diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html
index 57300db4b5ff6..31c99382994e0 100644
--- a/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.html
@@ -56,8 +56,8 @@ sections.
 RCU-preempt Expedited Grace Periods</a></h2>
 
 <p>
-<tt>CONFIG_PREEMPT=y</tt> kernels implement RCU-preempt.
-The overall flow of the handling of a given CPU by an RCU-preempt
+<tt>CONFIG_PREEMPT=y</tt> and <tt>CONFIG_PREEMPT_RT=y</tt> kernels implement
+RCU-preempt. The overall flow of the handling of a given CPU by an RCU-preempt
 expedited grace period is shown in the following diagram:
 
 <p><img src="ExpRCUFlow.svg" alt="ExpRCUFlow.svg" width="55%">
@@ -140,8 +140,8 @@ or offline, among other things.
 RCU-sched Expedited Grace Periods</a></h2>
 
 <p>
-<tt>CONFIG_PREEMPT=n</tt> kernels implement RCU-sched.
-The overall flow of the handling of a given CPU by an RCU-sched
+<tt>CONFIG_PREEMPT=n</tt> and <tt>CONFIG_PREEMPT_RT=n</tt> kernels implement
+RCU-sched. The overall flow of the handling of a given CPU by an RCU-sched
 expedited grace period is shown in the following diagram:
 
 <p><img src="ExpSchedFlow.svg" alt="ExpSchedFlow.svg" width="55%">
diff --git a/Documentation/RCU/Design/Requirements/Requirements.html b/Documentation/RCU/Design/Requirements/Requirements.html
index 467251f7fef69..348c5db1ff2bb 100644
--- a/Documentation/RCU/Design/Requirements/Requirements.html
+++ b/Documentation/RCU/Design/Requirements/Requirements.html
@@ -106,7 +106,7 @@ big RCU read-side critical section.
 Production-quality implementations of <tt>rcu_read_lock()</tt> and
 <tt>rcu_read_unlock()</tt> are extremely lightweight, and in
 fact have exactly zero overhead in Linux kernels built for production
-use with <tt>CONFIG_PREEMPT=n</tt>.
+use with <tt>CONFIG_PREEMPTION=n</tt>.
 
 <p>
 This guarantee allows ordering to be enforced with extremely low
@@ -1499,7 +1499,7 @@ costs have plummeted.
 However, as I learned from Matt Mackall's
 <a href="http://elinux.org/Linux_Tiny-FAQ">bloatwatch</a>
 efforts, memory footprint is critically important on single-CPU systems with
-non-preemptible (<tt>CONFIG_PREEMPT=n</tt>) kernels, and thus
+non-preemptible (<tt>CONFIG_PREEMPTION=n</tt>) kernels, and thus
 <a href="https://lkml.kernel.org/g/20090113221724.GA15307@linux.vnet.ibm.com">tiny RCU</a>
 was born.
 Josh Triplett has since taken over the small-memory banner with his
@@ -1887,7 +1887,7 @@ constructs, there are limitations.
 <p>
 Implementations of RCU for which <tt>rcu_read_lock()</tt>
 and <tt>rcu_read_unlock()</tt> generate no code, such as
-Linux-kernel RCU when <tt>CONFIG_PREEMPT=n</tt>, can be
+Linux-kernel RCU when <tt>CONFIG_PREEMPTION=n</tt>, can be
 nested arbitrarily deeply.
 After all, there is no overhead.
 Except that if all these instances of <tt>rcu_read_lock()</tt>
@@ -2229,7 +2229,7 @@ be a no-op.
 <p>
 However, once the scheduler has spawned its first kthread, this early
 boot trick fails for <tt>synchronize_rcu()</tt> (as well as for
-<tt>synchronize_rcu_expedited()</tt>) in <tt>CONFIG_PREEMPT=y</tt>
+<tt>synchronize_rcu_expedited()</tt>) in <tt>CONFIG_PREEMPTION=y</tt>
 kernels.
 The reason is that an RCU read-side critical section might be preempted,
 which means that a subsequent <tt>synchronize_rcu()</tt> really does have
@@ -2568,7 +2568,7 @@ The compiler must not be permitted to transform this source code into
 
 <p>
 If the compiler did make this transformation in a
-<tt>CONFIG_PREEMPT=n</tt> kernel build, and if <tt>get_user()</tt> did
+<tt>CONFIG_PREEMPTION=n</tt> kernel build, and if <tt>get_user()</tt> did
 page fault, the result would be a quiescent state in the middle
 of an RCU read-side critical section.
 This misplaced quiescent state could result in line&nbsp;4 being
@@ -2906,7 +2906,7 @@ in conjunction with the
 The real-time-latency response requirements are such that the
 traditional approach of disabling preemption across RCU
 read-side critical sections is inappropriate.
-Kernels built with <tt>CONFIG_PREEMPT=y</tt> therefore
+Kernels built with <tt>CONFIG_PREEMPTION=y</tt> therefore
 use an RCU implementation that allows RCU read-side critical
 sections to be preempted.
 This requirement made its presence known after users made it
@@ -3064,7 +3064,7 @@ includes
 <tt>rcu_barrier_bh()</tt>, and
 <tt>rcu_read_lock_bh_held()</tt>.
 However, the update-side APIs are now simple wrappers for other RCU
-flavors, namely RCU-sched in CONFIG_PREEMPT=n kernels and RCU-preempt
+flavors, namely RCU-sched in CONFIG_PREEMPTION=n kernels and RCU-preempt
 otherwise.
 
 <h3><a name="Sched Flavor">Sched Flavor (Historical)</a></h3>
@@ -3088,12 +3088,12 @@ of an RCU read-side critical section can be a quiescent state.
 Therefore, <i>RCU-sched</i> was created, which follows &ldquo;classic&rdquo;
 RCU in that an RCU-sched grace period waits for for pre-existing
 interrupt and NMI handlers.
-In kernels built with <tt>CONFIG_PREEMPT=n</tt>, the RCU and RCU-sched
+In kernels built with <tt>CONFIG_PREEMPTION=n</tt>, the RCU and RCU-sched
 APIs have identical implementations, while kernels built with
-<tt>CONFIG_PREEMPT=y</tt> provide a separate implementation for each.
+<tt>CONFIG_PREEMPTION=y</tt> provide a separate implementation for each.
 
 <p>
-Note well that in <tt>CONFIG_PREEMPT=y</tt> kernels,
+Note well that in <tt>CONFIG_PREEMPTION=y</tt> kernels,
 <tt>rcu_read_lock_sched()</tt> and <tt>rcu_read_unlock_sched()</tt>
 disable and re-enable preemption, respectively.
 This means that if there was a preemption attempt during the
@@ -3302,12 +3302,12 @@ The tasks-RCU API is quite compact, consisting only of
 <tt>call_rcu_tasks()</tt>,
 <tt>synchronize_rcu_tasks()</tt>, and
 <tt>rcu_barrier_tasks()</tt>.
-In <tt>CONFIG_PREEMPT=n</tt> kernels, trampolines cannot be preempted,
+In <tt>CONFIG_PREEMPTION=n</tt> kernels, trampolines cannot be preempted,
 so these APIs map to
 <tt>call_rcu()</tt>,
 <tt>synchronize_rcu()</tt>, and
 <tt>rcu_barrier()</tt>, respectively.
-In <tt>CONFIG_PREEMPT=y</tt> kernels, trampolines can be preempted,
+In <tt>CONFIG_PREEMPTION=y</tt> kernels, trampolines can be preempted,
 and these three APIs are therefore implemented by separate functions
 that check for voluntary context switches.
 
diff --git a/Documentation/RCU/checklist.txt b/Documentation/RCU/checklist.txt
index e98ff261a438b..087dc6c22c37c 100644
--- a/Documentation/RCU/checklist.txt
+++ b/Documentation/RCU/checklist.txt
@@ -210,8 +210,8 @@ over a rather long period of time, but improvements are always welcome!
 	the rest of the system.
 
 7.	As of v4.20, a given kernel implements only one RCU flavor,
-	which is RCU-sched for PREEMPT=n and RCU-preempt for PREEMPT=y.
-	If the updater uses call_rcu() or synchronize_rcu(),
+	which is RCU-sched for PREEMPTION=n and RCU-preempt for
+	PREEMPTION=y. If the updater uses call_rcu() or synchronize_rcu(),
 	then the corresponding readers my use rcu_read_lock() and
 	rcu_read_unlock(), rcu_read_lock_bh() and rcu_read_unlock_bh(),
 	or any pair of primitives that disables and re-enables preemption,
diff --git a/Documentation/RCU/rcubarrier.txt b/Documentation/RCU/rcubarrier.txt
index a2782df697328..5aa93c215af46 100644
--- a/Documentation/RCU/rcubarrier.txt
+++ b/Documentation/RCU/rcubarrier.txt
@@ -6,8 +6,8 @@ RCU (read-copy update) is a synchronization mechanism that can be thought
 of as a replacement for read-writer locking (among other things), but with
 very low-overhead readers that are immune to deadlock, priority inversion,
 and unbounded latency. RCU read-side critical sections are delimited
-by rcu_read_lock() and rcu_read_unlock(), which, in non-CONFIG_PREEMPT
-kernels, generate no code whatsoever.
+by rcu_read_lock() and rcu_read_unlock(), which, in
+non-CONFIG_PREEMPTION kernels, generate no code whatsoever.
 
 This means that RCU writers are unaware of the presence of concurrent
 readers, so that RCU updates to shared data must be undertaken quite
@@ -303,10 +303,10 @@ Answer: This cannot happen. The reason is that on_each_cpu() has its last
 	to smp_call_function() and further to smp_call_function_on_cpu(),
 	causing this latter to spin until the cross-CPU invocation of
 	rcu_barrier_func() has completed. This by itself would prevent
-	a grace period from completing on non-CONFIG_PREEMPT kernels,
+	a grace period from completing on non-CONFIG_PREEMPTION kernels,
 	since each CPU must undergo a context switch (or other quiescent
 	state) before the grace period can complete. However, this is
-	of no use in CONFIG_PREEMPT kernels.
+	of no use in CONFIG_PREEMPTION kernels.
 
 	Therefore, on_each_cpu() disables preemption across its call
 	to smp_call_function() and also across the local call to
diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
index f48f4621ccbc2..bd510771b75ec 100644
--- a/Documentation/RCU/stallwarn.txt
+++ b/Documentation/RCU/stallwarn.txt
@@ -20,7 +20,7 @@ o	A CPU looping with preemption disabled.
 
 o	A CPU looping with bottom halves disabled.
 
-o	For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel
+o	For !CONFIG_PREEMPTION kernels, a CPU looping anywhere in the kernel
 	without invoking schedule().  If the looping in the kernel is
 	really expected and desirable behavior, you might need to add
 	some calls to cond_resched().
@@ -39,7 +39,7 @@ o	Anything that prevents RCU's grace-period kthreads from running.
 	result in the "rcu_.*kthread starved for" console-log message,
 	which will include additional debugging information.
 
-o	A CPU-bound real-time task in a CONFIG_PREEMPT kernel, which might
+o	A CPU-bound real-time task in a CONFIG_PREEMPTION kernel, which might
 	happen to preempt a low-priority task in the middle of an RCU
 	read-side critical section.   This is especially damaging if
 	that low-priority task is not permitted to run on any other CPU,
diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index 7e1a8721637ab..7e03e8f80b293 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -648,9 +648,10 @@ Quick Quiz #1:	Why is this argument naive?  How could a deadlock
 
 This section presents a "toy" RCU implementation that is based on
 "classic RCU".  It is also short on performance (but only for updates) and
-on features such as hotplug CPU and the ability to run in CONFIG_PREEMPT
-kernels.  The definitions of rcu_dereference() and rcu_assign_pointer()
-are the same as those shown in the preceding section, so they are omitted.
+on features such as hotplug CPU and the ability to run in
+CONFIG_PREEMPTION kernels. The definitions of rcu_dereference() and
+rcu_assign_pointer() are the same as those shown in the preceding
+section, so they are omitted.
 
 	void rcu_read_lock(void) { }
 
diff --git a/Documentation/printk-ringbuffer.txt b/Documentation/printk-ringbuffer.txt
new file mode 100644
index 0000000000000..6bde5dbd8545b
--- /dev/null
+++ b/Documentation/printk-ringbuffer.txt
@@ -0,0 +1,377 @@
+struct printk_ringbuffer
+------------------------
+John Ogness <john.ogness@linutronix.de>
+
+Overview
+~~~~~~~~
+As the name suggests, this ring buffer was implemented specifically to serve
+the needs of the printk() infrastructure. The ring buffer itself is not
+specific to printk and could be used for other purposes. _However_, the
+requirements and semantics of printk are rather unique. If you intend to use
+this ring buffer for anything other than printk, you need to be very clear on
+its features, behavior, and pitfalls.
+
+Features
+^^^^^^^^
+The printk ring buffer has the following features:
+
+- single global buffer
+- resides in initialized data section (available at early boot)
+- lockless readers
+- supports multiple writers
+- supports multiple non-consuming readers
+- safe from any context (including NMI)
+- groups bytes into variable length blocks (referenced by entries)
+- entries tagged with sequence numbers
+
+Behavior
+^^^^^^^^
+Since the printk ring buffer readers are lockless, there exists no
+synchronization between readers and writers. Basically writers are the tasks
+in control and may overwrite any and all committed data at any time and from
+any context. For this reason readers can miss entries if they are overwritten
+before the reader was able to access the data. The reader API implementation
+is such that reader access to entries is atomic, so there is no risk of
+readers having to deal with partial or corrupt data. Also, entries are
+tagged with sequence numbers so readers can recognize if entries were missed.
+
+Writing to the ring buffer consists of 2 steps. First a writer must reserve
+an entry of desired size. After this step the writer has exclusive access
+to the memory region. Once the data has been written to memory, it needs to
+be committed to the ring buffer. After this step the entry has been inserted
+into the ring buffer and assigned an appropriate sequence number.
+
+Once committed, a writer must no longer access the data directly. This is
+because the data may have been overwritten and no longer exists. If a
+writer must access the data, it should either keep a private copy before
+committing the entry or use the reader API to gain access to the data.
+
+Because of how the data backend is implemented, entries that have been
+reserved but not yet committed act as barriers, preventing future writers
+from filling the ring buffer beyond the location of the reserved but not
+yet committed entry region. For this reason it is *important* that writers
+perform both reserve and commit as quickly as possible. Also, be aware that
+preemption and local interrupts are disabled and writing to the ring buffer
+is processor-reentrant locked during the reserve/commit window. Writers in
+NMI contexts can still preempt any other writers, but as long as these
+writers do not write a large amount of data with respect to the ring buffer
+size, this should not become an issue.
+
+API
+~~~
+
+Declaration
+^^^^^^^^^^^
+The printk ring buffer can be instantiated as a static structure:
+
+ /* declare a static struct printk_ringbuffer */
+ #define DECLARE_STATIC_PRINTKRB(name, szbits, cpulockptr)
+
+The value of szbits specifies the size of the ring buffer in bits. The
+cpulockptr field is a pointer to a prb_cpulock struct that is used to
+perform processor-reentrant spin locking for the writers. It is specified
+externally because it may be used for multiple ring buffers (or other
+code) to synchronize writers without risk of deadlock.
+
+Here is an example of a declaration of a printk ring buffer specifying a
+32KB (2^15) ring buffer:
+
+....
+DECLARE_STATIC_PRINTKRB_CPULOCK(rb_cpulock);
+DECLARE_STATIC_PRINTKRB(rb, 15, &rb_cpulock);
+....
+
+If writers will be using multiple ring buffers and the ordering of that usage
+is not clear, the same prb_cpulock should be used for both ring buffers.
+
+Writer API
+^^^^^^^^^^
+The writer API consists of 2 functions. The first is to reserve an entry in
+the ring buffer, the second is to commit that data to the ring buffer. The
+reserved entry information is stored within a provided `struct prb_handle`.
+
+ /* reserve an entry */
+ char *prb_reserve(struct prb_handle *h, struct printk_ringbuffer *rb,
+                   unsigned int size);
+
+ /* commit a reserved entry to the ring buffer */
+ void prb_commit(struct prb_handle *h);
+
+Here is an example of a function to write data to a ring buffer:
+
+....
+int write_data(struct printk_ringbuffer *rb, char *data, int size)
+{
+    struct prb_handle h;
+    char *buf;
+
+    buf = prb_reserve(&h, rb, size);
+    if (!buf)
+        return -1;
+    memcpy(buf, data, size);
+    prb_commit(&h);
+
+    return 0;
+}
+....
+
+Pitfalls
+++++++++
+Be aware that prb_reserve() can fail. A retry might be successful, but it
+depends entirely on whether or not the next part of the ring buffer to
+overwrite belongs to reserved but not yet committed entries of other writers.
+Writers can use the prb_inc_lost() function to allow readers to notice that a
+message was lost.
+
+Reader API
+^^^^^^^^^^
+The reader API utilizes a `struct prb_iterator` to track the reader's
+position in the ring buffer.
+
+ /* declare a pre-initialized static iterator for a ring buffer */
+ #define DECLARE_STATIC_PRINTKRB_ITER(name, rbaddr)
+
+ /* initialize iterator for a ring buffer (if static macro NOT used) */
+ void prb_iter_init(struct prb_iterator *iter,
+                    struct printk_ringbuffer *rb, u64 *seq);
+
+ /* make a deep copy of an iterator */
+ void prb_iter_copy(struct prb_iterator *dest,
+                    struct prb_iterator *src);
+
+ /* non-blocking, advance to next entry (and read the data) */
+ int prb_iter_next(struct prb_iterator *iter, char *buf,
+                   int size, u64 *seq);
+
+ /* blocking, advance to next entry (and read the data) */
+ int prb_iter_wait_next(struct prb_iterator *iter, char *buf,
+                        int size, u64 *seq);
+
+ /* position iterator at the entry seq */
+ int prb_iter_seek(struct prb_iterator *iter, u64 seq);
+
+ /* read data at current position */
+ int prb_iter_data(struct prb_iterator *iter, char *buf,
+                   int size, u64 *seq);
+
+Typically prb_iter_data() is not needed because the data can be retrieved
+directly with prb_iter_next().
+
+Here is an example of a non-blocking function that will read all the data in
+a ring buffer:
+
+....
+void read_all_data(struct printk_ringbuffer *rb, char *buf, int size)
+{
+    struct prb_iterator iter;
+    u64 prev_seq = 0;
+    u64 seq;
+    int ret;
+
+    prb_iter_init(&iter, rb, NULL);
+
+    for (;;) {
+        ret = prb_iter_next(&iter, buf, size, &seq);
+        if (ret > 0) {
+            if (seq != ++prev_seq) {
+                /* "seq - prev_seq" entries missed */
+                prev_seq = seq;
+            }
+            /* process buf here */
+        } else if (ret == 0) {
+            /* hit the end, done */
+            break;
+        } else if (ret < 0) {
+            /*
+             * iterator is invalid, a writer overtook us, reset the
+             * iterator and keep going, entries were missed
+             */
+            prb_iter_init(&iter, rb, NULL);
+        }
+    }
+}
+....
+
+Pitfalls
+++++++++
+The reader's iterator can become invalid at any time because the reader was
+overtaken by a writer. Typically the reader should reset the iterator back
+to the current oldest entry (which will be newer than the entry the reader
+was at) and continue, noting the number of entries that were missed.
+
+Utility API
+^^^^^^^^^^^
+Several functions are available as convenience for external code.
+
+ /* query the size of the data buffer */
+ int prb_buffer_size(struct printk_ringbuffer *rb);
+
+ /* skip a seq number to signify a lost record */
+ void prb_inc_lost(struct printk_ringbuffer *rb);
+
+ /* processor-reentrant spin lock */
+ void prb_lock(struct prb_cpulock *cpu_lock, unsigned int *cpu_store);
+
+ /* processor-reentrant spin unlock */
+ void prb_lock(struct prb_cpulock *cpu_lock, unsigned int *cpu_store);
+
+Pitfalls
+++++++++
+Although the value returned by prb_buffer_size() does represent an absolute
+upper bound, the amount of data that can be stored within the ring buffer
+is actually less because of the additional storage space of a header for each
+entry.
+
+The prb_lock() and prb_unlock() functions can be used to synchronize between
+ring buffer writers and other external activities. The function of a
+processor-reentrant spin lock is to disable preemption and local interrupts
+and synchronize against other processors. It does *not* protect against
+multiple contexts of a single processor, i.e NMI.
+
+Implementation
+~~~~~~~~~~~~~~
+This section describes several of the implementation concepts and details to
+help developers better understand the code.
+
+Entries
+^^^^^^^
+All ring buffer data is stored within a single static byte array. The reason
+for this is to ensure that any pointers to the data (past and present) will
+always point to valid memory. This is important because the lockless readers
+may be preempted for long periods of time and when they resume may be working
+with expired pointers.
+
+Entries are identified by start index and size. (The start index plus size
+is the start index of the next entry.) The start index is not simply an
+offset into the byte array, but rather a logical position (lpos) that maps
+directly to byte array offsets.
+
+For example, for a byte array of 1000, an entry may have have a start index
+of 100. Another entry may have a start index of 1100. And yet another 2100.
+All of these entry are pointing to the same memory region, but only the most
+recent entry is valid. The other entries are pointing to valid memory, but
+represent entries that have been overwritten.
+
+Note that due to overflowing, the most recent entry is not necessarily the one
+with the highest lpos value. Indeed, the printk ring buffer initializes its
+data such that an overflow happens relatively quickly in order to validate the
+handling of this situation. The implementation assumes that an lpos (unsigned
+long) will never completely wrap while a reader is preempted. If this were to
+become an issue, the seq number (which never wraps) could be used to increase
+the robustness of handling this situation.
+
+Buffer Wrapping
+^^^^^^^^^^^^^^^
+If an entry starts near the end of the byte array but would extend beyond it,
+a special terminating entry (size = -1) is inserted into the byte array and
+the real entry is placed at the beginning of the byte array. This can waste
+space at the end of the byte array, but simplifies the implementation by
+allowing writers to always work with contiguous buffers.
+
+Note that the size field is the first 4 bytes of the entry header. Also note
+that calc_next() always ensures that there are at least 4 bytes left at the
+end of the byte array to allow room for a terminating entry.
+
+Ring Buffer Pointers
+^^^^^^^^^^^^^^^^^^^^
+Three pointers (lpos values) are used to manage the ring buffer:
+
+ - _tail_: points to the oldest entry
+ - _head_: points to where the next new committed entry will be
+ - _reserve_: points to where the next new reserved entry will be
+
+These pointers always maintain a logical ordering:
+
+ tail <= head <= reserve
+
+The reserve pointer moves forward when a writer reserves a new entry. The
+head pointer moves forward when a writer commits a new entry.
+
+The reserve pointer cannot overwrite the tail pointer in a wrap situation. In
+such a situation, the tail pointer must be "pushed forward", thus
+invalidating that oldest entry. Readers identify if they are accessing a
+valid entry by ensuring their entry pointer is `>= tail && < head`.
+
+If the tail pointer is equal to the head pointer, it cannot be pushed and any
+reserve operation will fail. The only resolution is for writers to commit
+their reserved entries.
+
+Processor-Reentrant Locking
+^^^^^^^^^^^^^^^^^^^^^^^^^^^
+The purpose of the processor-reentrant locking is to limit the interruption
+scenarios of writers to 2 contexts. This allows for a simplified
+implementation where:
+
+- The reserve/commit window only exists on 1 processor at a time. A reserve
+  can never fail due to uncommitted entries of other processors.
+
+- When committing entries, it is trivial to handle the situation when
+  subsequent entries have already been committed, i.e. managing the head
+  pointer.
+
+Performance
+~~~~~~~~~~~
+Some basic tests were performed on a quad Intel(R) Xeon(R) CPU E5-2697 v4 at
+2.30GHz (36 cores / 72 threads). All tests involved writing a total of
+32,000,000 records at an average of 33 bytes each. Each writer was pinned to
+its own CPU and would write as fast as it could until a total of 32,000,000
+records were written. All tests involved 2 readers that were both pinned
+together to another CPU. Each reader would read as fast as it could and track
+how many of the 32,000,000 records it could read. All tests used a ring buffer
+of 16KB in size, which holds around 350 records (header + data for each
+entry).
+
+The only difference between the tests is the number of writers (and thus also
+the number of records per writer). As more writers are added, the time to
+write a record increases. This is because data pointers, modified via cmpxchg,
+and global data access in general become more contended.
+
+1 writer
+^^^^^^^^
+ runtime: 0m 18s
+ reader1: 16219900/32000000 (50%) records
+ reader2: 16141582/32000000 (50%) records
+
+2 writers
+^^^^^^^^^
+ runtime: 0m 32s
+ reader1: 16327957/32000000 (51%) records
+ reader2: 16313988/32000000 (50%) records
+
+4 writers
+^^^^^^^^^
+ runtime: 0m 42s
+ reader1: 16421642/32000000 (51%) records
+ reader2: 16417224/32000000 (51%) records
+
+8 writers
+^^^^^^^^^
+ runtime: 0m 43s
+ reader1: 16418300/32000000 (51%) records
+ reader2: 16432222/32000000 (51%) records
+
+16 writers
+^^^^^^^^^^
+ runtime: 0m 54s
+ reader1: 16539189/32000000 (51%) records
+ reader2: 16542711/32000000 (51%) records
+
+32 writers
+^^^^^^^^^^
+ runtime: 1m 13s
+ reader1: 16731808/32000000 (52%) records
+ reader2: 16735119/32000000 (52%) records
+
+Comments
+^^^^^^^^
+It is particularly interesting to compare/contrast the 1-writer and 32-writer
+tests. Despite the writing of the 32,000,000 records taking over 4 times
+longer, the readers (which perform no cmpxchg) were still unable to keep up.
+This shows that the memory contention between the increasing number of CPUs
+also has a dramatic effect on readers.
+
+It should also be noted that in all cases each reader was able to read >=50%
+of the records. This means that a single reader would have been able to keep
+up with the writer(s) in all cases, becoming slightly easier as more writers
+are added. This was the purpose of pinning 2 readers to 1 CPU: to observe how
+maximum reader performance changes.
diff --git a/Documentation/trace/ftrace-uses.rst b/Documentation/trace/ftrace-uses.rst
index 1fbc69894eed0..1e0020b0bc745 100644
--- a/Documentation/trace/ftrace-uses.rst
+++ b/Documentation/trace/ftrace-uses.rst
@@ -146,7 +146,7 @@ FTRACE_OPS_FL_RECURSION_SAFE
 	itself or any nested functions that those functions call.
 
