lru_add_pvecs)[lru];
 
 	page_cache_get(page);
 	if (!pagevec_add(pvec, page))
 		____pagevec_lru_add(pvec, lru);
-	put_cpu_var(lru_add_pvecs);
+	put_locked_var(swapvec_lock, lru_add_pvecs);
 }
 EXPORT_SYMBOL(__lru_cache_add);
 
@@ -588,9 +593,9 @@
 		unsigned long flags;
 
 		/* No harm done if a racing interrupt already did this */
-		local_irq_save(flags);
+		local_lock_irqsave(rotate_lock, flags);
 		pagevec_move_tail(pvec);
-		local_irq_restore(flags);
+		local_unlock_irqrestore(rotate_lock, flags);
 	}
 
 	pvec = &per_cpu(lru_deactivate_pvecs, cpu);
@@ -618,18 +623,19 @@
 		return;
 
 	if (likely(get_page_unless_zero(page))) {
-		struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs);
+		struct pagevec *pvec = &get_locked_var(swapvec_lock,
+						       lru_deactivate_pvecs);
 
 		if (!pagevec_add(pvec, page))
 			pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
-		put_cpu_var(lru_deactivate_pvecs);
+		put_locked_var(swapvec_lock, lru_deactivate_pvecs);
 	}
 }
 
 void lru_add_drain(void)
 {
-	drain_cpu_pagevecs(get_cpu());
-	put_cpu();
+	drain_cpu_pagevecs(local_lock_cpu(swapvec_lock));
+	local_unlock_cpu(swapvec_lock);
 }
 
 static void lru_add_drain_per_cpu(struct work_struct *dummy)
@@ -842,6 +848,15 @@
 
 EXPORT_SYMBOL(pagevec_lookup);
 
+/* Early setup for the local locks */
+static int __init swap_init_locks(void)
+{
+	local_irq_lock_init(rotate_lock);
+	local_irq_lock_init(swapvec_lock);
+	return 1;
+}
+early_initcall(swap_init_locks);
+
 unsigned pagevec_lookup_tag(struct pagevec *pvec, struct address_space *mapping,
 		pgoff_t *index, int tag, unsigned nr_pages)
 {
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 1431458..6faf1f7 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -788,7 +788,7 @@
 	struct vmap_block *vb;
 	struct vmap_area *va;
 	unsigned long vb_idx;
-	int node, err;
+	int node, err, cpu;
 
 	node = numa_node_id();
 
@@ -827,12 +827,13 @@
 	BUG_ON(err);
 	radix_tree_preload_end();
 
-	vbq = &get_cpu_var(vmap_block_queue);
+	cpu = get_cpu_light();
+	vbq = &__get_cpu_var(vmap_block_queue);
 	vb->vbq = vbq;
 	spin_lock(&vbq->lock);
 	list_add_rcu(&vb->free_list, &vbq->free);
 	spin_unlock(&vbq->lock);
-	put_cpu_var(vmap_block_queue);
+	put_cpu_light();
 
 	return vb;
 }
@@ -906,7 +907,7 @@
 	struct vmap_block *vb;
 	unsigned long addr = 0;
 	unsigned int order;
-	int purge = 0;
+	int purge = 0, cpu;
 
 	BUG_ON(size & ~PAGE_MASK);
 	BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC);
@@ -914,7 +915,8 @@
 
 again:
 	rcu_read_lock();
-	vbq = &get_cpu_var(vmap_block_queue);
+	cpu = get_cpu_light();
+	vbq = &__get_cpu_var(vmap_block_queue);
 	list_for_each_entry_rcu(vb, &vbq->free, free_list) {
 		int i;
 
@@ -951,7 +953,7 @@
 	if (purge)
 		purge_fragmented_blocks_thiscpu();
 
-	put_cpu_var(vmap_block_queue);
+	put_cpu_light();
 	rcu_read_unlock();
 
 	if (!addr) {
diff --git a/mm/vmscan.c b/mm/vmscan.c
index ab98dc6..dacf892 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1381,8 +1381,8 @@
  */
 static noinline_for_stack void
 putback_lru_pages(struct zone *zone, struct scan_control *sc,
-				unsigned long nr_anon, unsigned long nr_file,
-				struct list_head *page_list)
+		  unsigned long nr_anon, unsigned long nr_file,
+		  struct list_head *page_list, unsigned long nr_reclaimed)
 {
 	struct page *page;
 	struct pagevec pvec;
@@ -1393,7 +1393,12 @@
 	/*
 	 * Put back any unfreeable pages.
 	 */
-	spin_lock(&zone->lru_lock);
+	spin_lock_irq(&zone->lru_lock);
+
+	if (current_is_kswapd())
+		__count_vm_events(KSWAPD_STEAL, nr_reclaimed);
+	__count_zone_vm_events(PGSTEAL, zone, nr_reclaimed);
+
 	while (!list_empty(page_list)) {
 		int lru;
 		page = lru_to_page(page_list);
@@ -1576,12 +1581,7 @@
 					priority, &nr_dirty, &nr_writeback);
 	}
 