 	If this flag is set, it is possible that the callback will also
-	be called with preemption enabled (when CONFIG_PREEMPT is set),
+	be called with preemption enabled (when CONFIG_PREEMPTION is set),
 	but this is not guaranteed.
 
 FTRACE_OPS_FL_IPMODIFY
diff --git a/arch/Kconfig b/arch/Kconfig
index 5f8a5d84dbbe9..d71dd2b76c988 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -31,6 +31,7 @@ config OPROFILE
 	tristate "OProfile system profiling"
 	depends on PROFILING
 	depends on HAVE_OPROFILE
+	depends on !PREEMPT_RT
 	select RING_BUFFER
 	select RING_BUFFER_ALLOW_SWAP
 	help
diff --git a/arch/alpha/include/asm/spinlock_types.h b/arch/alpha/include/asm/spinlock_types.h
index 1d5716bc060be..6883bc952d224 100644
--- a/arch/alpha/include/asm/spinlock_types.h
+++ b/arch/alpha/include/asm/spinlock_types.h
@@ -2,10 +2,6 @@
 #ifndef _ALPHA_SPINLOCK_TYPES_H
 #define _ALPHA_SPINLOCK_TYPES_H
 
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
 typedef struct {
 	volatile unsigned int lock;
 } arch_spinlock_t;
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
index 72be01270e246..1f6bb184a44db 100644
--- a/arch/arc/kernel/entry.S
+++ b/arch/arc/kernel/entry.S
@@ -337,11 +337,11 @@ ENTRY(ret_from_exception)
 resume_kernel_mode:
 
 	; Disable Interrupts from this point on
-	; CONFIG_PREEMPT: This is a must for preempt_schedule_irq()
-	; !CONFIG_PREEMPT: To ensure restore_regs is intr safe
+	; CONFIG_PREEMPTION: This is a must for preempt_schedule_irq()
+	; !CONFIG_PREEMPTION: To ensure restore_regs is intr safe
 	IRQ_DISABLE	r9
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 
 	; Can't preempt if preemption disabled
 	GET_CURR_THR_INFO_FROM_SP   r10
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 8a50efb559f35..0e95b6d0bd74c 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -32,6 +32,7 @@ config ARM
 	select ARCH_OPTIONAL_KERNEL_RWX if ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_OPTIONAL_KERNEL_RWX_DEFAULT if CPU_V7
 	select ARCH_SUPPORTS_ATOMIC_RMW
+	select ARCH_SUPPORTS_RT
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
@@ -64,7 +65,7 @@ config ARM
 	select HARDIRQS_SW_RESEND
 	select HAVE_ARCH_AUDITSYSCALL if AEABI && !OABI_COMPAT
 	select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
-	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
+	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU && !PREEMPT_RT
 	select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
 	select HAVE_ARCH_SECCOMP_FILTER if AEABI && !OABI_COMPAT
@@ -102,6 +103,7 @@ config ARM
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
+	select HAVE_PREEMPT_LAZY
 	select HAVE_RCU_TABLE_FREE if SMP && ARM_LPAE
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RSEQ
diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h
index 46d41140df27d..c421b5b81946e 100644
--- a/arch/arm/include/asm/irq.h
+++ b/arch/arm/include/asm/irq.h
@@ -23,6 +23,8 @@
 #endif
 
 #ifndef __ASSEMBLY__
+#include <linux/cpumask.h>
+
 struct irqaction;
 struct pt_regs;
 
diff --git a/arch/arm/include/asm/spinlock_types.h b/arch/arm/include/asm/spinlock_types.h
index 5976958647fe1..a37c0803954ba 100644
--- a/arch/arm/include/asm/spinlock_types.h
+++ b/arch/arm/include/asm/spinlock_types.h
@@ -2,10 +2,6 @@
 #ifndef __ASM_SPINLOCK_TYPES_H
 #define __ASM_SPINLOCK_TYPES_H
 
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
 #define TICKET_SHIFT	16
 
 typedef struct {
diff --git a/arch/arm/include/asm/switch_to.h b/arch/arm/include/asm/switch_to.h
index d3e937dcee4d0..285e6248454fc 100644
--- a/arch/arm/include/asm/switch_to.h
+++ b/arch/arm/include/asm/switch_to.h
@@ -4,13 +4,20 @@
 
 #include <linux/thread_info.h>
 
+#if defined CONFIG_PREEMPT_RT && defined CONFIG_HIGHMEM
+void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p);
+#else
+static inline void
+switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) { }
+#endif
+
 /*
  * For v7 SMP cores running a preemptible kernel we may be pre-empted
  * during a TLB maintenance operation, so execute an inner-shareable dsb
  * to ensure that the maintenance completes in case we migrate to another
  * CPU.
  */
-#if defined(CONFIG_PREEMPT) && defined(CONFIG_SMP) && defined(CONFIG_CPU_V7)
+#if defined(CONFIG_PREEMPTION) && defined(CONFIG_SMP) && defined(CONFIG_CPU_V7)
 #define __complete_pending_tlbi()	dsb(ish)
 #else
 #define __complete_pending_tlbi()
@@ -26,6 +33,7 @@ extern struct task_struct *__switch_to(struct task_struct *, struct thread_info
 #define switch_to(prev,next,last)					\
 do {									\
 	__complete_pending_tlbi();					\
+	switch_kmaps(prev, next);					\
 	last = __switch_to(prev,task_thread_info(prev), task_thread_info(next));	\
 } while (0)
 
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 0d0d5178e2c32..13be9c2137e26 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -46,6 +46,7 @@ struct cpu_context_save {
 struct thread_info {
 	unsigned long		flags;		/* low level flags */
 	int			preempt_count;	/* 0 => preemptable, <0 => bug */
+	int			preempt_lazy_count; /* 0 => preemptable, <0 => bug */
 	mm_segment_t		addr_limit;	/* address limit */
 	struct task_struct	*task;		/* main task structure */
 	__u32			cpu;		/* cpu */
@@ -139,7 +140,8 @@ extern int vfp_restore_user_hwstate(struct user_vfp *,
 #define TIF_SYSCALL_TRACE	4	/* syscall trace active */
 #define TIF_SYSCALL_AUDIT	5	/* syscall auditing active */
 #define TIF_SYSCALL_TRACEPOINT	6	/* syscall tracepoint instrumentation */
-#define TIF_SECCOMP		7	/* seccomp syscall filtering active */
+#define TIF_SECCOMP		8	/* seccomp syscall filtering active */
+#define TIF_NEED_RESCHED_LAZY	7
 
 #define TIF_NOHZ		12	/* in adaptive nohz mode */
 #define TIF_USING_IWMMXT	17
@@ -149,6 +151,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp *,
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
+#define _TIF_NEED_RESCHED_LAZY	(1 << TIF_NEED_RESCHED_LAZY)
 #define _TIF_UPROBE		(1 << TIF_UPROBE)
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
@@ -164,7 +167,8 @@ extern int vfp_restore_user_hwstate(struct user_vfp *,
  * Change these and you break ASM code in entry-common.S
  */
 #define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
-				 _TIF_NOTIFY_RESUME | _TIF_UPROBE)
+				 _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
+				 _TIF_NEED_RESCHED_LAZY)
 
 #endif /* __KERNEL__ */
 #endif /* __ASM_ARM_THREAD_INFO_H */
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index c773b829ee8ee..f3a0e1cd1f048 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -53,6 +53,7 @@ int main(void)
   BLANK();
   DEFINE(TI_FLAGS,		offsetof(struct thread_info, flags));
   DEFINE(TI_PREEMPT,		offsetof(struct thread_info, preempt_count));
+  DEFINE(TI_PREEMPT_LAZY,	offsetof(struct thread_info, preempt_lazy_count));
   DEFINE(TI_ADDR_LIMIT,		offsetof(struct thread_info, addr_limit));
   DEFINE(TI_TASK,		offsetof(struct thread_info, task));
   DEFINE(TI_CPU,		offsetof(struct thread_info, cpu));
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 858d4e5415326..e917b3da4b28a 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -211,13 +211,20 @@ ENDPROC(__dabt_svc)
 	svc_entry
 	irq_handler
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	ldr	r8, [tsk, #TI_PREEMPT]		@ get preempt count
-	ldr	r0, [tsk, #TI_FLAGS]		@ get flags
 	teq	r8, #0				@ if preempt count != 0
+	bne	1f				@ return from exeption
+	ldr	r0, [tsk, #TI_FLAGS]		@ get flags
+	tst	r0, #_TIF_NEED_RESCHED		@ if NEED_RESCHED is set
+	blne	svc_preempt			@ preempt!
+
+	ldr	r8, [tsk, #TI_PREEMPT_LAZY]	@ get preempt lazy count
+	teq	r8, #0				@ if preempt lazy count != 0
 	movne	r0, #0				@ force flags to 0
-	tst	r0, #_TIF_NEED_RESCHED
+	tst	r0, #_TIF_NEED_RESCHED_LAZY
 	blne	svc_preempt
+1:
 #endif
 
 	svc_exit r5, irq = 1			@ return from exception
@@ -226,14 +233,20 @@ ENDPROC(__irq_svc)
 
 	.ltorg
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 svc_preempt:
 	mov	r8, lr
 1:	bl	preempt_schedule_irq		@ irq en/disable is done inside
 	ldr	r0, [tsk, #TI_FLAGS]		@ get new tasks TI_FLAGS
 	tst	r0, #_TIF_NEED_RESCHED
+	bne	1b
+	tst	r0, #_TIF_NEED_RESCHED_LAZY
 	reteq	r8				@ go again
-	b	1b
+	ldr	r0, [tsk, #TI_PREEMPT_LAZY]	@ get preempt lazy count
+	teq	r0, #0				@ if preempt lazy count != 0
+	beq	1b
+	ret	r8				@ go again
+
 #endif
 
 __und_fault:
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 271cb8a1eba1e..fd039b1b37319 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -53,7 +53,9 @@ saved_pc	.req	lr
 	cmp	r2, #TASK_SIZE
 	blne	addr_limit_check_failed
 	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
-	tst	r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
+	tst	r1, #((_TIF_SYSCALL_WORK | _TIF_WORK_MASK) & ~_TIF_SECCOMP)
+	bne	fast_work_pending
+	tst	r1, #_TIF_SECCOMP
 	bne	fast_work_pending
 
 
@@ -90,8 +92,11 @@ ENDPROC(ret_fast_syscall)
 	cmp	r2, #TASK_SIZE
 	blne	addr_limit_check_failed
 	ldr	r1, [tsk, #TI_FLAGS]		@ re-check for syscall tracing
-	tst	r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK
+	tst	r1, #((_TIF_SYSCALL_WORK | _TIF_WORK_MASK) & ~_TIF_SECCOMP)
+	bne	do_slower_path
+	tst	r1, #_TIF_SECCOMP
 	beq	no_work_pending
+do_slower_path:
  UNWIND(.fnend		)
 ENDPROC(ret_fast_syscall)
 
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index ab2568996ddb0..50d43ce823bfb 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -649,7 +649,8 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
 	 */
 	trace_hardirqs_off();
 	do {
-		if (likely(thread_flags & _TIF_NEED_RESCHED)) {
+		if (likely(thread_flags & (_TIF_NEED_RESCHED |
+					   _TIF_NEED_RESCHED_LAZY))) {
 			schedule();
 		} else {
 			if (unlikely(!user_mode(regs)))
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 4b0bab2607e47..329926363e66c 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -678,11 +678,9 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 		break;
 
 	case IPI_CPU_BACKTRACE:
-		printk_nmi_enter();
 		irq_enter();
 		nmi_cpu_backtrace(regs);
 		irq_exit();
-		printk_nmi_exit();
 		break;
 
 	default:
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index c053abd1fb539..abb7dd7e656fd 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -248,6 +248,8 @@ void show_stack(struct task_struct *tsk, unsigned long *sp)
 