-	local_irq_disable();
-	if (current_is_kswapd())
-		__count_vm_events(KSWAPD_STEAL, nr_reclaimed);
-	__count_zone_vm_events(PGSTEAL, zone, nr_reclaimed);
-
-	putback_lru_pages(zone, sc, nr_anon, nr_file, &page_list);
+	putback_lru_pages(zone, sc, nr_anon, nr_file, &page_list, nr_reclaimed);
 
 	/*
 	 * If reclaim is isolating dirty pages under writeback, it implies
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 8fd603b..726f0b6 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -216,6 +216,7 @@
 	long x;
 	long t;
 
+	preempt_disable_rt();
 	x = delta + __this_cpu_read(*p);
 
 	t = __this_cpu_read(pcp->stat_threshold);
@@ -225,6 +226,7 @@
 		x = 0;
 	}
 	__this_cpu_write(*p, x);
+	preempt_enable_rt();
 }
 EXPORT_SYMBOL(__mod_zone_page_state);
 
@@ -257,6 +259,7 @@
 	s8 __percpu *p = pcp->vm_stat_diff + item;
 	s8 v, t;
 
+	preempt_disable_rt();
 	v = __this_cpu_inc_return(*p);
 	t = __this_cpu_read(pcp->stat_threshold);
 	if (unlikely(v > t)) {
@@ -265,6 +268,7 @@
 		zone_page_state_add(v + overstep, zone, item);
 		__this_cpu_write(*p, -overstep);
 	}
+	preempt_enable_rt();
 }
 
 void __inc_zone_page_state(struct page *page, enum zone_stat_item item)
@@ -279,6 +283,7 @@
 	s8 __percpu *p = pcp->vm_stat_diff + item;
 	s8 v, t;
 
+	preempt_disable_rt();
 	v = __this_cpu_dec_return(*p);
 	t = __this_cpu_read(pcp->stat_threshold);
 	if (unlikely(v < - t)) {
@@ -287,6 +292,7 @@
 		zone_page_state_add(v - overstep, zone, item);
 		__this_cpu_write(*p, overstep);
 	}
+	preempt_enable_rt();
 }
 
 void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
diff --git a/net/core/dev.c b/net/core/dev.c
index 7f43202..dd452fc 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -222,14 +222,14 @@
 static inline void rps_lock(struct softnet_data *sd)
 {
 #ifdef CONFIG_RPS
-	spin_lock(&sd->input_pkt_queue.lock);
+	raw_spin_lock(&sd->input_pkt_queue.raw_lock);
 #endif
 }
 
 static inline void rps_unlock(struct softnet_data *sd)
 {
 #ifdef CONFIG_RPS
-	spin_unlock(&sd->input_pkt_queue.lock);
+	raw_spin_unlock(&sd->input_pkt_queue.raw_lock);
 #endif
 }
 
@@ -1821,6 +1821,7 @@
 	sd->output_queue_tailp = &q->next_sched;
 	raise_softirq_irqoff(NET_TX_SOFTIRQ);
 	local_irq_restore(flags);
+	preempt_check_resched_rt();
 }
 
 void __netif_schedule(struct Qdisc *q)
@@ -1842,6 +1843,7 @@
 		sd->completion_queue = skb;
 		raise_softirq_irqoff(NET_TX_SOFTIRQ);
 		local_irq_restore(flags);
+		preempt_check_resched_rt();
 	}
 }
 EXPORT_SYMBOL(dev_kfree_skb_irq);
@@ -2974,6 +2976,7 @@
 	rps_unlock(sd);
 
 	local_irq_restore(flags);
+	preempt_check_resched_rt();
 
 	atomic_long_inc(&skb->dev->rx_dropped);
 	kfree_skb(skb);
@@ -3012,7 +3015,7 @@
 		struct rps_dev_flow voidflow, *rflow = &voidflow;
 		int cpu;
 
-		preempt_disable();
+		migrate_disable();
 		rcu_read_lock();
 
 		cpu = get_rps_cpu(skb->dev, skb, &rflow);
@@ -3022,13 +3025,13 @@
 		ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
 
 		rcu_read_unlock();
-		preempt_enable();
+		migrate_enable();
 	}
 #else
 	{
 		unsigned int qtail;
-		ret = enqueue_to_backlog(skb, get_cpu(), &qtail);
-		put_cpu();
+		ret = enqueue_to_backlog(skb, get_cpu_light(), &qtail);
+		put_cpu_light();
 	}
 #endif
 	return ret;
@@ -3039,16 +3042,46 @@
 {
 	int err;
 
-	preempt_disable();
+	migrate_disable();
 	err = netif_rx(skb);
 	if (local_softirq_pending())
-		do_softirq();
-	preempt_enable();
+		thread_do_softirq();
+	migrate_enable();
 
 	return err;
 }
 EXPORT_SYMBOL(netif_rx_ni);
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+/*
+ * RT runs ksoftirqd as a real time thread and the root_lock is a
+ * "sleeping spinlock". If the trylock fails then we can go into an
+ * infinite loop when ksoftirqd preempted the task which actually
+ * holds the lock, because we requeue q and raise NET_TX softirq
+ * causing ksoftirqd to loop forever.
+ *
+ * It's safe to use spin_lock on RT here as softirqs run in thread
+ * context and cannot deadlock against the thread which is holding
+ * root_lock.
+ *
+ * On !RT the trylock might fail, but there we bail out from the
+ * softirq loop after 10 attempts which we can't do on RT. And the
+ * task holding root_lock cannot be preempted, so the only downside of
+ * that trylock is that we need 10 loops to decide that we should have
+ * given up in the first one :)
+ */
+static inline int take_root_lock(spinlock_t *lock)
+{
+	spin_lock(lock);
+	return 1;
+}
+#else
+static inline int take_root_lock(spinlock_t *lock)
+{
+	return spin_trylock(lock);
+}
+#endif
+
 static void net_tx_action(struct softirq_action *h)
 {
 	struct softnet_data *sd = &__get_cpu_var(softnet_data);
@@ -3087,7 +3120,7 @@
 			head = head->next_sched;
 
 			root_lock = qdisc_lock(q);
-			if (spin_trylock(root_lock)) {
+			if (take_root_lock(root_lock)) {
 				smp_mb__before_clear_bit();
 				clear_bit(__QDISC_STATE_SCHED,
 					  &q->state);
@@ -3416,7 +3449,7 @@
 	skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) {
 		if (skb->dev == dev) {
 			__skb_unlink(skb, &sd->input_pkt_queue);
-			kfree_skb(skb);
+			__skb_queue_tail(&sd->tofree_queue, skb);
 			input_queue_head_incr(sd);
 		}
 	}
@@ -3425,10 +3458,13 @@
 	skb_queue_walk_safe(&sd->process_queue, skb, tmp) {
 		if (skb->dev == dev) {
 			__skb_unlink(skb, &sd->process_queue);
-			kfree_skb(skb);
+			__skb_queue_tail(&sd->tofree_queue, skb);
 			input_queue_head_incr(sd);
 		}
 	}
+
+	if (!skb_queue_empty(&sd->tofree_queue))
+		raise_softirq_irqoff(NET_RX_SOFTIRQ);
 }
 
 static int napi_gro_complete(struct sk_buff *skb)
@@ -3767,6 +3803,7 @@
 	} else
 #endif
 		local_irq_enable();
+	preempt_check_resched_rt();
 }
 
 static int process_backlog(struct napi_struct *napi, int quota)
@@ -3841,6 +3878,7 @@
 	local_irq_save(flags);
 	____napi_schedule(&__get_cpu_var(softnet_data), n);
 	local_irq_restore(flags);
+	preempt_check_resched_rt();
 }
 EXPORT_SYMBOL(__napi_schedule);
 
@@ -3915,10 +3953,17 @@
 	struct softnet_data *sd = &__get_cpu_var(softnet_data);
 	unsigned long time_limit = jiffies + 2;
 	int budget = netdev_budget;
+	struct sk_buff *skb;
 	void *have;
 
 	local_irq_disable();
 