 #ifdef CONFIG_PREEMPT
 #define S_PREEMPT " PREEMPT"
+#elif defined(CONFIG_PREEMPT_RT)
+#define S_PREEMPT " PREEMPT_RT"
 #else
 #define S_PREEMPT ""
 #endif
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 0ee8fc4b4672c..dc8f152f35566 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -135,13 +135,13 @@ ENTRY(v7_flush_dcache_all)
 	and	r1, r1, #7			@ mask of the bits for current cache only
 	cmp	r1, #2				@ see what cache we have at this level
 	blt	skip				@ skip if no cache, or just i-cache
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	save_and_disable_irqs_notrace r9	@ make cssr&csidr read atomic
 #endif
 	mcr	p15, 2, r10, c0, c0, 0		@ select current cache level in cssr
 	isb					@ isb to sych the new cssr&csidr
 	mrc	p15, 1, r1, c0, c0, 0		@ read the new csidr
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	restore_irqs_notrace r9
 #endif
 	and	r2, r1, #7			@ extract the length of the cache lines
diff --git a/arch/arm/mm/cache-v7m.S b/arch/arm/mm/cache-v7m.S
index a0035c426ce63..1bc3a0a507539 100644
--- a/arch/arm/mm/cache-v7m.S
+++ b/arch/arm/mm/cache-v7m.S
@@ -183,13 +183,13 @@ ENTRY(v7m_flush_dcache_all)
 	and	r1, r1, #7			@ mask of the bits for current cache only
 	cmp	r1, #2				@ see what cache we have at this level
 	blt	skip				@ skip if no cache, or just i-cache
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	save_and_disable_irqs_notrace r9	@ make cssr&csidr read atomic
 #endif
 	write_csselr r10, r1			@ set current cache level
 	isb					@ isb to sych the new cssr&csidr
 	read_ccsidr r1				@ read the new csidr
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	restore_irqs_notrace r9
 #endif
 	and	r2, r1, #7			@ extract the length of the cache lines
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index bd0f4821f7e11..865fd8fbfe59c 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -414,6 +414,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 	if (addr < TASK_SIZE)
 		return do_page_fault(addr, fsr, regs);
 
+	if (interrupts_enabled(regs))
+		local_irq_enable();
+
 	if (user_mode(regs))
 		goto bad_area;
 
@@ -481,6 +484,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 static int
 do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 {
+	if (interrupts_enabled(regs))
+		local_irq_enable();
+
 	do_bad_area(addr, fsr, regs);
 	return 0;
 }
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index a76f8ace9ce66..eb4a361d47d7b 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -31,6 +31,11 @@ static inline pte_t get_fixmap_pte(unsigned long vaddr)
 	return *ptep;
 }
 
+static unsigned int fixmap_idx(int type)
+{
+	return FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id();
+}
+
 void *kmap(struct page *page)
 {
 	might_sleep();
@@ -51,12 +56,13 @@ EXPORT_SYMBOL(kunmap);
 
 void *kmap_atomic(struct page *page)
 {
+	pte_t pte = mk_pte(page, kmap_prot);
 	unsigned int idx;
 	unsigned long vaddr;
 	void *kmap;
 	int type;
 
-	preempt_disable();
+	preempt_disable_nort();
 	pagefault_disable();
 	if (!PageHighMem(page))
 		return page_address(page);
@@ -76,7 +82,7 @@ void *kmap_atomic(struct page *page)
 
 	type = kmap_atomic_idx_push();
 
-	idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id();
+	idx = fixmap_idx(type);
 	vaddr = __fix_to_virt(idx);
 #ifdef CONFIG_DEBUG_HIGHMEM
 	/*
@@ -90,7 +96,10 @@ void *kmap_atomic(struct page *page)
 	 * in place, so the contained TLB flush ensures the TLB is updated
 	 * with the new mapping.
 	 */
-	set_fixmap_pte(idx, mk_pte(page, kmap_prot));
+#ifdef CONFIG_PREEMPT_RT
+	current->kmap_pte[type] = pte;
+#endif
+	set_fixmap_pte(idx, pte);
 
 	return (void *)vaddr;
 }
@@ -103,44 +112,75 @@ void __kunmap_atomic(void *kvaddr)
 
 	if (kvaddr >= (void *)FIXADDR_START) {
 		type = kmap_atomic_idx();
-		idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id();
+		idx = fixmap_idx(type);
 
 		if (cache_is_vivt())
 			__cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE);
+#ifdef CONFIG_PREEMPT_RT
+		current->kmap_pte[type] = __pte(0);
+#endif
 #ifdef CONFIG_DEBUG_HIGHMEM
 		BUG_ON(vaddr != __fix_to_virt(idx));
-		set_fixmap_pte(idx, __pte(0));
 #else
 		(void) idx;  /* to kill a warning */
 #endif
+		set_fixmap_pte(idx, __pte(0));
 		kmap_atomic_idx_pop();
 	} else if (vaddr >= PKMAP_ADDR(0) && vaddr < PKMAP_ADDR(LAST_PKMAP)) {
 		/* this address was obtained through kmap_high_get() */
 		kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)]));
 	}
 	pagefault_enable();
-	preempt_enable();
+	preempt_enable_nort();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
 
 void *kmap_atomic_pfn(unsigned long pfn)
 {
+	pte_t pte = pfn_pte(pfn, kmap_prot);
 	unsigned long vaddr;
 	int idx, type;
 	struct page *page = pfn_to_page(pfn);
 
-	preempt_disable();
+	preempt_disable_nort();
 	pagefault_disable();
 	if (!PageHighMem(page))
 		return page_address(page);
 
 	type = kmap_atomic_idx_push();
-	idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id();
+	idx = fixmap_idx(type);
 	vaddr = __fix_to_virt(idx);
 #ifdef CONFIG_DEBUG_HIGHMEM
 	BUG_ON(!pte_none(get_fixmap_pte(vaddr)));
 #endif
-	set_fixmap_pte(idx, pfn_pte(pfn, kmap_prot));
+#ifdef CONFIG_PREEMPT_RT
+	current->kmap_pte[type] = pte;
+#endif
+	set_fixmap_pte(idx, pte);
 
 	return (void *)vaddr;
 }
+#if defined CONFIG_PREEMPT_RT
+void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p)
+{
+	int i;
+
+	/*
+	 * Clear @prev's kmap_atomic mappings
+	 */
+	for (i = 0; i < prev_p->kmap_idx; i++) {
+		int idx = fixmap_idx(i);
+
+		set_fixmap_pte(idx, __pte(0));
+	}
+	/*
+	 * Restore @next_p's kmap_atomic mappings
+	 */
+	for (i = 0; i < next_p->kmap_idx; i++) {
+		int idx = fixmap_idx(i);
+
+		if (!pte_none(next_p->kmap_pte[i]))
+			set_fixmap_pte(idx, next_p->kmap_pte[i]);
+	}
+}
+#endif
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 3f047afb982c8..d7a5bf29d2118 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -35,32 +35,32 @@ config ARM64
 	select ARCH_HAS_TEARDOWN_DMA_OPS if IOMMU_SUPPORT
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
-	select ARCH_INLINE_READ_LOCK if !PREEMPT
-	select ARCH_INLINE_READ_LOCK_BH if !PREEMPT
-	select ARCH_INLINE_READ_LOCK_IRQ if !PREEMPT
-	select ARCH_INLINE_READ_LOCK_IRQSAVE if !PREEMPT
-	select ARCH_INLINE_READ_UNLOCK if !PREEMPT
-	select ARCH_INLINE_READ_UNLOCK_BH if !PREEMPT
-	select ARCH_INLINE_READ_UNLOCK_IRQ if !PREEMPT
-	select ARCH_INLINE_READ_UNLOCK_IRQRESTORE if !PREEMPT
-	select ARCH_INLINE_WRITE_LOCK if !PREEMPT
-	select ARCH_INLINE_WRITE_LOCK_BH if !PREEMPT
-	select ARCH_INLINE_WRITE_LOCK_IRQ if !PREEMPT
-	select ARCH_INLINE_WRITE_LOCK_IRQSAVE if !PREEMPT
-	select ARCH_INLINE_WRITE_UNLOCK if !PREEMPT
-	select ARCH_INLINE_WRITE_UNLOCK_BH if !PREEMPT
-	select ARCH_INLINE_WRITE_UNLOCK_IRQ if !PREEMPT
-	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE if !PREEMPT
-	select ARCH_INLINE_SPIN_TRYLOCK if !PREEMPT
-	select ARCH_INLINE_SPIN_TRYLOCK_BH if !PREEMPT
-	select ARCH_INLINE_SPIN_LOCK if !PREEMPT
-	select ARCH_INLINE_SPIN_LOCK_BH if !PREEMPT
-	select ARCH_INLINE_SPIN_LOCK_IRQ if !PREEMPT
-	select ARCH_INLINE_SPIN_LOCK_IRQSAVE if !PREEMPT
-	select ARCH_INLINE_SPIN_UNLOCK if !PREEMPT
-	select ARCH_INLINE_SPIN_UNLOCK_BH if !PREEMPT
-	select ARCH_INLINE_SPIN_UNLOCK_IRQ if !PREEMPT
-	select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE if !PREEMPT
+	select ARCH_INLINE_READ_LOCK if !PREEMPTION
+	select ARCH_INLINE_READ_LOCK_BH if !PREEMPTION
+	select ARCH_INLINE_READ_LOCK_IRQ if !PREEMPTION
+	select ARCH_INLINE_READ_LOCK_IRQSAVE if !PREEMPTION
+	select ARCH_INLINE_READ_UNLOCK if !PREEMPTION
+	select ARCH_INLINE_READ_UNLOCK_BH if !PREEMPTION
+	select ARCH_INLINE_READ_UNLOCK_IRQ if !PREEMPTION
+	select ARCH_INLINE_READ_UNLOCK_IRQRESTORE if !PREEMPTION
+	select ARCH_INLINE_WRITE_LOCK if !PREEMPTION
+	select ARCH_INLINE_WRITE_LOCK_BH if !PREEMPTION
+	select ARCH_INLINE_WRITE_LOCK_IRQ if !PREEMPTION
+	select ARCH_INLINE_WRITE_LOCK_IRQSAVE if !PREEMPTION
+	select ARCH_INLINE_WRITE_UNLOCK if !PREEMPTION
+	select ARCH_INLINE_WRITE_UNLOCK_BH if !PREEMPTION
+	select ARCH_INLINE_WRITE_UNLOCK_IRQ if !PREEMPTION
+	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE if !PREEMPTION
+	select ARCH_INLINE_SPIN_TRYLOCK if !PREEMPTION
+	select ARCH_INLINE_SPIN_TRYLOCK_BH if !PREEMPTION
+	select ARCH_INLINE_SPIN_LOCK if !PREEMPTION
+	select ARCH_INLINE_SPIN_LOCK_BH if !PREEMPTION
+	select ARCH_INLINE_SPIN_LOCK_IRQ if !PREEMPTION
+	select ARCH_INLINE_SPIN_LOCK_IRQSAVE if !PREEMPTION
+	select ARCH_INLINE_SPIN_UNLOCK if !PREEMPTION
+	select ARCH_INLINE_SPIN_UNLOCK_BH if !PREEMPTION
+	select ARCH_INLINE_SPIN_UNLOCK_IRQ if !PREEMPTION
+	select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE if !PREEMPTION
 	select ARCH_KEEP_MEMBLOCK
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_USE_QUEUED_RWLOCKS
@@ -69,6 +69,7 @@ config ARM64
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_INT128 if GCC_VERSION >= 50000 || CC_IS_CLANG
 	select ARCH_SUPPORTS_NUMA_BALANCING
+	select ARCH_SUPPORTS_RT
 	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION if COMPAT
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
 	select ARCH_WANT_FRAME_POINTERS
@@ -158,6 +159,7 @@ config ARM64
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
+	select HAVE_PREEMPT_LAZY
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_FUNCTION_ARG_ACCESS_API
 	select HAVE_RCU_TABLE_FREE
diff --git a/arch/arm64/crypto/sha256-glue.c b/arch/arm64/crypto/sha256-glue.c
index e273faca924f9..999da59f03a9d 100644
--- a/arch/arm64/crypto/sha256-glue.c
+++ b/arch/arm64/crypto/sha256-glue.c
@@ -97,7 +97,7 @@ static int sha256_update_neon(struct shash_desc *desc, const u8 *data,
 		 * input when running on a preemptible kernel, but process the
 		 * data block by block instead.
 		 */
-		if (IS_ENABLED(CONFIG_PREEMPT) &&
+		if (IS_ENABLED(CONFIG_PREEMPTION) &&
 		    chunk + sctx->count % SHA256_BLOCK_SIZE > SHA256_BLOCK_SIZE)
 			chunk = SHA256_BLOCK_SIZE -
 				sctx->count % SHA256_BLOCK_SIZE;
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index b8cf7c85ffa2a..2cc0dd8bd9f78 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -699,8 +699,8 @@ USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
  * where <label> is optional, and marks the point where execution will resume
  * after a yield has been performed. If omitted, execution resumes right after
  * the endif_yield_neon invocation. Note that the entire sequence, including
- * the provided patchup code, will be omitted from the image if CONFIG_PREEMPT
- * is not defined.
+ * the provided patchup code, will be omitted from the image if
+ * CONFIG_PREEMPTION is not defined.
  *
  * As a convenience, in the case where no patchup code is required, the above
  * sequence may be abbreviated to
@@ -728,7 +728,7 @@ USER(\label, ic	ivau, \tmp2)			// invalidate I line PoU
 	.endm
 
 	.macro		if_will_cond_yield_neon
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	get_current_task	x0
 	ldr		x0, [x0, #TSK_TI_PREEMPT]
 	sub		x0, x0, #PREEMPT_DISABLE_OFFSET
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index befe37d4bc0e5..53d846f1bfe70 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -91,6 +91,7 @@ alternative_cb_end
 
 void kvm_update_va_mask(struct alt_instr *alt,
 			__le32 *origptr, __le32 *updptr, int nr_inst);
+void kvm_compute_layout(void);
 
 static inline unsigned long __kern_hyp_va(unsigned long v)
 {
diff --git a/arch/arm64/include/asm/preempt.h b/arch/arm64/include/asm/preempt.h
index d499516470149..3b19db2db1ed0 100644
--- a/arch/arm64/include/asm/preempt.h
+++ b/arch/arm64/include/asm/preempt.h
@@ -70,20 +70,43 @@ static inline bool __preempt_count_dec_and_test(void)
 	 * interrupt occurring between the non-atomic READ_ONCE/WRITE_ONCE
 	 * pair.
 	 */
-	return !pc || !READ_ONCE(ti->preempt_count);
+	if (!pc || !READ_ONCE(ti->preempt_count))
+		return true;
+#ifdef CONFIG_PREEMPT_LAZY
+	if ((pc & ~PREEMPT_NEED_RESCHED))
+		return false;
+	if (current_thread_info()->preempt_lazy_count)
+		return false;
+	return test_thread_flag(TIF_NEED_RESCHED_LAZY);
+#else
+	return false;
+#endif
 }
 
 static inline bool should_resched(int preempt_offset)
 {
+#ifdef CONFIG_PREEMPT_LAZY
+	u64 pc = READ_ONCE(current_thread_info()->preempt_count);
+	if (pc == preempt_offset)
+		return true;
+
+	if ((pc & ~PREEMPT_NEED_RESCHED) != preempt_offset)
+		return false;
+
+	if (current_thread_info()->preempt_lazy_count)
+		return false;
+	return test_thread_flag(TIF_NEED_RESCHED_LAZY);
+#else
 	u64 pc = READ_ONCE(current_thread_info()->preempt_count);
 	return pc == preempt_offset;
+#endif
 }
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 void preempt_schedule(void);
 #define __preempt_schedule() preempt_schedule()
 void preempt_schedule_notrace(void);
 #define __preempt_schedule_notrace() preempt_schedule_notrace()
-#endif /* CONFIG_PREEMPT */
+#endif /* CONFIG_PREEMPTION */
 
 #endif /* __ASM_PREEMPT_H */
diff --git a/arch/arm64/include/asm/spinlock_types.h b/arch/arm64/include/asm/spinlock_types.h
index 18782f0c47212..6672b05350b4e 100644
--- a/arch/arm64/include/asm/spinlock_types.h
+++ b/arch/arm64/include/asm/spinlock_types.h
@@ -5,10 +5,6 @@
 #ifndef __ASM_SPINLOCK_TYPES_H
 #define __ASM_SPINLOCK_TYPES_H
 
-#if !defined(__LINUX_SPINLOCK_TYPES_H) && !defined(__ASM_SPINLOCK_H)
-# error "please don't include this file directly"
-#endif
-
 #include <asm-generic/qspinlock_types.h>
 #include <asm-generic/qrwlock_types.h>
 
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index f0cec4160136e..33328454d531e 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -29,6 +29,7 @@ struct thread_info {
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
 	u64			ttbr0;		/* saved TTBR0_EL1 */
 #endif
+	int			preempt_lazy_count;	/* 0 => preemptable, <0 => bug */
 	union {
 		u64		preempt_count;	/* 0 => preemptible, <0 => bug */
 		struct {
@@ -63,6 +64,7 @@ void arch_release_task_struct(struct task_struct *tsk);
 #define TIF_FOREIGN_FPSTATE	3	/* CPU's FP state is not current's */
 #define TIF_UPROBE		4	/* uprobe breakpoint or singlestep */
 #define TIF_FSCHECK		5	/* Check FS is USER_DS on return */
+#define TIF_NEED_RESCHED_LAZY	6
 #define TIF_NOHZ		7
 #define TIF_SYSCALL_TRACE	8	/* syscall trace active */
 #define TIF_SYSCALL_AUDIT	9	/* syscall auditing */
@@ -83,6 +85,7 @@ void arch_release_task_struct(struct task_struct *tsk);
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
 #define _TIF_FOREIGN_FPSTATE	(1 << TIF_FOREIGN_FPSTATE)
+#define _TIF_NEED_RESCHED_LAZY	(1 << TIF_NEED_RESCHED_LAZY)
 #define _TIF_NOHZ		(1 << TIF_NOHZ)
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
@@ -96,8 +99,9 @@ void arch_release_task_struct(struct task_struct *tsk);
 
 #define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
 				 _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \
-				 _TIF_UPROBE | _TIF_FSCHECK)
+				 _TIF_UPROBE | _TIF_FSCHECK | _TIF_NEED_RESCHED_LAZY)
 
+#define _TIF_NEED_RESCHED_MASK	(_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)
 #define _TIF_SYSCALL_WORK	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
 				 _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \
 				 _TIF_NOHZ | _TIF_SYSCALL_EMU)
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 214685760e1c3..f7975b079551e 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -30,6 +30,7 @@ int main(void)
   BLANK();
   DEFINE(TSK_TI_FLAGS,		offsetof(struct task_struct, thread_info.flags));
   DEFINE(TSK_TI_PREEMPT,	offsetof(struct task_struct, thread_info.preempt_count));
+  DEFINE(TSK_TI_PREEMPT_LAZY,	offsetof(struct task_struct, thread_info.preempt_lazy_count));
   DEFINE(TSK_TI_ADDR_LIMIT,	offsetof(struct task_struct, thread_info.addr_limit));
 #ifdef CONFIG_ARM64_SW_TTBR0_PAN
   DEFINE(TSK_TI_TTBR0,		offsetof(struct task_struct, thread_info.ttbr0));
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index cf3bd2976e574..b25f633650809 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -669,7 +669,7 @@ ENDPROC(el1_sync)
 
 	irq_handler
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	ldr	x24, [tsk, #TSK_TI_PREEMPT]	// get preempt count
 alternative_if ARM64_HAS_IRQ_PRIO_MASKING
 	/*
@@ -679,9 +679,18 @@ alternative_if ARM64_HAS_IRQ_PRIO_MASKING
 	mrs	x0, daif
 	orr	x24, x24, x0
 alternative_else_nop_endif
-	cbnz	x24, 1f				// preempt count != 0 || NMI return path
-	bl	arm64_preempt_schedule_irq	// irq en/disable is done inside
+
+	cbz	x24, 1f					// (need_resched + count) == 0
+	cbnz	w24, 2f					// count != 0
+
+	ldr	w24, [tsk, #TSK_TI_PREEMPT_LAZY]	// get preempt lazy count
+	cbnz	w24, 2f					// preempt lazy count != 0
+
+	ldr	x0, [tsk, #TSK_TI_FLAGS]		// get flags
+	tbz	x0, #TIF_NEED_RESCHED_LAZY, 2f		// needs rescheduling?
 1:
+	bl	arm64_preempt_schedule_irq		// irq en/disable is done inside
+2:
 #endif
 
 #ifdef CONFIG_ARM64_PSEUDO_NMI
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 37d3912cfe06f..ac326cac8b939 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -213,6 +213,16 @@ static void sve_free(struct task_struct *task)
 	__sve_free(task);
 }
 
+static void *sve_free_atomic(struct task_struct *task)
+{
+	void *sve_state = task->thread.sve_state;
+
+	WARN_ON(test_tsk_thread_flag(task, TIF_SVE));
+
+	task->thread.sve_state = NULL;
+	return sve_state;
+}
+
 /*
  * TIF_SVE controls whether a task can use SVE without trapping while
  * in userspace, and also the way a task's FPSIMD/SVE state is stored
@@ -1008,6 +1018,7 @@ void fpsimd_thread_switch(struct task_struct *next)
 void fpsimd_flush_thread(void)
 {
 	int vl, supported_vl;
+	void *mem = NULL;
 
 	if (!system_supports_fpsimd())
 		return;
@@ -1020,7 +1031,7 @@ void fpsimd_flush_thread(void)
 
 	if (system_supports_sve()) {
 		clear_thread_flag(TIF_SVE);
-		sve_free(current);
+		mem = sve_free_atomic(current);
 
 		/*
 		 * Reset the task vector length as required.
@@ -1054,6 +1065,7 @@ void fpsimd_flush_thread(void)
 	}
 
 	put_cpu_fpsimd_context();
+	kfree(mem);
 }
 
 /*
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index dd2cdc0d5be20..94dbce6b27195 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -910,7 +910,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
 		/* Check valid user FS if needed */
 		addr_limit_user_check();
 
-		if (thread_flags & _TIF_NEED_RESCHED) {
+		if (thread_flags & _TIF_NEED_RESCHED_MASK) {
 			/* Unmask Debug and SError for the next task */
 			local_daif_restore(DAIF_PROCCTX_NOIRQ);
 
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index dc9fe879c2793..02d41eae3da86 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -31,6 +31,7 @@
 #include <linux/of.h>
 #include <linux/irq_work.h>
 #include <linux/kexec.h>
+#include <linux/kvm_host.h>
 
 #include <asm/alternative.h>
 #include <asm/atomic.h>
@@ -39,6 +40,7 @@
 #include <asm/cputype.h>
 #include <asm/cpu_ops.h>
 #include <asm/daifflags.h>
+#include <asm/kvm_mmu.h>
 #include <asm/mmu_context.h>
 #include <asm/numa.h>
 #include <asm/pgtable.h>
@@ -408,6 +410,8 @@ static void __init hyp_mode_check(void)
 			   "CPU: CPUs started in inconsistent modes");
 	else
 		pr_info("CPU: All CPU(s) started at EL1\n");
+	if (IS_ENABLED(CONFIG_KVM_ARM_HOST))
+		kvm_compute_layout();
 }
 
 void __init smp_cpus_done(unsigned int max_cpus)
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 34739e80211bc..0bf934257744d 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -143,9 +143,12 @@ void show_stack(struct task_struct *tsk, unsigned long *sp)
 
 #ifdef CONFIG_PREEMPT
 #define S_PREEMPT " PREEMPT"
+#elif defined(CONFIG_PREEMPT_RT)
+#define S_PREEMPT " PREEMPT_RT"
 #else
 #define S_PREEMPT ""
 #endif
+
 #define S_SMP " SMP"
 
 static int __die(const char *str, int err, struct pt_regs *regs)
diff --git a/arch/arm64/kvm/va_layout.c b/arch/arm64/kvm/va_layout.c
index 2cf7d4b606c38..dab1fea4752aa 100644
--- a/arch/arm64/kvm/va_layout.c
+++ b/arch/arm64/kvm/va_layout.c
@@ -22,7 +22,7 @@ static u8 tag_lsb;
 static u64 tag_val;
 static u64 va_mask;
 
-static void compute_layout(void)
+__init void kvm_compute_layout(void)
 {
 	phys_addr_t idmap_addr = __pa_symbol(__hyp_idmap_text_start);
 	u64 hyp_va_msb;
@@ -110,9 +110,6 @@ void __init kvm_update_va_mask(struct alt_instr *alt,
 
 	BUG_ON(nr_inst != 5);
 
-	if (!has_vhe() && !va_mask)
-		compute_layout();
-
 	for (i = 0; i < nr_inst; i++) {
 		u32 rd, rn, insn, oinsn;
 
@@ -156,9 +153,6 @@ void kvm_patch_vector_branch(struct alt_instr *alt,
 		return;
 	}
 
-	if (!va_mask)
-		compute_layout();
-
 	/*
 	 * Compute HYP VA by using the same computation as kern_hyp_va()
 	 */
diff --git a/arch/c6x/kernel/entry.S b/arch/c6x/kernel/entry.S
index 4332a10aec6c7..fb154d19625bc 100644
--- a/arch/c6x/kernel/entry.S
+++ b/arch/c6x/kernel/entry.S
@@ -18,7 +18,7 @@
 #define DP	B14
 #define SP	B15
 
-#ifndef CONFIG_PREEMPT
+#ifndef CONFIG_PREEMPTION
 #define resume_kernel restore_all
 #endif
 
@@ -287,7 +287,7 @@
 	;; is a little bit different
 	;;
 ENTRY(ret_from_exception)
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	MASK_INT B2
 #endif
 
@@ -557,7 +557,7 @@ ENDPROC(_nmi_handler)
 	;;
 	;; Jump to schedule() then return to ret_from_isr
 	;;
-#ifdef	CONFIG_PREEMPT
+#ifdef	CONFIG_PREEMPTION
 resume_kernel:
 	GET_THREAD_INFO A12
 	LDW	.D1T1	*+A12(THREAD_INFO_PREEMPT_COUNT),A1
@@ -582,7 +582,7 @@ ENDPROC(_nmi_handler)
 	B	.S2	preempt_schedule_irq
 #endif
 	ADDKPC	.S2	preempt_schedule,B3,4
-#endif /* CONFIG_PREEMPT */
+#endif /* CONFIG_PREEMPTION */
 
 ENTRY(enable_exception)
 	DINT
diff --git a/arch/csky/kernel/entry.S b/arch/csky/kernel/entry.S
index a7a5b67df8989..0077063280000 100644
--- a/arch/csky/kernel/entry.S
+++ b/arch/csky/kernel/entry.S
@@ -277,7 +277,7 @@ ENTRY(csky_irq)
 	zero_fp
 	psrset	ee
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	mov	r9, sp			/* Get current stack  pointer */
 	bmaski	r10, THREAD_SHIFT
 	andn	r9, r10			/* Get thread_info */
@@ -294,7 +294,7 @@ ENTRY(csky_irq)
 	mov	a0, sp
 	jbsr	csky_do_IRQ
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	subi	r12, 1
 	stw	r12, (r9, TINFO_PREEMPT)
 	cmpnei	r12, 0
diff --git a/arch/h8300/kernel/entry.S b/arch/h8300/kernel/entry.S
index 4ade5f8299bae..c6e289b5f1f28 100644
--- a/arch/h8300/kernel/entry.S
+++ b/arch/h8300/kernel/entry.S
@@ -284,12 +284,12 @@ INTERRUPTS = 128
 	mov.l	er0,@(LER0:16,sp)
 	bra	resume_userspace
 
-#if !defined(CONFIG_PREEMPT)
+#if !defined(CONFIG_PREEMPTION)
 #define resume_kernel restore_all
 #endif
 
 ret_from_exception:
-#if defined(CONFIG_PREEMPT)
+#if defined(CONFIG_PREEMPTION)
 	orc	#0xc0,ccr
 #endif
 ret_from_interrupt:
@@ -319,7 +319,7 @@ INTERRUPTS = 128
 restore_all:
 	RESTORE_ALL			/* Does RTE */
 
-#if defined(CONFIG_PREEMPT)
+#if defined(CONFIG_PREEMPTION)
 resume_kernel:
 	mov.l	@(TI_PRE_COUNT:16,er4),er0
 	bne	restore_all:8
diff --git a/arch/hexagon/include/asm/spinlock_types.h b/arch/hexagon/include/asm/spinlock_types.h
index 19d233497ba52..de72fb23016dc 100644
--- a/arch/hexagon/include/asm/spinlock_types.h
+++ b/arch/hexagon/include/asm/spinlock_types.h
@@ -8,10 +8,6 @@
 #ifndef _ASM_SPINLOCK_TYPES_H
 #define _ASM_SPINLOCK_TYPES_H
 
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
 typedef struct {
 	volatile unsigned int lock;
 } arch_spinlock_t;
diff --git a/arch/hexagon/kernel/vm_entry.S b/arch/hexagon/kernel/vm_entry.S
index 12242c27e2df5..65a1ea0eed2fa 100644
--- a/arch/hexagon/kernel/vm_entry.S
+++ b/arch/hexagon/kernel/vm_entry.S
@@ -265,12 +265,12 @@
 	 * should be in the designated register (usually R19)
 	 *
 	 * If we were in kernel mode, we don't need to check scheduler
-	 * or signals if CONFIG_PREEMPT is not set.  If set, then it has
+	 * or signals if CONFIG_PREEMPTION is not set.  If set, then it has
 	 * to jump to a need_resched kind of block.
-	 * BTW, CONFIG_PREEMPT is not supported yet.
+	 * BTW, CONFIG_PREEMPTION is not supported yet.
 	 */
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	R0 = #VM_INT_DISABLE
 	trap1(#HVM_TRAP1_VMSETIE)
 #endif
diff --git a/arch/ia64/include/asm/spinlock_types.h b/arch/ia64/include/asm/spinlock_types.h
index 6e345fefcdcab..681408d6816fb 100644
--- a/arch/ia64/include/asm/spinlock_types.h
+++ b/arch/ia64/include/asm/spinlock_types.h
@@ -2,10 +2,6 @@
 #ifndef _ASM_IA64_SPINLOCK_TYPES_H
 #define _ASM_IA64_SPINLOCK_TYPES_H
 
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
 typedef struct {
 	volatile unsigned int lock;
 } arch_spinlock_t;
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index a9992be5718b8..2ac9263315000 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -670,12 +670,12 @@ GLOBAL_ENTRY(ia64_leave_syscall)
 	 *
 	 * p6 controls whether current_thread_info()->flags needs to be check for
 	 * extra work.  We always check for extra work when returning to user-level.
-	 * With CONFIG_PREEMPT, we also check for extra work when the preempt_count
+	 * With CONFIG_PREEMPTION, we also check for extra work when the preempt_count
 	 * is 0.  After extra work processing has been completed, execution
 	 * resumes at ia64_work_processed_syscall with p6 set to 1 if the extra-work-check
 	 * needs to be redone.
 	 */
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	RSM_PSR_I(p0, r2, r18)			// disable interrupts
 	cmp.eq pLvSys,p0=r0,r0			// pLvSys=1: leave from syscall
 (pKStk) adds r20=TI_PRE_COUNT+IA64_TASK_SIZE,r13
@@ -685,7 +685,7 @@ GLOBAL_ENTRY(ia64_leave_syscall)
 (pUStk)	mov r21=0			// r21 <- 0
 	;;
 	cmp.eq p6,p0=r21,r0		// p6 <- pUStk || (preempt_count == 0)
-#else /* !CONFIG_PREEMPT */
+#else /* !CONFIG_PREEMPTION */
 	RSM_PSR_I(pUStk, r2, r18)
 	cmp.eq pLvSys,p0=r0,r0		// pLvSys=1: leave from syscall
 (pUStk)	cmp.eq.unc p6,p0=r0,r0		// p6 <- pUStk
@@ -814,12 +814,12 @@ GLOBAL_ENTRY(ia64_leave_kernel)
 	 *
 	 * p6 controls whether current_thread_info()->flags needs to be check for
 	 * extra work.  We always check for extra work when returning to user-level.
-	 * With CONFIG_PREEMPT, we also check for extra work when the preempt_count
+	 * With CONFIG_PREEMPTION, we also check for extra work when the preempt_count
 	 * is 0.  After extra work processing has been completed, execution
 	 * resumes at .work_processed_syscall with p6 set to 1 if the extra-work-check
 	 * needs to be redone.
 	 */
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	RSM_PSR_I(p0, r17, r31)			// disable interrupts
 	cmp.eq p0,pLvSys=r0,r0			// pLvSys=0: leave from kernel
 (pKStk)	adds r20=TI_PRE_COUNT+IA64_TASK_SIZE,r13
@@ -1120,7 +1120,7 @@ GLOBAL_ENTRY(ia64_leave_kernel)
 
 	/*
 	 * On entry:
-	 *	r20 = &current->thread_info->pre_count (if CONFIG_PREEMPT)
+	 *	r20 = &current->thread_info->pre_count (if CONFIG_PREEMPTION)
 	 *	r31 = current->thread_info->flags
 	 * On exit:
 	 *	p6 = TRUE if work-pending-check needs to be redone
diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c
index b8356edbde659..a6d6a0556f089 100644
--- a/arch/ia64/kernel/kprobes.c
+++ b/arch/ia64/kernel/kprobes.c
@@ -841,7 +841,7 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
 		return 1;
 	}
 
-#if !defined(CONFIG_PREEMPT)
+#if !defined(CONFIG_PREEMPTION)
 	if (p->ainsn.inst_flag == INST_FLAG_BOOSTABLE && !p->post_handler) {
 		/* Boost up -- we can execute copied instructions directly */
 		ia64_psr(regs)->ri = p->ainsn.slot;
diff --git a/arch/m68k/coldfire/entry.S b/arch/m68k/coldfire/entry.S
index 52d312d5b4d4f..d43a02795a4a4 100644
--- a/arch/m68k/coldfire/entry.S
+++ b/arch/m68k/coldfire/entry.S
@@ -108,7 +108,7 @@ ENTRY(system_call)
 	btst	#5,%sp@(PT_OFF_SR)	/* check if returning to kernel */
 	jeq	Luser_return		/* if so, skip resched, signals */
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	movel	%sp,%d1			/* get thread_info pointer */
 	andl	#-THREAD_SIZE,%d1	/* at base of kernel stack */
 	movel	%d1,%a0
diff --git a/arch/microblaze/kernel/entry.S b/arch/microblaze/kernel/entry.S
index 4e1b567becd6a..253f2b702b4c0 100644
--- a/arch/microblaze/kernel/entry.S
+++ b/arch/microblaze/kernel/entry.S
@@ -728,7 +728,7 @@ irq_call:rtbd	r0, do_IRQ;
 	bri	6f;
 /* MS: Return to kernel state. */
 2:
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	lwi	r11, CURRENT_TASK, TS_THREAD_INFO;
 	/* MS: get preempt_count from thread info */
 	lwi	r5, r11, TI_PREEMPT_COUNT;
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index a0bd9bdb5f830..ce89ab6dd4e3e 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2586,7 +2586,7 @@ config MIPS_CRC_SUPPORT
 #
 config HIGHMEM
 	bool "High Memory Support"
-	depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !CPU_MIPS32_3_5_EVA
+	depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !CPU_MIPS32_3_5_EVA && !PREEMPT_RT
 
 config CPU_SUPPORTS_HIGHMEM
 	bool
diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h
index feb069cbf44e8..655f40ddb6d1e 100644
--- a/arch/mips/include/asm/asmmacro.h
+++ b/arch/mips/include/asm/asmmacro.h
@@ -63,7 +63,7 @@
 	.endm
 
 	.macro	local_irq_disable reg=t0
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	lw      \reg, TI_PRE_COUNT($28)
 	addi    \reg, \reg, 1
 	sw      \reg, TI_PRE_COUNT($28)
@@ -73,7 +73,7 @@
 	xori	\reg, \reg, 1
 	mtc0	\reg, CP0_STATUS
 	irq_disable_hazard
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	lw      \reg, TI_PRE_COUNT($28)
 	addi    \reg, \reg, -1
 	sw      \reg, TI_PRE_COUNT($28)
diff --git a/arch/mips/kernel/entry.S b/arch/mips/kernel/entry.S
index 5469d43b69668..4849a48afc0f8 100644
--- a/arch/mips/kernel/entry.S
+++ b/arch/mips/kernel/entry.S
@@ -19,7 +19,7 @@
 #include <asm/thread_info.h>
 #include <asm/war.h>
 
-#ifndef CONFIG_PREEMPT
+#ifndef CONFIG_PREEMPTION
 #define resume_kernel	restore_all
 #else
 #define __ret_from_irq	ret_from_exception
@@ -27,7 +27,7 @@
 
 	.text
 	.align	5
-#ifndef CONFIG_PREEMPT
+#ifndef CONFIG_PREEMPTION
 FEXPORT(ret_from_exception)
 	local_irq_disable			# preempt stop
 	b	__ret_from_irq
@@ -53,7 +53,7 @@ FEXPORT(__ret_from_irq)
 	bnez	t0, work_pending
 	j	restore_all
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 resume_kernel:
 	local_irq_disable
 	lw	t0, TI_PRE_COUNT($28)
diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig
index fbd68329737f4..abbb74e46f054 100644
--- a/arch/nds32/Kconfig
+++ b/arch/nds32/Kconfig
@@ -61,7 +61,7 @@ config GENERIC_HWEIGHT
 
 config GENERIC_LOCKBREAK
 	def_bool y
-	depends on PREEMPT
+	depends on PREEMPTION
 
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool y
diff --git a/arch/nds32/kernel/ex-exit.S b/arch/nds32/kernel/ex-exit.S
index 1df02a7933641..6a2966c2d8c8f 100644
--- a/arch/nds32/kernel/ex-exit.S
+++ b/arch/nds32/kernel/ex-exit.S
@@ -72,7 +72,7 @@
 	restore_user_regs_last
 	.endm
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	.macro	preempt_stop
 	.endm
 #else
@@ -158,7 +158,7 @@ ENTRY(ret_slow_syscall)
 /*
  * preemptive kernel
  */
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 resume_kernel:
 	gie_disable
 	lwi	$t0, [tsk+#TSK_TI_PREEMPT]
diff --git a/arch/nios2/kernel/entry.S b/arch/nios2/kernel/entry.S
index 1e515ccd698e3..3d8d1d0bcb64b 100644
--- a/arch/nios2/kernel/entry.S
+++ b/arch/nios2/kernel/entry.S
@@ -365,7 +365,7 @@ ENTRY(ret_from_interrupt)
 	ldw	r1, PT_ESTATUS(sp)	/* check if returning to kernel */
 	TSTBNZ	r1, r1, ESTATUS_EU, Luser_return
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	GET_THREAD_INFO	r1
 	ldw	r4, TI_PREEMPT_COUNT(r1)
 	bne	r4, r0, restore_all
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index b16237c95ea33..593e4014cef84 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -81,7 +81,7 @@ config STACK_GROWSUP
 config GENERIC_LOCKBREAK
 	bool
 	default y
-	depends on SMP && PREEMPT
+	depends on SMP && PREEMPTION
 
 config ARCH_HAS_ILOG2_U32
 	bool
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index b96d744969779..9a03e29c87330 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -940,14 +940,14 @@ ENTRY(intr_return)
 	rfi
 	nop
 