+	while ((skb = __skb_dequeue(&sd->tofree_queue))) {
+		local_irq_enable();
+		kfree_skb(skb);
+		local_irq_disable();
+	}
+
 	while (!list_empty(&sd->poll_list)) {
 		struct napi_struct *n;
 		int work, weight;
@@ -6354,6 +6399,7 @@
 
 	raise_softirq_irqoff(NET_TX_SOFTIRQ);
 	local_irq_enable();
+	preempt_check_resched_rt();
 
 	/* Process offline CPU's input_pkt_queue */
 	while ((skb = __skb_dequeue(&oldsd->process_queue))) {
@@ -6364,6 +6410,9 @@
 		netif_rx(skb);
 		input_queue_head_incr(oldsd);
 	}
+	while ((skb = __skb_dequeue(&oldsd->tofree_queue))) {
+		kfree_skb(skb);
+	}
 
 	return NOTIFY_OK;
 }
@@ -6631,8 +6680,9 @@
 		struct softnet_data *sd = &per_cpu(softnet_data, i);
 
 		memset(sd, 0, sizeof(*sd));
-		skb_queue_head_init(&sd->input_pkt_queue);
-		skb_queue_head_init(&sd->process_queue);
+		skb_queue_head_init_raw(&sd->input_pkt_queue);
+		skb_queue_head_init_raw(&sd->process_queue);
+		skb_queue_head_init_raw(&sd->tofree_queue);
 		sd->completion_queue = NULL;
 		INIT_LIST_HEAD(&sd->poll_list);
 		sd->output_queue = NULL;
diff --git a/net/core/sock.c b/net/core/sock.c
index e093528..fb9464e 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2037,12 +2037,11 @@
 	if (sk->sk_lock.owned)
 		__lock_sock(sk);
 	sk->sk_lock.owned = 1;
-	spin_unlock(&sk->sk_lock.slock);
+	spin_unlock_bh(&sk->sk_lock.slock);
 	/*
 	 * The sk_lock has mutex_lock() semantics here:
 	 */
 	mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_);
-	local_bh_enable();
 }
 EXPORT_SYMBOL(lock_sock_nested);
 
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index ab188ae..028eb47 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -67,6 +67,7 @@
 #include <linux/jiffies.h>
 #include <linux/kernel.h>
 #include <linux/fcntl.h>
+#include <linux/sysrq.h>
 #include <linux/socket.h>
 #include <linux/in.h>
 #include <linux/inet.h>
@@ -801,6 +802,30 @@
 }
 
 /*
+ * 32bit and 64bit have different timestamp length, so we check for
+ * the cookie at offset 20 and verify it is repeated at offset 50
+ */
+#define CO_POS0		20
+#define CO_POS1		50
+#define CO_SIZE		sizeof(int)
+#define ICMP_SYSRQ_SIZE	57
+
+/*
+ * We got a ICMP_SYSRQ_SIZE sized ping request. Check for the cookie
+ * pattern and if it matches send the next byte as a trigger to sysrq.
+ */
+static void icmp_check_sysrq(struct net *net, struct sk_buff *skb)
+{
+	int cookie = htonl(net->ipv4.sysctl_icmp_echo_sysrq);
+	char *p = skb->data;
+
+	if (!memcmp(&cookie, p + CO_POS0, CO_SIZE) &&
+	    !memcmp(&cookie, p + CO_POS1, CO_SIZE) &&
+	    p[CO_POS0 + CO_SIZE] == p[CO_POS1 + CO_SIZE])
+		handle_sysrq(p[CO_POS0 + CO_SIZE]);
+}
+
+/*
  *	Handle ICMP_ECHO ("ping") requests.
  *
  *	RFC 1122: 3.2.2.6 MUST have an echo server that answers ICMP echo
@@ -827,6 +852,11 @@
 		icmp_param.data_len	   = skb->len;
 		icmp_param.head_len	   = sizeof(struct icmphdr);
 		icmp_reply(&icmp_param, skb);
+
+		if (skb->len == ICMP_SYSRQ_SIZE &&
+		    net->ipv4.sysctl_icmp_echo_sysrq) {
+			icmp_check_sysrq(net, skb);
+		}
 	}
 }
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 8e79a9e..6a7046e 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -254,7 +254,7 @@
 };
 