-#ifndef CONFIG_PREEMPT
+#ifndef CONFIG_PREEMPTION
 # define intr_do_preempt	intr_restore
-#endif /* !CONFIG_PREEMPT */
+#endif /* !CONFIG_PREEMPTION */
 
 	.import schedule,code
 intr_do_resched:
 	/* Only call schedule on return to userspace. If we're returning
-	 * to kernel space, we may schedule if CONFIG_PREEMPT, otherwise
+	 * to kernel space, we may schedule if CONFIG_PREEMPTION, otherwise
 	 * we jump back to intr_restore.
 	 */
 	LDREG	PT_IASQ0(%r16), %r20
@@ -979,7 +979,7 @@ ENTRY(intr_return)
 	 * and preempt_count is 0. otherwise, we continue on
 	 * our merry way back to the current running task.
 	 */
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	.import preempt_schedule_irq,code
 intr_do_preempt:
 	rsm	PSW_SM_I, %r0		/* disable interrupts */
@@ -999,7 +999,7 @@ ENTRY(intr_return)
 	nop
 
 	b,n	intr_restore		/* ssm PSW_SM_I done by intr_restore */
-#endif /* CONFIG_PREEMPT */
+#endif /* CONFIG_PREEMPTION */
 
 	/*
 	 * External interrupts.
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 3e56c9c2f16ee..2ee24d22d575a 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -106,7 +106,7 @@ config LOCKDEP_SUPPORT
 config GENERIC_LOCKBREAK
 	bool
 	default y
-	depends on SMP && PREEMPT
+	depends on SMP && PREEMPTION
 
 config GENERIC_HWEIGHT
 	bool
@@ -144,6 +144,7 @@ config PPC
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select ARCH_OPTIONAL_KERNEL_RWX		if ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_SUPPORTS_ATOMIC_RMW
+	select ARCH_SUPPORTS_RT
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF		if PPC64
 	select ARCH_WANT_IPC_PARSE_VERSION
@@ -221,6 +222,7 @@ config PPC
 	select HAVE_HARDLOCKUP_DETECTOR_PERF	if PERF_EVENTS && HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
+	select HAVE_PREEMPT_LAZY
 	select HAVE_RCU_TABLE_FREE		if SMP
 	select HAVE_RCU_TABLE_NO_INVALIDATE	if HAVE_RCU_TABLE_FREE
 	select HAVE_MMU_GATHER_PAGE_SIZE
@@ -398,7 +400,7 @@ menu "Kernel options"
 
 config HIGHMEM
 	bool "High memory support"
-	depends on PPC32
+	depends on PPC32 && !PREEMPT_RT
 
 source "kernel/Kconfig.hz"
 
diff --git a/arch/powerpc/include/asm/spinlock_types.h b/arch/powerpc/include/asm/spinlock_types.h
index 87adaf13b7e84..7305cb6a53e47 100644
--- a/arch/powerpc/include/asm/spinlock_types.h
+++ b/arch/powerpc/include/asm/spinlock_types.h
@@ -2,10 +2,6 @@
 #ifndef _ASM_POWERPC_SPINLOCK_TYPES_H
 #define _ASM_POWERPC_SPINLOCK_TYPES_H
 
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
 typedef struct {
 	volatile unsigned int slock;
 } arch_spinlock_t;
diff --git a/arch/powerpc/include/asm/stackprotector.h b/arch/powerpc/include/asm/stackprotector.h
index 1c8460e235838..b1653c160bab9 100644
--- a/arch/powerpc/include/asm/stackprotector.h
+++ b/arch/powerpc/include/asm/stackprotector.h
@@ -24,7 +24,11 @@ static __always_inline void boot_init_stack_canary(void)
 	unsigned long canary;
 
 	/* Try to get a semi random initial value. */
+#ifdef CONFIG_PREEMPT_RT
+	canary = (unsigned long)&canary;
+#else
 	canary = get_random_canary();
+#endif
 	canary ^= mftb();
 	canary ^= LINUX_VERSION_CODE;
 	canary &= CANARY_MASK;
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index 8e1d0195ac366..594fdb569e540 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -30,6 +30,8 @@
 struct thread_info {
 	int		preempt_count;		/* 0 => preemptable,
 						   <0 => BUG */
+	int             preempt_lazy_count;	/* 0 => preemptable,
+						   <0 => BUG */
 	unsigned long	local_flags;		/* private flags for thread */
 #ifdef CONFIG_LIVEPATCH
 	unsigned long *livepatch_sp;
@@ -80,11 +82,12 @@ void arch_setup_new_exec(void);
 #define TIF_SINGLESTEP		8	/* singlestepping active */
 #define TIF_NOHZ		9	/* in adaptive nohz mode */
 #define TIF_SECCOMP		10	/* secure computing */
-#define TIF_RESTOREALL		11	/* Restore all regs (implies NOERROR) */
-#define TIF_NOERROR		12	/* Force successful syscall return */
+
+#define TIF_NEED_RESCHED_LAZY	11	/* lazy rescheduling necessary */
+#define TIF_SYSCALL_TRACEPOINT	12	/* syscall tracepoint instrumentation */
+
 #define TIF_NOTIFY_RESUME	13	/* callback before returning to user */
 #define TIF_UPROBE		14	/* breakpointed or single-stepping */
-#define TIF_SYSCALL_TRACEPOINT	15	/* syscall tracepoint instrumentation */
 #define TIF_EMULATE_STACK_STORE	16	/* Is an instruction emulation
 						for stack store? */
 #define TIF_MEMDIE		17	/* is terminating due to OOM killer */
@@ -93,6 +96,9 @@ void arch_setup_new_exec(void);
 #endif
 #define TIF_POLLING_NRFLAG	19	/* true if poll_idle() is polling TIF_NEED_RESCHED */
 #define TIF_32BIT		20	/* 32 bit binary */
+#define TIF_RESTOREALL		21	/* Restore all regs (implies NOERROR) */
+#define TIF_NOERROR		22	/* Force successful syscall return */
+
 
 /* as above, but as bit values */
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
@@ -112,6 +118,7 @@ void arch_setup_new_exec(void);
 #define _TIF_SYSCALL_TRACEPOINT	(1<<TIF_SYSCALL_TRACEPOINT)
 #define _TIF_EMULATE_STACK_STORE	(1<<TIF_EMULATE_STACK_STORE)
 #define _TIF_NOHZ		(1<<TIF_NOHZ)
+#define _TIF_NEED_RESCHED_LAZY	(1<<TIF_NEED_RESCHED_LAZY)
 #define _TIF_FSCHECK		(1<<TIF_FSCHECK)
 #define _TIF_SYSCALL_EMU	(1<<TIF_SYSCALL_EMU)
 #define _TIF_SYSCALL_DOTRACE	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
@@ -121,8 +128,9 @@ void arch_setup_new_exec(void);
 #define _TIF_USER_WORK_MASK	(_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
 				 _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
 				 _TIF_RESTORE_TM | _TIF_PATCH_PENDING | \
-				 _TIF_FSCHECK)
+				 _TIF_FSCHECK | _TIF_NEED_RESCHED_LAZY)
 #define _TIF_PERSYSCALL_MASK	(_TIF_RESTOREALL|_TIF_NOERROR)
+#define _TIF_NEED_RESCHED_MASK	(_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)
 
 /* Bits in local_flags */
 /* Don't move TLF_NAPPING without adjusting the code in entry_32.S */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 5c0a1e17219b7..b28cd3acd6743 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -167,6 +167,7 @@ int main(void)
 	OFFSET(TI_FLAGS, thread_info, flags);
 	OFFSET(TI_LOCAL_FLAGS, thread_info, local_flags);
 	OFFSET(TI_PREEMPT, thread_info, preempt_count);
+	OFFSET(TI_PREEMPT_LAZY, thread_info, preempt_lazy_count);
 
 #ifdef CONFIG_PPC64
 	OFFSET(DCACHEL1BLOCKSIZE, ppc64_caches, l1d.block_size);
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index d60908ea37fb9..940de56e90d19 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -400,7 +400,9 @@ _GLOBAL(DoSyscall)
 	MTMSRD(r10)
 	lwz	r9,TI_FLAGS(r2)
 	li	r8,-MAX_ERRNO
-	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
+	lis	r0,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)@h
+	ori	r0,r0, (_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)@l
+	and.	r0,r9,r0
 	bne-	syscall_exit_work
 	cmplw	0,r3,r8
 	blt+	syscall_exit_cont
@@ -515,13 +517,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
 	b	syscall_dotrace_cont
 
 syscall_exit_work:
-	andi.	r0,r9,_TIF_RESTOREALL
+	andis.	r0,r9,_TIF_RESTOREALL@h
 	beq+	0f
 	REST_NVGPRS(r1)
 	b	2f
 0:	cmplw	0,r3,r8
 	blt+	1f
-	andi.	r0,r9,_TIF_NOERROR
+	andis.	r0,r9,_TIF_NOERROR@h
 	bne-	1f
 	lwz	r11,_CCR(r1)			/* Load CR */
 	neg	r3,r3
@@ -530,12 +532,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
 
 1:	stw	r6,RESULT(r1)	/* Save result */
 	stw	r3,GPR3(r1)	/* Update return value */
-2:	andi.	r0,r9,(_TIF_PERSYSCALL_MASK)
+2:	andi.	r0,r9,(_TIF_PERSYSCALL_MASK)@h
 	beq	4f
 
 	/* Clear per-syscall TIF flags if any are set.  */
 
-	li	r11,_TIF_PERSYSCALL_MASK
+	li	r11,_TIF_PERSYSCALL_MASK@h
 	addi	r12,r2,TI_FLAGS
 3:	lwarx	r8,0,r12
 	andc	r8,r8,r11
@@ -897,13 +899,20 @@ user_exc_return:		/* r10 contains MSR_KERNEL here */
 	bne-	0b
 1:
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	/* check current_thread_info->preempt_count */
 	lwz	r0,TI_PREEMPT(r2)
 	cmpwi	0,r0,0		/* if non-zero, just restore regs and return */
 	bne	restore_kuap
 	andi.	r8,r8,_TIF_NEED_RESCHED
+	bne+	1f
+	lwz	r0,TI_PREEMPT_LAZY(r2)
+	cmpwi	0,r0,0          /* if non-zero, just restore regs and return */
+	bne	restore_kuap
+	lwz	r0,TI_FLAGS(r2)
+	andi.	r0,r0,_TIF_NEED_RESCHED_LAZY
 	beq+	restore_kuap
+1:
 	lwz	r3,_MSR(r1)
 	andi.	r0,r3,MSR_EE	/* interrupts off? */
 	beq	restore_kuap	/* don't schedule if so */
@@ -921,7 +930,7 @@ user_exc_return:		/* r10 contains MSR_KERNEL here */
 	 */
 	bl	trace_hardirqs_on
 #endif
-#endif /* CONFIG_PREEMPT */
+#endif /* CONFIG_PREEMPTION */
 restore_kuap:
 	kuap_restore r1, r2, r9, r10, r0
 
@@ -1224,7 +1233,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_NEED_PAIRED_STWCX)
 #endif /* !(CONFIG_4xx || CONFIG_BOOKE) */
 
 do_work:			/* r10 contains MSR_KERNEL here */
-	andi.	r0,r9,_TIF_NEED_RESCHED
+	andi.	r0,r9,_TIF_NEED_RESCHED_MASK
 	beq	do_user_signal
 
 do_resched:			/* r10 contains MSR_KERNEL here */
@@ -1245,7 +1254,7 @@ do_resched:			/* r10 contains MSR_KERNEL here */
 	SYNC
 	MTMSRD(r10)		/* disable interrupts */
 	lwz	r9,TI_FLAGS(r2)
-	andi.	r0,r9,_TIF_NEED_RESCHED
+	andi.	r0,r9,_TIF_NEED_RESCHED_MASK
 	bne-	do_resched
 	andi.	r0,r9,_TIF_USER_WORK_MASK
 	beq	restore_user
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 3fd3ef352e3fd..dfd96e87d7b6c 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -240,7 +240,9 @@ system_call:			/* label this so stack traces look sane */
 
 	ld	r9,TI_FLAGS(r12)
 	li	r11,-MAX_ERRNO
-	andi.	r0,r9,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)
+	lis	r0,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)@h
+	ori	r0,r0,(_TIF_SYSCALL_DOTRACE|_TIF_SINGLESTEP|_TIF_USER_WORK_MASK|_TIF_PERSYSCALL_MASK)@l
+	and.	r0,r9,r0
 	bne-	.Lsyscall_exit_work
 
 	andi.	r0,r8,MSR_FP
@@ -363,25 +365,25 @@ END_FTR_SECTION_IFSET(CPU_FTR_HAS_PPR)
 	/* If TIF_RESTOREALL is set, don't scribble on either r3 or ccr.
 	 If TIF_NOERROR is set, just save r3 as it is. */
 
-	andi.	r0,r9,_TIF_RESTOREALL
+	andis.	r0,r9,_TIF_RESTOREALL@h
 	beq+	0f
 	REST_NVGPRS(r1)
 	b	2f
 0:	cmpld	r3,r11		/* r11 is -MAX_ERRNO */
 	blt+	1f
-	andi.	r0,r9,_TIF_NOERROR
+	andis.	r0,r9,_TIF_NOERROR@h
 	bne-	1f
 	ld	r5,_CCR(r1)
 	neg	r3,r3
 	oris	r5,r5,0x1000	/* Set SO bit in CR */
 	std	r5,_CCR(r1)
 1:	std	r3,GPR3(r1)
-2:	andi.	r0,r9,(_TIF_PERSYSCALL_MASK)
+2:	andis.	r0,r9,(_TIF_PERSYSCALL_MASK)@h
 	beq	4f
 
 	/* Clear per-syscall TIF flags if any are set.  */
 
-	li	r11,_TIF_PERSYSCALL_MASK
+	lis	r11,(_TIF_PERSYSCALL_MASK)@h
 	addi	r12,r12,TI_FLAGS
 3:	ldarx	r10,0,r12
 	andc	r10,r10,r11
@@ -786,7 +788,7 @@ _GLOBAL(ret_from_except_lite)
 	bl	restore_math
 	b	restore
 #endif
-1:	andi.	r0,r4,_TIF_NEED_RESCHED
+1:	andi.	r0,r4,_TIF_NEED_RESCHED_MASK
 	beq	2f
 	bl	restore_interrupts
 	SCHEDULE_USER
@@ -846,12 +848,20 @@ _GLOBAL(ret_from_except_lite)
 	bne-	0b
 1:
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	/* Check if we need to preempt */
-	andi.	r0,r4,_TIF_NEED_RESCHED
-	beq+	restore
-	/* Check that preempt_count() == 0 and interrupts are enabled */
 	lwz	r8,TI_PREEMPT(r9)
+	cmpwi	0,r8,0		/* if non-zero, just restore regs and return */
+	bne	restore
+	andi.	r0,r4,_TIF_NEED_RESCHED
+	bne+	check_count
+
+	andi.	r0,r4,_TIF_NEED_RESCHED_LAZY
+	beq+	restore
+	lwz	r8,TI_PREEMPT_LAZY(r9)
+
+	/* Check that preempt_count() == 0 and interrupts are enabled */
+check_count:
 	cmpwi	cr0,r8,0
 	bne	restore
 	ld	r0,SOFTE(r1)
@@ -877,7 +887,7 @@ _GLOBAL(ret_from_except_lite)
 	li	r10,MSR_RI
 	mtmsrd	r10,1		  /* Update machine state */
 #endif /* CONFIG_PPC_BOOK3E */
-#endif /* CONFIG_PREEMPT */
+#endif /* CONFIG_PREEMPTION */
 
 	.globl	fast_exc_return_irq
 fast_exc_return_irq:
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 5645bc9cbc09a..5e720cea41a9b 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -679,10 +679,12 @@ void *mcheckirq_ctx[NR_CPUS] __read_mostly;
 void *softirq_ctx[NR_CPUS] __read_mostly;
 void *hardirq_ctx[NR_CPUS] __read_mostly;
 
+#ifndef CONFIG_PREEMPT_RT
 void do_softirq_own_stack(void)
 {
 	call_do_softirq(softirq_ctx[smp_processor_id()]);
 }
+#endif
 
 irq_hw_number_t virq_to_hw(unsigned int virq)
 {
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 82df4b09e79f4..4af2ef8783619 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -37,6 +37,7 @@
  * We store the saved ksp_limit in the unused part
  * of the STACK_FRAME_OVERHEAD
  */
+#ifndef CONFIG_PREEMPT_RT
 _GLOBAL(call_do_softirq)
 	mflr	r0
 	stw	r0,4(r1)
@@ -52,6 +53,7 @@ _GLOBAL(call_do_softirq)
 	stw	r10,THREAD+KSP_LIMIT(r2)
 	mtlr	r0
 	blr
+#endif
 
 /*
  * void call_do_irq(struct pt_regs *regs, void *sp);
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 9bc0aa9aeb654..9bce8e23f33eb 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -27,6 +27,7 @@
 
 	.text
 
+#ifndef CONFIG_PREEMPT_RT
 _GLOBAL(call_do_softirq)
 	mflr	r0
 	std	r0,16(r1)
@@ -37,6 +38,7 @@ _GLOBAL(call_do_softirq)
 	ld	r0,16(r1)
 	mtlr	r0
 	blr
+#endif
 
 _GLOBAL(call_do_irq)
 	mflr	r0
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 82f43535e6867..dc17897f108d3 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -171,7 +171,6 @@ extern void panic_flush_kmsg_start(void)
 
 extern void panic_flush_kmsg_end(void)
 {
-	printk_safe_flush_on_panic();
 	kmsg_dump(KMSG_DUMP_PANIC);
 	bust_spinlocks(0);
 	debug_locks_off();
@@ -252,14 +251,19 @@ NOKPROBE_SYMBOL(oops_end);
 
 static int __die(const char *str, struct pt_regs *regs, long err)
 {
+	const char *pr = "";
+
 	printk("Oops: %s, sig: %ld [#%d]\n", str, err, ++die_counter);
 
+	if (IS_ENABLED(CONFIG_PREEMPTION))
+		pr = IS_ENABLED(CONFIG_PREEMPT_RT) ? " PREEMPT_RT" : " PREEMPT";
+
 	printk("%s PAGE_SIZE=%luK%s%s%s%s%s%s%s %s\n",
 	       IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN) ? "LE" : "BE",
 	       PAGE_SIZE / 1024,
 	       early_radix_enabled() ? " MMU=Radix" : "",
 	       early_mmu_has_feature(MMU_FTR_HPTE_TABLE) ? " MMU=Hash" : "",
-	       IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "",
+	       pr,
 	       IS_ENABLED(CONFIG_SMP) ? " SMP" : "",
 	       IS_ENABLED(CONFIG_SMP) ? (" NR_CPUS=" __stringify(NR_CPUS)) : "",
 	       debug_pagealloc_enabled() ? " DEBUG_PAGEALLOC" : "",
diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c
index af3c15a1d41eb..8ae46c5945d07 100644
--- a/arch/powerpc/kernel/watchdog.c
+++ b/arch/powerpc/kernel/watchdog.c
@@ -181,11 +181,6 @@ static void watchdog_smp_panic(int cpu, u64 tb)
 
 	wd_smp_unlock(&flags);
 
-	printk_safe_flush();
-	/*
-	 * printk_safe_flush() seems to require another print
-	 * before anything actually goes out to console.
-	 */
 	if (sysctl_hardlockup_all_cpu_backtrace)
 		trigger_allbutself_cpu_backtrace();
 
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 711fca9bc6f0c..dd3babcb3b16a 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -178,6 +178,7 @@ config KVM_E500MC
 config KVM_MPIC
 	bool "KVM in-kernel MPIC emulation"
 	depends on KVM && E500
+	depends on !PREEMPT_RT
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_IRQFD
 	select HAVE_KVM_IRQ_ROUTING
diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c
index 2735ec90414dc..359231cea8cd7 100644
--- a/arch/powerpc/platforms/ps3/device-init.c
+++ b/arch/powerpc/platforms/ps3/device-init.c
@@ -738,8 +738,8 @@ static int ps3_notification_read_write(struct ps3_notification_device *dev,
 	}
 	pr_debug("%s:%u: notification %s issued\n", __func__, __LINE__, op);
 
-	res = wait_event_interruptible(dev->done.wait,
-				       dev->done.done || kthread_should_stop());
+	res = swait_event_interruptible_exclusive(dev->done.wait,
+						  dev->done.done || kthread_should_stop());
 	if (kthread_should_stop())
 		res = -EINTR;
 	if (res) {
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 6ba081dd61c93..60d060ba9fea7 100644
--- a/arch/powerpc/platforms/pseries/iommu.c
+++ b/arch/powerpc/platforms/pseries/iommu.c
@@ -24,6 +24,7 @@
 #include <linux/of.h>
 #include <linux/iommu.h>
 #include <linux/rculist.h>
+#include <linux/locallock.h>
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/rtas.h>
@@ -178,6 +179,7 @@ static int tce_build_pSeriesLP(struct iommu_table *tbl, long tcenum,
 }
 
 static DEFINE_PER_CPU(__be64 *, tce_page);
+static DEFINE_LOCAL_IRQ_LOCK(tcp_page_lock);
 
 static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 				     long npages, unsigned long uaddr,
@@ -198,7 +200,8 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		                           direction, attrs);
 	}
 
-	local_irq_save(flags);	/* to protect tcep and the page behind it */
+	/* to protect tcep and the page behind it */
+	local_lock_irqsave(tcp_page_lock, flags);
 
 	tcep = __this_cpu_read(tce_page);
 
@@ -209,7 +212,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		tcep = (__be64 *)__get_free_page(GFP_ATOMIC);
 		/* If allocation fails, fall back to the loop implementation */
 		if (!tcep) {
-			local_irq_restore(flags);
+			local_unlock_irqrestore(tcp_page_lock, flags);
 			return tce_build_pSeriesLP(tbl, tcenum, npages, uaddr,
 					    direction, attrs);
 		}
@@ -243,7 +246,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		tcenum += limit;
 	} while (npages > 0 && !rc);
 
-	local_irq_restore(flags);
+	local_unlock_irqrestore(tcp_page_lock, flags);
 
 	if (unlikely(rc == H_NOT_ENOUGH_RESOURCES)) {
 		ret = (int)rc;
@@ -401,13 +404,14 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn,
 	u64 rc = 0;
 	long l, limit;
 
-	local_irq_disable();	/* to protect tcep and the page behind it */
+	/* to protect tcep and the page behind it */
+	local_lock_irq(tcp_page_lock);
 	tcep = __this_cpu_read(tce_page);
 
 	if (!tcep) {
 		tcep = (__be64 *)__get_free_page(GFP_ATOMIC);
 		if (!tcep) {
-			local_irq_enable();
+			local_unlock_irq(tcp_page_lock);
 			return -ENOMEM;
 		}
 		__this_cpu_write(tce_page, tcep);
@@ -453,7 +457,7 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn,
 
 	/* error cleanup: caller will clear whole range */
 
-	local_irq_enable();
+	local_unlock_irq(tcp_page_lock);
 	return rc;
 }
 
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 8ca4798311429..8f482313e5601 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -155,7 +155,7 @@
 	REG_L x2,  PT_SP(sp)
 	.endm
 
-#if !IS_ENABLED(CONFIG_PREEMPT)
+#if !IS_ENABLED(CONFIG_PREEMPTION)
 .set resume_kernel, restore_all
 #endif
 
@@ -269,7 +269,7 @@ ENTRY(handle_exception)
 	RESTORE_ALL
 	sret
 
-#if IS_ENABLED(CONFIG_PREEMPT)
+#if IS_ENABLED(CONFIG_PREEMPTION)
 resume_kernel:
 	REG_L s0, TASK_TI_PREEMPT_COUNT(tp)
 	bnez s0, restore_all
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 43a81d0ad5074..33d968175038e 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -30,7 +30,7 @@ config GENERIC_BUG_RELATIVE_POINTERS
 	def_bool y
 
 config GENERIC_LOCKBREAK
-	def_bool y if PREEMPT
+	def_bool y if PREEMPTTION
 
 config PGSTE
 	def_bool y if KVM
diff --git a/arch/s390/include/asm/preempt.h b/arch/s390/include/asm/preempt.h
index b5ea9e14c017a..6ede29907fbf7 100644
--- a/arch/s390/include/asm/preempt.h
+++ b/arch/s390/include/asm/preempt.h
@@ -130,11 +130,11 @@ static inline bool should_resched(int preempt_offset)
 
 #endif /* CONFIG_HAVE_MARCH_Z196_FEATURES */
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 extern asmlinkage void preempt_schedule(void);
 #define __preempt_schedule() preempt_schedule()
 extern asmlinkage void preempt_schedule_notrace(void);
 #define __preempt_schedule_notrace() preempt_schedule_notrace()
-#endif /* CONFIG_PREEMPT */
+#endif /* CONFIG_PREEMPTION */
 
 #endif /* __ASM_PREEMPT_H */
diff --git a/arch/s390/include/asm/spinlock_types.h b/arch/s390/include/asm/spinlock_types.h
index cfed272e4fd59..8e28e8176ec88 100644
--- a/arch/s390/include/asm/spinlock_types.h
+++ b/arch/s390/include/asm/spinlock_types.h
@@ -2,10 +2,6 @@
 #ifndef __ASM_SPINLOCK_TYPES_H
 #define __ASM_SPINLOCK_TYPES_H
 
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
 typedef struct {
 	int lock;
 } __attribute__ ((aligned (4))) arch_spinlock_t;
diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c
index 34bdc60c0b11d..8e38447be4653 100644
--- a/arch/s390/kernel/dumpstack.c
+++ b/arch/s390/kernel/dumpstack.c
@@ -194,6 +194,8 @@ void die(struct pt_regs *regs, const char *str)
 	       regs->int_code >> 17, ++die_counter);
 #ifdef CONFIG_PREEMPT
 	pr_cont("PREEMPT ");
+#elif defined(CONFIG_PREEMPT_RT)
+	pr_cont("PREEMPT_RT ");
 #endif
 	pr_cont("SMP ");
 	if (debug_pagealloc_enabled())
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 270d1d145761b..9205add8481d5 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -790,7 +790,7 @@ ENTRY(io_int_handler)
 .Lio_work:
 	tm	__PT_PSW+1(%r11),0x01	# returning to user ?
 	jo	.Lio_work_user		# yes -> do resched & signal
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	# check for preemptive scheduling
 	icm	%r0,15,__LC_PREEMPT_COUNT
 	jnz	.Lio_restore		# preemption is disabled
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index f356ee674d89b..9ece111b02548 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -108,7 +108,7 @@ config GENERIC_CALIBRATE_DELAY
 
 config GENERIC_LOCKBREAK
 	def_bool y
-	depends on SMP && PREEMPT
+	depends on SMP && PREEMPTION
 
 config ARCH_SUSPEND_POSSIBLE
 	def_bool n
diff --git a/arch/sh/include/asm/spinlock_types.h b/arch/sh/include/asm/spinlock_types.h
index e82369f286a20..22ca9a98bbb8b 100644
--- a/arch/sh/include/asm/spinlock_types.h
+++ b/arch/sh/include/asm/spinlock_types.h
@@ -2,10 +2,6 @@
 #ifndef __ASM_SH_SPINLOCK_TYPES_H
 #define __ASM_SH_SPINLOCK_TYPES_H
 
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
 typedef struct {
 	volatile unsigned int lock;
 } arch_spinlock_t;
diff --git a/arch/sh/kernel/cpu/sh5/entry.S b/arch/sh/kernel/cpu/sh5/entry.S
index de68ffdfffbf5..81c8b64b977ff 100644
--- a/arch/sh/kernel/cpu/sh5/entry.S
+++ b/arch/sh/kernel/cpu/sh5/entry.S
@@ -86,7 +86,7 @@
 	andi	r6, ~0xf0, r6;		\
 	putcon	r6, SR;
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 #  define preempt_stop()	CLI()
 #else
 #  define preempt_stop()
@@ -884,7 +884,7 @@ LRESVEC_block_end:			/* Marker. Unused. */
 
 	/* Check softirqs */
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	pta   ret_from_syscall, tr0
 	blink   tr0, ZERO
 
diff --git a/arch/sh/kernel/entry-common.S b/arch/sh/kernel/entry-common.S
index d31f66e82ce51..956a7a03b0c83 100644
--- a/arch/sh/kernel/entry-common.S
+++ b/arch/sh/kernel/entry-common.S
@@ -41,7 +41,7 @@
  */
 #include <asm/dwarf.h>
 
-#if defined(CONFIG_PREEMPT)
+#if defined(CONFIG_PREEMPTION)
 #  define preempt_stop()	cli ; TRACE_IRQS_OFF
 #else
 #  define preempt_stop()
@@ -84,7 +84,7 @@ ENTRY(ret_from_irq)
 	get_current_thread_info r8, r0
 	bt	resume_kernel	! Yes, it's from kernel, go back soon
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	bra	resume_userspace
 	 nop
 ENTRY(resume_kernel)
diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c
index 5717c7cbdd97a..c4e46252377ed 100644
--- a/arch/sh/kernel/irq.c
+++ b/arch/sh/kernel/irq.c
@@ -148,6 +148,7 @@ void irq_ctx_exit(int cpu)
 	hardirq_ctx[cpu] = NULL;
 }
 
+#ifndef CONFIG_PREEMPT_RT
 void do_softirq_own_stack(void)
 {
 	struct thread_info *curctx;
@@ -175,6 +176,7 @@ void do_softirq_own_stack(void)
 		  "r5", "r6", "r7", "r8", "r9", "r15", "t", "pr"
 	);
 }
+#endif
 #else
 static inline void handle_one_irq(unsigned int irq)
 {
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index eb24cb1afc11f..e8c3ea01c12f6 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -277,7 +277,7 @@ config US3_MC
 config GENERIC_LOCKBREAK
 	bool
 	default y
-	depends on SPARC64 && SMP && PREEMPT
+	depends on SPARC64 && SMP && PREEMPTION
 
 config NUMA
 	bool "NUMA support"
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index 3ec9f1402aad3..eb21682abfcb1 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -854,6 +854,7 @@ void __irq_entry handler_irq(int pil, struct pt_regs *regs)
 	set_irq_regs(old_regs);
 }
 
+#ifndef CONFIG_PREEMPT_RT
 void do_softirq_own_stack(void)
 {
 	void *orig_sp, *sp = softirq_stack[smp_processor_id()];
@@ -868,6 +869,7 @@ void do_softirq_own_stack(void)
 	__asm__ __volatile__("mov %0, %%sp"
 			     : : "r" (orig_sp));
 }
+#endif
 
 #ifdef CONFIG_HOTPLUG_CPU
 void fixup_irqs(void)
diff --git a/arch/sparc/kernel/rtrap_64.S b/arch/sparc/kernel/rtrap_64.S
index 29aa34f11720c..c5fd4b450d9b6 100644
--- a/arch/sparc/kernel/rtrap_64.S
+++ b/arch/sparc/kernel/rtrap_64.S
@@ -310,7 +310,7 @@ kern_rtt:	rdpr			%canrestore, %g1
 		retry
 
 to_kernel:
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 		ldsw			[%g6 + TI_PRE_COUNT], %l5
 		brnz			%l5, kern_fpucheck
 		 ldx			[%g6 + TI_FLAGS], %l5
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8ef85139553f5..4b77b3273051e 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -90,6 +90,7 @@ config X86
 	select ARCH_SUPPORTS_ACPI
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_NUMA_BALANCING	if X86_64
+	select ARCH_SUPPORTS_RT
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
@@ -132,8 +133,8 @@ config X86
 	select HAVE_ALIGNED_STRUCT_PAGE		if SLUB
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_HUGE_VMAP		if X86_64 || X86_PAE
-	select HAVE_ARCH_JUMP_LABEL
-	select HAVE_ARCH_JUMP_LABEL_RELATIVE
+	select HAVE_ARCH_JUMP_LABEL		if !PREEMPT_RT
+	select HAVE_ARCH_JUMP_LABEL_RELATIVE	if !PREEMPT_RT
 	select HAVE_ARCH_KASAN			if X86_64
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_MMAP_RND_BITS		if MMU
@@ -199,6 +200,7 @@ config X86
 	select HAVE_PCI
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
+	select HAVE_PREEMPT_LAZY
 	select HAVE_RCU_TABLE_FREE		if PARAVIRT
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RELIABLE_STACKTRACE		if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index 3e707e81afdb4..0e80da8190be1 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -387,14 +387,14 @@ static int ecb_encrypt(struct skcipher_request *req)
 
 	err = skcipher_walk_virt(&walk, req, true);
 
-	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);
+		kernel_fpu_end();
 		nbytes &= AES_BLOCK_SIZE - 1;
 		err = skcipher_walk_done(&walk, nbytes);
 	}
-	kernel_fpu_end();
 
 	return err;
 }
@@ -409,14 +409,14 @@ static int ecb_decrypt(struct skcipher_request *req)
 
 	err = skcipher_walk_virt(&walk, req, true);
 
-	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 = skcipher_walk_done(&walk, nbytes);
 	}
-	kernel_fpu_end();
 
 	return err;
 }
@@ -431,14 +431,14 @@ static int cbc_encrypt(struct skcipher_request *req)
 
 	err = skcipher_walk_virt(&walk, req, true);
 
-	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 = skcipher_walk_done(&walk, nbytes);
 	}
-	kernel_fpu_end();
 
 	return err;
 }
@@ -453,14 +453,14 @@ static int cbc_decrypt(struct skcipher_request *req)
 
 	err = skcipher_walk_virt(&walk, req, true);
 
-	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 = skcipher_walk_done(&walk, nbytes);
 	}
-	kernel_fpu_end();
 
 	return err;
 }
@@ -510,18 +510,20 @@ static int ctr_crypt(struct skcipher_request *req)
 
 	err = skcipher_walk_virt(&walk, req, true);
 
-	kernel_fpu_begin();
 	while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) {
+		kernel_fpu_begin();
 		aesni_ctr_enc_tfm(ctx, walk.dst.virt.addr, walk.src.virt.addr,
 			              nbytes & AES_BLOCK_MASK, walk.iv);
+		kernel_fpu_end();
 		nbytes &= AES_BLOCK_SIZE - 1;
 		err = skcipher_walk_done(&walk, nbytes);
 	}
 	if (walk.nbytes) {
+		kernel_fpu_begin();
 		ctr_crypt_final(ctx, &walk);
+		kernel_fpu_end();
 		err = skcipher_walk_done(&walk, 0);
 	}
-	kernel_fpu_end();
 
 	return err;
 }
diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c
index 384ccb00f9e15..2f8df8ef8644e 100644
--- a/arch/x86/crypto/cast5_avx_glue.c
+++ b/arch/x86/crypto/cast5_avx_glue.c
@@ -46,7 +46,7 @@ static inline void cast5_fpu_end(bool fpu_enabled)
 
 static int ecb_crypt(struct skcipher_request *req, bool enc)
 {
-	bool fpu_enabled = false;
+	bool fpu_enabled;
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct cast5_ctx *ctx = crypto_skcipher_ctx(tfm);
 	struct skcipher_walk walk;
@@ -61,7 +61,7 @@ static int ecb_crypt(struct skcipher_request *req, bool enc)
 		u8 *wsrc = walk.src.virt.addr;
 		u8 *wdst = walk.dst.virt.addr;
 
-		fpu_enabled = cast5_fpu_begin(fpu_enabled, &walk, nbytes);
+		fpu_enabled = cast5_fpu_begin(false, &walk, nbytes);
 
 		/* Process multi-block batch */
 		if (nbytes >= bsize * CAST5_PARALLEL_BLOCKS) {
@@ -90,10 +90,9 @@ static int ecb_crypt(struct skcipher_request *req, bool enc)
 		} while (nbytes >= bsize);
 
 done:
+		cast5_fpu_end(fpu_enabled);
 		err = skcipher_walk_done(&walk, nbytes);
 	}
-
-	cast5_fpu_end(fpu_enabled);
 	return err;
 }
 
@@ -197,7 +196,7 @@ static int cbc_decrypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct cast5_ctx *ctx = crypto_skcipher_ctx(tfm);
-	bool fpu_enabled = false;
+	bool fpu_enabled;
 	struct skcipher_walk walk;
 	unsigned int nbytes;
 	int err;
@@ -205,12 +204,11 @@ static int cbc_decrypt(struct skcipher_request *req)
 	err = skcipher_walk_virt(&walk, req, false);
 
 	while ((nbytes = walk.nbytes)) {
-		fpu_enabled = cast5_fpu_begin(fpu_enabled, &walk, nbytes);
+		fpu_enabled = cast5_fpu_begin(false, &walk, nbytes);
 		nbytes = __cbc_decrypt(ctx, &walk);
+		cast5_fpu_end(fpu_enabled);
 		err = skcipher_walk_done(&walk, nbytes);
 	}
-
-	cast5_fpu_end(fpu_enabled);
 	return err;
 }
 
@@ -277,7 +275,7 @@ static int ctr_crypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct cast5_ctx *ctx = crypto_skcipher_ctx(tfm);
-	bool fpu_enabled = false;
+	bool fpu_enabled;
 	struct skcipher_walk walk;
 	unsigned int nbytes;
 	int err;
@@ -285,13 +283,12 @@ static int ctr_crypt(struct skcipher_request *req)
 	err = skcipher_walk_virt(&walk, req, false);
 
 	while ((nbytes = walk.nbytes) >= CAST5_BLOCK_SIZE) {
-		fpu_enabled = cast5_fpu_begin(fpu_enabled, &walk, nbytes);
+		fpu_enabled = cast5_fpu_begin(false, &walk, nbytes);
 		nbytes = __ctr_crypt(&walk, ctx);
+		cast5_fpu_end(fpu_enabled);
 		err = skcipher_walk_done(&walk, nbytes);
 	}
 
-	cast5_fpu_end(fpu_enabled);
-
 	if (walk.nbytes) {
 		ctr_crypt_final(&walk, ctx);
 		err = skcipher_walk_done(&walk, 0);
diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c
index 388f95a4ec240..f8e9ee81c39dd 100644
--- a/arch/x86/crypto/chacha_glue.c
+++ b/arch/x86/crypto/chacha_glue.c
@@ -127,7 +127,6 @@ static int chacha_simd_stream_xor(struct skcipher_walk *walk,
 				  const struct chacha_ctx *ctx, const u8 *iv)
 {
 	u32 *state, state_buf[16 + 2] __aligned(8);
-	int next_yield = 4096; /* bytes until next FPU yield */
 	int err = 0;
 