 #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) || \
-	defined(CONFIG_PROVE_LOCKING)
+	defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_PREEMPT_RT_FULL)
 /*
  * Instead of using one spinlock for each rt_hash_bucket, we use a table of spinlocks
  * The size of this table is a power of two and depends on the number of CPUS.
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 253dd80..9315cdc 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -693,6 +693,13 @@
 		.proc_handler	= proc_dointvec
 	},
 	{
+		.procname	= "icmp_echo_sysrq",
+		.data		= &init_net.ipv4.sysctl_icmp_echo_sysrq,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
 		.procname	= "icmp_ignore_bogus_error_responses",
 		.data		= &init_net.ipv4.sysctl_icmp_ignore_bogus_error_responses,
 		.maxlen		= sizeof(int),
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 7c53eff..bedade3 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -3017,7 +3017,7 @@
 	struct ieee80211_supported_band *sband;
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
 
-	WARN_ON_ONCE(softirq_count() == 0);
+	WARN_ON_ONCE_NONRT(softirq_count() == 0);
 
 	if (WARN_ON(status->band < 0 ||
 		    status->band >= IEEE80211_NUM_BANDS))
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index afca6c7..aa3f87b 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -20,11 +20,17 @@
 #include <linux/proc_fs.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
+#include <linux/locallock.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
 
 #include "nf_internals.h"
 
+#ifdef CONFIG_PREEMPT_RT_BASE
+DEFINE_LOCAL_IRQ_LOCK(xt_write_lock);
+EXPORT_PER_CPU_SYMBOL(xt_write_lock);
+#endif
+
 static DEFINE_MUTEX(afinfo_mutex);
 
 const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO] __read_mostly;
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 0c21f06..9f2ab3c 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -89,6 +89,7 @@
 #include <linux/virtio_net.h>
 #include <linux/errqueue.h>
 #include <linux/net_tstamp.h>
+#include <linux/delay.h>
 
 #ifdef CONFIG_INET
 #include <net/inet_common.h>
@@ -681,7 +682,7 @@
 	if (BLOCK_NUM_PKTS(pbd)) {
 		while (atomic_read(&pkc->blk_fill_in_prog)) {
 			/* Waiting for skb_copy_bits to finish... */
-			cpu_relax();
+			cpu_chill();
 		}
 	}
 
@@ -926,7 +927,7 @@
 		if (!(status & TP_STATUS_BLK_TMO)) {
 			while (atomic_read(&pkc->blk_fill_in_prog)) {
 				/* Waiting for skb_copy_bits to finish... */
-				cpu_relax();
+				cpu_chill();
 			}
 		}
 		prb_close_block(pkc, pbd, po, status);
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index a985158..0f63c71 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -34,6 +34,7 @@
 #include <linux/slab.h>
 #include <linux/rculist.h>
 #include <linux/llist.h>
+#include <linux/delay.h>
 
 #include "rds.h"
 #include "ib.h"
@@ -286,7 +287,7 @@
 	for_each_online_cpu(cpu) {
 		flag = &per_cpu(clean_list_grace, cpu);
 		while (test_bit(CLEAN_LIST_BUSY_BIT, flag))
-			cpu_relax();
+			cpu_chill();
 	}
 }
 
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 69fca27..9ede52e 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -847,7 +847,7 @@
 	/* Wait for outstanding qdisc_run calls. */
 	list_for_each_entry(dev, head, unreg_list)
 		while (some_qdisc_is_busy(dev))
-			yield();
+			msleep(1);
 }
 
 void dev_deactivate(struct net_device *dev)
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 9acee9d..877ec8c 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -322,9 +322,9 @@
 	if (!svc_xprt_has_something_to_do(xprt))
 		return;
 
-	cpu = get_cpu();
+	cpu = get_cpu_light();
 	pool = svc_pool_for_cpu(xprt->xpt_server, cpu);
-	put_cpu();
+	put_cpu_light();
 
 	spin_lock_bh(&pool->sp_lock);
 
diff --git a/scripts/mkcompile_h b/scripts/mkcompile_h
index f221ddf..5f44009 100755
--- a/scripts/mkcompile_h
+++ b/scripts/mkcompile_h
@@ -4,7 +4,8 @@
 ARCH=$2
 SMP=$3
 PREEMPT=$4
-CC=$5
+RT=$5
+CC=$6
 
 vecho() { [ "${quiet}" = "silent_" ] || echo "$@" ; }
 
@@ -57,6 +58,7 @@
 CONFIG_FLAGS=""
 if [ -n "$SMP" ] ; then CONFIG_FLAGS="SMP"; fi
 if [ -n "$PREEMPT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS PREEMPT"; fi
+if [ -n "$RT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS RT"; fi
 UTS_VERSION="$UTS_VERSION $CONFIG_FLAGS $TIMESTAMP"
 
 # Truncate to maximum length