 	BUILD_BUG_ON(CHACHA_STATE_ALIGN != 16);
@@ -140,20 +139,14 @@ static int chacha_simd_stream_xor(struct skcipher_walk *walk,
 
 		if (nbytes < walk->total) {
 			nbytes = round_down(nbytes, walk->stride);
-			next_yield -= nbytes;
 		}
 
 		chacha_dosimd(state, walk->dst.virt.addr, walk->src.virt.addr,
 			      nbytes, ctx->nrounds);
 
-		if (next_yield <= 0) {
-			/* temporarily allow preemption */
-			kernel_fpu_end();
-			kernel_fpu_begin();
-			next_yield = 4096;
-		}
-
+		kernel_fpu_end();
 		err = skcipher_walk_done(walk, walk->nbytes - nbytes);
+		kernel_fpu_begin();
 	}
 
 	return err;
diff --git a/arch/x86/crypto/glue_helper.c b/arch/x86/crypto/glue_helper.c
index d15b99397480b..36c28b295b8e3 100644
--- a/arch/x86/crypto/glue_helper.c
+++ b/arch/x86/crypto/glue_helper.c
@@ -24,7 +24,7 @@ int glue_ecb_req_128bit(const struct common_glue_ctx *gctx,
 	void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req));
 	const unsigned int bsize = 128 / 8;
 	struct skcipher_walk walk;
-	bool fpu_enabled = false;
+	bool fpu_enabled;
 	unsigned int nbytes;
 	int err;
 
@@ -37,7 +37,7 @@ int glue_ecb_req_128bit(const struct common_glue_ctx *gctx,
 		unsigned int i;
 
 		fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
-					     &walk, fpu_enabled, nbytes);
+					     &walk, false, nbytes);
 		for (i = 0; i < gctx->num_funcs; i++) {
 			func_bytes = bsize * gctx->funcs[i].num_blocks;
 
@@ -55,10 +55,9 @@ int glue_ecb_req_128bit(const struct common_glue_ctx *gctx,
 			if (nbytes < bsize)
 				break;
 		}
+		glue_fpu_end(fpu_enabled);
 		err = skcipher_walk_done(&walk, nbytes);
 	}
-
-	glue_fpu_end(fpu_enabled);
 	return err;
 }
 EXPORT_SYMBOL_GPL(glue_ecb_req_128bit);
@@ -101,7 +100,7 @@ int glue_cbc_decrypt_req_128bit(const struct common_glue_ctx *gctx,
 	void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req));
 	const unsigned int bsize = 128 / 8;
 	struct skcipher_walk walk;
-	bool fpu_enabled = false;
+	bool fpu_enabled;
 	unsigned int nbytes;
 	int err;
 
@@ -115,7 +114,7 @@ int glue_cbc_decrypt_req_128bit(const struct common_glue_ctx *gctx,
 		u128 last_iv;
 
 		fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
-					     &walk, fpu_enabled, nbytes);
+					     &walk, false, nbytes);
 		/* Start of the last block. */
 		src += nbytes / bsize - 1;
 		dst += nbytes / bsize - 1;
@@ -147,10 +146,10 @@ int glue_cbc_decrypt_req_128bit(const struct common_glue_ctx *gctx,
 done:
 		u128_xor(dst, dst, (u128 *)walk.iv);
 		*(u128 *)walk.iv = last_iv;
+		glue_fpu_end(fpu_enabled);
 		err = skcipher_walk_done(&walk, nbytes);
 	}
 
-	glue_fpu_end(fpu_enabled);
 	return err;
 }
 EXPORT_SYMBOL_GPL(glue_cbc_decrypt_req_128bit);
@@ -161,7 +160,7 @@ int glue_ctr_req_128bit(const struct common_glue_ctx *gctx,
 	void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req));
 	const unsigned int bsize = 128 / 8;
 	struct skcipher_walk walk;
-	bool fpu_enabled = false;
+	bool fpu_enabled;
 	unsigned int nbytes;
 	int err;
 
@@ -175,7 +174,7 @@ int glue_ctr_req_128bit(const struct common_glue_ctx *gctx,
 		le128 ctrblk;
 
 		fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
-					     &walk, fpu_enabled, nbytes);
+					     &walk, false, nbytes);
 
 		be128_to_le128(&ctrblk, (be128 *)walk.iv);
 
@@ -199,11 +198,10 @@ int glue_ctr_req_128bit(const struct common_glue_ctx *gctx,
 		}
 
 		le128_to_be128((be128 *)walk.iv, &ctrblk);
+		glue_fpu_end(fpu_enabled);
 		err = skcipher_walk_done(&walk, nbytes);
 	}
 
-	glue_fpu_end(fpu_enabled);
-
 	if (nbytes) {
 		le128 ctrblk;
 		u128 tmp;
@@ -301,8 +299,14 @@ int glue_xts_req_128bit(const struct common_glue_ctx *gctx,
 	tweak_fn(tweak_ctx, walk.iv, walk.iv);
 
 	while (nbytes) {
+		fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
+					     &walk, fpu_enabled,
+					     nbytes < bsize ? bsize : nbytes);
 		nbytes = __glue_xts_req_128bit(gctx, crypt_ctx, &walk);
 
+		glue_fpu_end(fpu_enabled);
+		fpu_enabled = false;
+
 		err = skcipher_walk_done(&walk, nbytes);
 		nbytes = walk.nbytes;
 	}
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 3f8e22615812b..26934d55c14a0 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -130,7 +130,7 @@ static long syscall_trace_enter(struct pt_regs *regs)
 
 #define EXIT_TO_USERMODE_LOOP_FLAGS				\
 	(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE |	\
-	 _TIF_NEED_RESCHED | _TIF_USER_RETURN_NOTIFY | _TIF_PATCH_PENDING)
+	 _TIF_NEED_RESCHED_MASK | _TIF_USER_RETURN_NOTIFY | _TIF_PATCH_PENDING)
 
 static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
 {
@@ -145,9 +145,16 @@ static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags)
 		/* We have work to do. */
 		local_irq_enable();
 
-		if (cached_flags & _TIF_NEED_RESCHED)
+		if (cached_flags & _TIF_NEED_RESCHED_MASK)
 			schedule();
 
+#ifdef ARCH_RT_DELAYS_SIGNAL_SEND
+		if (unlikely(current->forced_info.si_signo)) {
+			struct task_struct *t = current;
+			force_sig_info(&t->forced_info);
+			t->forced_info.si_signo = 0;
+		}
+#endif
 		if (cached_flags & _TIF_UPROBE)
 			uprobe_notify_resume(regs);
 
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index f07baf0388bce..69049e32b4fa1 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -1106,8 +1106,26 @@ ENTRY(entry_INT80_32)
 restore_all_kernel:
 #ifdef CONFIG_PREEMPTION
 	DISABLE_INTERRUPTS(CLBR_ANY)
+	# preempt count == 0 + NEED_RS set?
 	cmpl	$0, PER_CPU_VAR(__preempt_count)
+#ifndef CONFIG_PREEMPT_LAZY
 	jnz	.Lno_preempt
+#else
+	jz	test_int_off
+
+	# atleast preempt count == 0 ?
+	cmpl	$_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count)
+	jne	.Lno_preempt
+
+	movl	PER_CPU_VAR(current_task), %ebp
+	cmpl	$0,TASK_TI_preempt_lazy_count(%ebp)	# non-zero preempt_lazy_count ?
+	jnz	.Lno_preempt
+
+	testl	$_TIF_NEED_RESCHED_LAZY, TASK_TI_flags(%ebp)
+	jz	.Lno_preempt
+
+test_int_off:
+#endif
 	testl	$X86_EFLAGS_IF, PT_EFLAGS(%esp)	# interrupts off (exception path) ?
 	jz	.Lno_preempt
 	call	preempt_schedule_irq
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index b7c3ea4cb19d4..ce564dc48647f 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -670,7 +670,23 @@ GLOBAL(swapgs_restore_regs_and_return_to_usermode)
 	btl	$9, EFLAGS(%rsp)		/* were interrupts off? */
 	jnc	1f
 	cmpl	$0, PER_CPU_VAR(__preempt_count)
+#ifndef CONFIG_PREEMPT_LAZY
 	jnz	1f
+#else
+	jz	do_preempt_schedule_irq
+
+	# atleast preempt count == 0 ?
+	cmpl	$_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count)
+	jnz	1f
+
+	movq	PER_CPU_VAR(current_task), %rcx
+	cmpl	$0, TASK_TI_preempt_lazy_count(%rcx)
+	jnz	1f
+
+	btl	$TIF_NEED_RESCHED_LAZY,TASK_TI_flags(%rcx)
+	jnc	1f
+do_preempt_schedule_irq:
+#endif
 	call	preempt_schedule_irq
 1:
 #endif
@@ -1074,6 +1090,7 @@ EXPORT_SYMBOL(native_load_gs_index)
 	jmp	2b
 	.previous
 
+#ifndef CONFIG_PREEMPT_RT
 /* Call softirq on interrupt stack. Interrupts are off. */
 ENTRY(do_softirq_own_stack)
 	pushq	%rbp
@@ -1084,6 +1101,7 @@ ENTRY(do_softirq_own_stack)
 	leaveq
 	ret
 ENDPROC(do_softirq_own_stack)
+#endif
 
 #ifdef CONFIG_XEN_PV
 idtentry hypervisor_callback xen_do_hypervisor_callback has_error_code=0
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index b774c52e5411f..1786e4d9f70e8 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -23,6 +23,7 @@ extern void kernel_fpu_begin(void);
 extern void kernel_fpu_end(void);
 extern bool irq_fpu_usable(void);
 extern void fpregs_mark_activate(void);
+extern void kernel_fpu_resched(void);
 
 /*
  * Use fpregs_lock() while editing CPU's FPU registers or fpu->state.
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 3d4cb83a88284..1f28e9f3dc8e2 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -89,17 +89,48 @@ static __always_inline void __preempt_count_sub(int val)
  * a decrement which hits zero means we have no preempt_count and should
  * reschedule.
  */
-static __always_inline bool __preempt_count_dec_and_test(void)
+static __always_inline bool ____preempt_count_dec_and_test(void)
 {
 	return GEN_UNARY_RMWcc("decl", __preempt_count, e, __percpu_arg([var]));
 }
 
+static __always_inline bool __preempt_count_dec_and_test(void)
+{
+	if (____preempt_count_dec_and_test())
+		return true;
+#ifdef CONFIG_PREEMPT_LAZY
+	if (preempt_count())
+		return false;
+	if (current_thread_info()->preempt_lazy_count)
+		return false;
+	return test_thread_flag(TIF_NEED_RESCHED_LAZY);
+#else
+	return false;
+#endif
+}
+
 /*
  * Returns true when we need to resched and can (barring IRQ state).
  */
 static __always_inline bool should_resched(int preempt_offset)
 {
+#ifdef CONFIG_PREEMPT_LAZY
+	u32 tmp;
+	tmp = raw_cpu_read_4(__preempt_count);
+	if (tmp == preempt_offset)
+		return true;
+
+	/* preempt count == 0 ? */
+	tmp &= ~PREEMPT_NEED_RESCHED;
+	if (tmp != preempt_offset)
+		return false;
+	/* XXX PREEMPT_LOCK_OFFSET */
+	if (current_thread_info()->preempt_lazy_count)
+		return false;
+	return test_thread_flag(TIF_NEED_RESCHED_LAZY);
+#else
 	return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset);
+#endif
 }
 
 #ifdef CONFIG_PREEMPTION
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index 33d3c88a7225f..65b9a5d4132b7 100644
--- a/arch/x86/include/asm/signal.h
+++ b/arch/x86/include/asm/signal.h
@@ -28,6 +28,19 @@ typedef struct {
 #define SA_IA32_ABI	0x02000000u
 #define SA_X32_ABI	0x01000000u
 
+/*
+ * Because some traps use the IST stack, we must keep preemption
+ * disabled while calling do_trap(), but do_trap() may call
+ * force_sig_info() which will grab the signal spin_locks for the
+ * task, which in PREEMPT_RT 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)
+#define ARCH_RT_DELAYS_SIGNAL_SEND
+#endif
+
 #ifndef CONFIG_COMPAT
 typedef sigset_t compat_sigset_t;
 #endif
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 91e29b6a86a5e..1ef821537da8f 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -60,7 +60,7 @@
  */
 static __always_inline void boot_init_stack_canary(void)
 {
-	u64 canary;
+	u64 uninitialized_var(canary);
 	u64 tsc;
 
 #ifdef CONFIG_X86_64
@@ -71,8 +71,14 @@ static __always_inline void boot_init_stack_canary(void)
 	 * of randomness. The TSC only matters for very early init,
 	 * there it already has some randomness on most systems. Later
 	 * on during the bootup the random pool has true entropy too.
+	 * For preempt-rt we need to weaken the randomness a bit, as
+	 * we can't call into the random generator from atomic context
+	 * due to locking constraints. We just leave canary
+	 * uninitialized and use the TSC based randomness on top of it.
 	 */
+#ifndef CONFIG_PREEMPT_RT
 	get_random_bytes(&canary, sizeof(canary));
+#endif
 	tsc = rdtsc();
 	canary += tsc + (tsc << 32UL);
 	canary &= CANARY_MASK;
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index f9453536f9bbc..f346f24140be9 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -56,17 +56,24 @@ struct task_struct;
 struct thread_info {
 	unsigned long		flags;		/* low level flags */
 	u32			status;		/* thread synchronous flags */
+	int			preempt_lazy_count;	/* 0 => lazy preemptable
+							  <0 => BUG */
 };
 
 #define INIT_THREAD_INFO(tsk)			\
 {						\
 	.flags		= 0,			\
+	.preempt_lazy_count = 0,		\
 }
 
 #else /* !__ASSEMBLY__ */
 
 #include <asm/asm-offsets.h>
 
+#define GET_THREAD_INFO(reg) \
+	_ASM_MOV PER_CPU_VAR(cpu_current_top_of_stack),reg ; \
+	_ASM_SUB $(THREAD_SIZE),reg ;
+
 #endif
 
 /*
@@ -92,6 +99,7 @@ struct thread_info {
 #define TIF_NOCPUID		15	/* CPUID is not accessible in userland */
 #define TIF_NOTSC		16	/* TSC is not accessible in userland */
 #define TIF_IA32		17	/* IA32 compatibility process */
+#define TIF_NEED_RESCHED_LAZY	18	/* lazy rescheduling necessary */
 #define TIF_NOHZ		19	/* in adaptive nohz mode */
 #define TIF_MEMDIE		20	/* is terminating due to OOM killer */
 #define TIF_POLLING_NRFLAG	21	/* idle is polling for TIF_NEED_RESCHED */
@@ -122,6 +130,7 @@ struct thread_info {
 #define _TIF_NOCPUID		(1 << TIF_NOCPUID)
 #define _TIF_NOTSC		(1 << TIF_NOTSC)
 #define _TIF_IA32		(1 << TIF_IA32)
+#define _TIF_NEED_RESCHED_LAZY	(1 << TIF_NEED_RESCHED_LAZY)
 #define _TIF_NOHZ		(1 << TIF_NOHZ)
 #define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
 #define _TIF_IO_BITMAP		(1 << TIF_IO_BITMAP)
@@ -159,6 +168,8 @@ struct thread_info {
 #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY)
 #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW)
 
+#define _TIF_NEED_RESCHED_MASK	(_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)
+
 #define STACK_WARN		(THREAD_SIZE/8)
 
 /*
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index d6af97fd170a9..913c88617848b 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1725,19 +1725,20 @@ static bool io_apic_level_ack_pending(struct mp_chip_data *data)
 	return false;
 }
 
-static inline bool ioapic_irqd_mask(struct irq_data *data)
+static inline bool ioapic_prepare_move(struct irq_data *data)
 {
-	/* If we are moving the irq we need to mask it */
+	/* If we are moving the IRQ we need to mask it */
 	if (unlikely(irqd_is_setaffinity_pending(data))) {
-		mask_ioapic_irq(data);
+		if (!irqd_irq_masked(data))
+			mask_ioapic_irq(data);
 		return true;
 	}
 	return false;
 }
 
-static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked)
+static inline void ioapic_finish_move(struct irq_data *data, bool moveit)
 {
-	if (unlikely(masked)) {
+	if (unlikely(moveit)) {
 		/* Only migrate the irq if the ack has been received.
 		 *
 		 * On rare occasions the broadcast level triggered ack gets
@@ -1766,15 +1767,17 @@ static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked)
 		 */
 		if (!io_apic_level_ack_pending(data->chip_data))
 			irq_move_masked_irq(data);
-		unmask_ioapic_irq(data);
+		/* If the IRQ is masked in the core, leave it: */
+		if (!irqd_irq_masked(data))
+			unmask_ioapic_irq(data);
 	}
 }
 #else
-static inline bool ioapic_irqd_mask(struct irq_data *data)
+static inline bool ioapic_prepare_move(struct irq_data *data)
 {
 	return false;
 }
-static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked)
+static inline void ioapic_finish_move(struct irq_data *data, bool moveit)
 {
 }
 #endif
@@ -1783,11 +1786,11 @@ static void ioapic_ack_level(struct irq_data *irq_data)
 {
 	struct irq_cfg *cfg = irqd_cfg(irq_data);
 	unsigned long v;
-	bool masked;
+	bool moveit;
 	int i;
 
 	irq_complete_move(cfg);
-	masked = ioapic_irqd_mask(irq_data);
+	moveit = ioapic_prepare_move(irq_data);
 
 	/*
 	 * It appears there is an erratum which affects at least version 0x11
@@ -1842,7 +1845,7 @@ static void ioapic_ack_level(struct irq_data *irq_data)
 		eoi_ioapic_pin(cfg->vector, irq_data->chip_data);
 	}
 
-	ioapic_irqd_unmask(irq_data, masked);
+	ioapic_finish_move(irq_data, moveit);
 }
 
 static void ioapic_ir_ack_level(struct irq_data *irq_data)
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 5c7ee3df4d0b0..24bcc28f68d4b 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -38,6 +38,10 @@ static void __used common(void)
 #endif
 
 	BLANK();
+#ifdef CONFIG_PREEMPT_LAZY
+	OFFSET(TASK_TI_flags, task_struct, thread_info.flags);
+	OFFSET(TASK_TI_preempt_lazy_count, task_struct, thread_info.preempt_lazy_count);
+#endif
 	OFFSET(TASK_addr_limit, task_struct, thread.addr_limit);
 
 	BLANK();
@@ -92,6 +96,7 @@ static void __used common(void)
 
 	BLANK();
 	DEFINE(PTREGS_SIZE, sizeof(struct pt_regs));
+	DEFINE(_PREEMPT_ENABLED, PREEMPT_ENABLED);
 
 	/* TLB state for the entry code */
 	OFFSET(TLB_STATE_user_pcid_flush_mask, tlb_state, user_pcid_flush_mask);
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index c656d92cd708f..de56d671bc7fd 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -77,12 +77,13 @@ EXPORT_SYMBOL_GPL(hv_remove_vmbus_irq);
 __visible void __irq_entry hv_stimer0_vector_handler(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
+	u64 ip = regs ? instruction_pointer(regs) : 0;
 
 	entering_irq();
 	inc_irq_stat(hyperv_stimer0_count);
 	if (hv_stimer0_handler)
 		hv_stimer0_handler();
-	add_interrupt_randomness(HYPERV_STIMER0_VECTOR, 0);
+	add_interrupt_randomness(HYPERV_STIMER0_VECTOR, 0, ip);
 	ack_APIC_irq();
 
 	exiting_irq();
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 12c70840980e4..6909468cc7a04 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -113,6 +113,18 @@ void kernel_fpu_end(void)
 }
 EXPORT_SYMBOL_GPL(kernel_fpu_end);
 
+void kernel_fpu_resched(void)
+{
+	WARN_ON_FPU(!this_cpu_read(in_kernel_fpu));
+
+	if (should_resched(PREEMPT_OFFSET)) {
+		kernel_fpu_end();
+		cond_resched();
+		kernel_fpu_begin();
+	}
+}
+EXPORT_SYMBOL_GPL(kernel_fpu_resched);
+
 /*
  * Save the FPU state (mark it for reload if necessary):
  *
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index a759ca97cd01c..a74a7606806c1 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -131,6 +131,7 @@ int irq_init_percpu_irqstack(unsigned int cpu)
 	return 0;
 }
 
+#ifndef CONFIG_PREEMPT_RT
 void do_softirq_own_stack(void)
 {
 	struct irq_stack *irqstk;
@@ -147,6 +148,7 @@ void do_softirq_own_stack(void)
 
 	call_on_stack(__do_softirq, isp);
 }
+#endif
 
 void handle_irq(struct irq_desc *desc, struct pt_regs *regs)
 {
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index b8ceec4974fe3..39510443d996e 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -38,6 +38,7 @@
 #include <linux/io.h>
 #include <linux/kdebug.h>
 #include <linux/syscalls.h>
+#include <linux/highmem.h>
 
 #include <asm/pgtable.h>
 #include <asm/ldt.h>
@@ -196,6 +197,35 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
 }
 EXPORT_SYMBOL_GPL(start_thread);
 
+#ifdef CONFIG_PREEMPT_RT
+static void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p)
+{
+	int i;
+
+	/*
+	 * Clear @prev's kmap_atomic mappings
+	 */
+	for (i = 0; i < prev_p->kmap_idx; i++) {
+		int idx = i + KM_TYPE_NR * smp_processor_id();
+		pte_t *ptep = kmap_pte - idx;
+
+		kpte_clear_flush(ptep, __fix_to_virt(FIX_KMAP_BEGIN + idx));
+	}
+	/*
+	 * Restore @next_p's kmap_atomic mappings
+	 */
+	for (i = 0; i < next_p->kmap_idx; i++) {
+		int idx = i + KM_TYPE_NR * smp_processor_id();
+
+		if (!pte_none(next_p->kmap_pte[i]))
+			set_pte(kmap_pte - idx, next_p->kmap_pte[i]);
+	}
+}
+#else
+static inline void
+switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) { }
+#endif
+
 
 /*
  *	switch_to(x,y) should switch tasks from x to y.
@@ -266,6 +296,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	switch_to_extra(prev_p, next_p);
 
+	switch_kmaps(prev_p, next_p);
+
 	/*
 	 * Leave lazy mode, flushing any hypercalls made here.
 	 * This must be done before restoring TLS segments so
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8d82ec0482fc2..4511110d43e11 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -7207,6 +7207,14 @@ int kvm_arch_init(void *opaque)
 		goto out;
 	}
 
+#ifdef CONFIG_PREEMPT_RT
+	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
+		pr_err("RT requires X86_FEATURE_CONSTANT_TSC\n");
+		r = -EOPNOTSUPP;
+		goto out;
+	}
+#endif
+
 	r = -ENOMEM;
 	x86_fpu_cache = kmem_cache_create("x86_fpu", sizeof(struct fpu),
 					  __alignof__(struct fpu), SLAB_ACCOUNT,
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index 0a1898b8552e2..8606f17582073 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -33,10 +33,11 @@ EXPORT_SYMBOL(kunmap);
  */
 void *kmap_atomic_prot(struct page *page, pgprot_t prot)
 {
+	pte_t pte = mk_pte(page, prot);
 	unsigned long vaddr;
 	int idx, type;
 
-	preempt_disable();
+	preempt_disable_nort();
 	pagefault_disable();
 
 	if (!PageHighMem(page))
@@ -46,7 +47,10 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot)
 	idx = type + KM_TYPE_NR*smp_processor_id();
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
 	BUG_ON(!pte_none(*(kmap_pte-idx)));
-	set_pte(kmap_pte-idx, mk_pte(page, prot));
+#ifdef CONFIG_PREEMPT_RT
+	current->kmap_pte[type] = pte;
+#endif
+	set_pte(kmap_pte-idx, pte);
 	arch_flush_lazy_mmu_mode();
 
 	return (void *)vaddr;
@@ -89,6 +93,9 @@ void __kunmap_atomic(void *kvaddr)
 		 * is a bad idea also, in case the page changes cacheability
 		 * attributes or becomes a protected page in a hypervisor.
 		 */
+#ifdef CONFIG_PREEMPT_RT
+		current->kmap_pte[type] = __pte(0);
+#endif
 		kpte_clear_flush(kmap_pte-idx, vaddr);
 		kmap_atomic_idx_pop();
 		arch_flush_lazy_mmu_mode();
@@ -101,7 +108,7 @@ void __kunmap_atomic(void *kvaddr)
 #endif
 
 	pagefault_enable();
-	preempt_enable();
+	preempt_enable_nort();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
 
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index 6748b4c2baff3..54e2f28fe1897 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -46,6 +46,7 @@ EXPORT_SYMBOL_GPL(iomap_free);
 
 void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot)
 {
+	pte_t pte = pfn_pte(pfn, prot);
 	unsigned long vaddr;
 	int idx, type;
 
@@ -55,7 +56,12 @@ void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot)
 	type = kmap_atomic_idx_push();
 	idx = type + KM_TYPE_NR * smp_processor_id();
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-	set_pte(kmap_pte - idx, pfn_pte(pfn, prot));
+	WARN_ON(!pte_none(*(kmap_pte - idx)));
+
+#ifdef CONFIG_PREEMPT_RT
+	current->kmap_pte[type] = pte;
+#endif
+	set_pte(kmap_pte - idx, pte);
 	arch_flush_lazy_mmu_mode();
 
 	return (void *)vaddr;
@@ -106,6 +112,9 @@ iounmap_atomic(void __iomem *kvaddr)
 		 * is a bad idea also, in case the page changes cacheability
 		 * attributes or becomes a protected page in a hypervisor.
 		 */
+#ifdef CONFIG_PREEMPT_RT
+		current->kmap_pte[type] = __pte(0);
+#endif
 		kpte_clear_flush(kmap_pte-idx, vaddr);
 		kmap_atomic_idx_pop();
 	}
diff --git a/arch/xtensa/include/asm/spinlock_types.h b/arch/xtensa/include/asm/spinlock_types.h
index 64c9389254f13..dc846323b1cd7 100644
--- a/arch/xtensa/include/asm/spinlock_types.h
+++ b/arch/xtensa/include/asm/spinlock_types.h
@@ -2,10 +2,6 @@
 #ifndef __ASM_SPINLOCK_TYPES_H
 #define __ASM_SPINLOCK_TYPES_H
 
-#if !defined(__LINUX_SPINLOCK_TYPES_H) && !defined(__ASM_SPINLOCK_H)
-# error "please don't include this file directly"
-#endif
-
 #include <asm-generic/qspinlock_types.h>
 #include <asm-generic/qrwlock_types.h>
 
diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S
index 9e3676879168a..a6434813df6c8 100644
--- a/arch/xtensa/kernel/entry.S
+++ b/arch/xtensa/kernel/entry.S
@@ -520,7 +520,7 @@ ENTRY(kernel_exception)
 	call4	schedule	# void schedule (void)
 	j	1b
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 6:
 	_bbci.l	a4, TIF_NEED_RESCHED, 4f
 
diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c
index 4a6c495ce9b6d..2e7cf56412a05 100644
--- a/arch/xtensa/kernel/traps.c
+++ b/arch/xtensa/kernel/traps.c
@@ -524,12 +524,15 @@ DEFINE_SPINLOCK(die_lock);
 void die(const char * str, struct pt_regs * regs, long err)
 {
 	static int die_counter;
+	const char *pr = "";
+
+	if (IS_ENABLED(CONFIG_PREEMPTION))
+		pr = IS_ENABLED(CONFIG_PREEMPT_RT) ? " PREEMPT_RT" : " PREEMPT";
 
 	console_verbose();
 	spin_lock_irq(&die_lock);
 
-	pr_info("%s: sig: %ld [#%d]%s\n", str, err, ++die_counter,
-		IS_ENABLED(CONFIG_PREEMPT) ? " PREEMPT" : "");
+	pr_info("%s: sig: %ld [#%d]%s\n", str, err, ++die_counter, pr);
 	show_regs(regs);
 	if (!user_mode(regs))
 		show_stack(NULL, (unsigned long*)regs->areg[1]);
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index 5ed59ac6ae58b..b1da5f1592eb5 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -9,6 +9,7 @@
 #include <linux/blkdev.h>
 #include <linux/slab.h>
 #include <linux/sched/task.h>
+#include <linux/delay.h>
 
 #include "blk.h"
 
@@ -115,7 +116,7 @@ static void ioc_release_fn(struct work_struct *work)
 			spin_unlock(&q->queue_lock);
 		} else {
 			spin_unlock_irqrestore(&ioc->lock, flags);
-			cpu_relax();
+			cpu_chill();
 			spin_lock_irqsave_nested(&ioc->lock, flags, 1);
 		}
 	}
diff --git a/block/blk-mq.c b/block/blk-mq.c
index ec791156e9ccd..3811881ff624e 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -611,9 +611,17 @@ static void __blk_mq_complete_request(struct request *rq)
 		return;
 	}
 
-	cpu = get_cpu();
+	cpu = get_cpu_light();
+	/*
+	 * Avoid SMP function calls for completions because they acquire
+	 * sleeping spinlocks on RT.
+	 */
+#ifdef CONFIG_PREEMPT_RT
+	shared = true;
+#else
 	if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags))
 		shared = cpus_share_cache(cpu, ctx->cpu);
+#endif
 
 	if (cpu != ctx->cpu && !shared && cpu_online(ctx->cpu)) {
 		rq->csd.func = __blk_mq_complete_request_remote;
@@ -623,7 +631,7 @@ static void __blk_mq_complete_request(struct request *rq)
 	} else {
 		q->mq_ops->complete(rq);
 	}
-	put_cpu();
+	put_cpu_light();
 }
 
 static void hctx_unlock(struct blk_mq_hw_ctx *hctx, int srcu_idx)
@@ -1466,14 +1474,14 @@ static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
 		return;
 
 	if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) {
-		int cpu = get_cpu();
+		int cpu = get_cpu_light();
 		if (cpumask_test_cpu(cpu, hctx->cpumask)) {
 			__blk_mq_run_hw_queue(hctx);
-			put_cpu();
+			put_cpu_light();
 			return;
 		}
 
-		put_cpu();
+		put_cpu_light();
 	}
 
 	kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work,
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index 457d9ba3eb204..4debe1124b990 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -42,17 +42,13 @@ static __latent_entropy void blk_done_softirq(struct softirq_action *h)
 static void trigger_softirq(void *data)
 {
 	struct request *rq = data;
-	unsigned long flags;
 	struct list_head *list;
 
-	local_irq_save(flags);
 	list = this_cpu_ptr(&blk_cpu_done);
 	list_add_tail(&rq->ipi_list, list);
 
 	if (list->next == &rq->ipi_list)
 		raise_softirq_irqoff(BLOCK_SOFTIRQ);
-
-	local_irq_restore(flags);
 }
 
 /*
@@ -91,6 +87,7 @@ static int blk_softirq_cpu_dead(unsigned int cpu)
 			 this_cpu_ptr(&blk_cpu_done));
 	raise_softirq_irqoff(BLOCK_SOFTIRQ);
 	local_irq_enable();
+	preempt_check_resched_rt();
 
 	return 0;
 }
@@ -142,6 +139,7 @@ void __blk_complete_request(struct request *req)
 		goto do_local;
 
 	local_irq_restore(flags);
+	preempt_check_resched_rt();
 }
 
 static __init int blk_softirq_init(void)
diff --git a/crypto/cryptd.c b/crypto/cryptd.c
index 927760b316a4d..fb1e305aa3984 100644
--- a/crypto/cryptd.c
+++ b/crypto/cryptd.c
@@ -36,6 +36,7 @@ static struct workqueue_struct *cryptd_wq;
 struct cryptd_cpu_queue {
 	struct crypto_queue queue;
 	struct work_struct work;
+	spinlock_t qlock;
 };
 
 struct cryptd_queue {
@@ -105,6 +106,7 @@ static int cryptd_init_queue(struct cryptd_queue *queue,
 		cpu_queue = per_cpu_ptr(queue->cpu_queue, cpu);
 		crypto_init_queue(&cpu_queue->queue, max_cpu_qlen);
 		INIT_WORK(&cpu_queue->work, cryptd_queue_worker);
+		spin_lock_init(&cpu_queue->qlock);
 	}
 	pr_info("cryptd: max_cpu_qlen set to %d\n", max_cpu_qlen);
 	return 0;
@@ -129,8 +131,10 @@ static int cryptd_enqueue_request(struct cryptd_queue *queue,
 	struct cryptd_cpu_queue *cpu_queue;
 	refcount_t *refcnt;
 
-	cpu = get_cpu();
-	cpu_queue = this_cpu_ptr(queue->cpu_queue);
+	cpu_queue = raw_cpu_ptr(queue->cpu_queue);
+	spin_lock_bh(&cpu_queue->qlock);
+	cpu = smp_processor_id();
+
 	err = crypto_enqueue_request(&cpu_queue->queue, request);
 
 	refcnt = crypto_tfm_ctx(request->tfm);
@@ -146,7 +150,7 @@ static int cryptd_enqueue_request(struct cryptd_queue *queue,
 	refcount_inc(refcnt);
 
 out_put_cpu:
-	put_cpu();
+	spin_unlock_bh(&cpu_queue->qlock);
 
 	return err;
 }
@@ -162,16 +166,11 @@ static void cryptd_queue_worker(struct work_struct *work)
 	cpu_queue = container_of(work, struct cryptd_cpu_queue, work);
 	/*
 	 * Only handle one request at a time to avoid hogging crypto workqueue.
-	 * preempt_disable/enable is used to prevent being preempted by
-	 * cryptd_enqueue_request(). local_bh_disable/enable is used to prevent
-	 * cryptd_enqueue_request() being accessed from software interrupts.
 	 */
-	local_bh_disable();
-	preempt_disable();
+	spin_lock_bh(&cpu_queue->qlock);
 	backlog = crypto_get_backlog(&cpu_queue->queue);
 	req = crypto_dequeue_request(&cpu_queue->queue);
-	preempt_enable();
-	local_bh_enable();
+	spin_unlock_bh(&cpu_queue->qlock);
 
 	if (!req)
 		return;
diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c
index 1a8564a79d8dc..9dc3cc8beb2a6 100644
--- a/drivers/block/zram/zcomp.c
+++ b/drivers/block/zram/zcomp.c
@@ -113,12 +113,20 @@ ssize_t zcomp_available_show(const char *comp, char *buf)
 
 struct zcomp_strm *zcomp_stream_get(struct zcomp *comp)
 {
-	return *get_cpu_ptr(comp->stream);
+	struct zcomp_strm *zstrm;
+
+	zstrm = *get_local_ptr(comp->stream);
+	spin_lock(&zstrm->zcomp_lock);
+	return zstrm;
 }
 
 void zcomp_stream_put(struct zcomp *comp)
 {
-	put_cpu_ptr(comp->stream);
+	struct zcomp_strm *zstrm;
+
+	zstrm = *this_cpu_ptr(comp->stream);
+	spin_unlock(&zstrm->zcomp_lock);
+	put_local_ptr(zstrm);
 }
 
 int zcomp_compress(struct zcomp_strm *zstrm,
@@ -168,6 +176,7 @@ int zcomp_cpu_up_prepare(unsigned int cpu, struct hlist_node *node)
 		pr_err("Can't allocate a compression stream\n");
 		return -ENOMEM;
 	}
+	spin_lock_init(&zstrm->zcomp_lock);
 	*per_cpu_ptr(comp->stream, cpu) = zstrm;
 	return 0;
 }
diff --git a/drivers/block/zram/zcomp.h b/drivers/block/zram/zcomp.h
index 1806475b919df..b2c1db8a75ecb 100644
--- a/drivers/block/zram/zcomp.h
+++ b/drivers/block/zram/zcomp.h
@@ -10,6 +10,7 @@ struct zcomp_strm {
 	/* compression/decompression buffer */
 	void *buffer;
 	struct crypto_comp *tfm;
+	spinlock_t zcomp_lock;
 };
 
 /* dynamic per-device compression frontend */
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 4285e75e52c34..1699e84c9fce3 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -55,6 +55,40 @@ static void zram_free_page(struct zram *zram, size_t index);
 static int zram_bvec_read(struct zram *zram, struct bio_vec *bvec,
 				u32 index, int offset, struct bio *bio);
 
+#ifdef CONFIG_PREEMPT_RT
+static void zram_meta_init_table_locks(struct zram *zram, size_t num_pages)
+{
+	size_t index;
+
+	for (index = 0; index < num_pages; index++)
+		spin_lock_init(&zram->table[index].lock);
+}
+
+static int zram_slot_trylock(struct zram *zram, u32 index)
+{
+	int ret;
+
+	ret = spin_trylock(&zram->table[index].lock);
+	if (ret)
+		__set_bit(ZRAM_LOCK, &zram->table[index].flags);
+	return ret;
+}
+
+static void zram_slot_lock(struct zram *zram, u32 index)
+{
+	spin_lock(&zram->table[index].lock);
+	__set_bit(ZRAM_LOCK, &zram->table[index].flags);
+}
+
+static void zram_slot_unlock(struct zram *zram, u32 index)
+{
+	__clear_bit(ZRAM_LOCK, &zram->table[index].flags);
+	spin_unlock(&zram->table[index].lock);
+}
+
+#else
+
+static void zram_meta_init_table_locks(struct zram *zram, size_t num_pages) { }
 
 static int zram_slot_trylock(struct zram *zram, u32 index)
 {
@@ -70,6 +104,7 @@ static void zram_slot_unlock(struct zram *zram, u32 index)
 {
 	bit_spin_unlock(ZRAM_LOCK, &zram->table[index].flags);
 }
+#endif
 
 static inline bool init_done(struct zram *zram)
 {
@@ -1155,6 +1190,7 @@ static bool zram_meta_alloc(struct zram *zram, u64 disksize)
 
 	if (!huge_class_size)
 		huge_class_size = zs_huge_class_size(zram->mem_pool);
+	zram_meta_init_table_locks(zram, num_pages);
 	return true;
 }
 
@@ -1217,6 +1253,7 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
 	unsigned long handle;
 	unsigned int size;
 	void *src, *dst;
+	struct zcomp_strm *zstrm;
 
 	zram_slot_lock(zram, index);
 	if (zram_test_flag(zram, index, ZRAM_WB)) {
@@ -1247,6 +1284,7 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
 
 	size = zram_get_obj_size(zram, index);
 
+	zstrm = zcomp_stream_get(zram->comp);
 	src = zs_map_object(zram->mem_pool, handle, ZS_MM_RO);
 	if (size == PAGE_SIZE) {
 		dst = kmap_atomic(page);
@@ -1254,14 +1292,13 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
 		kunmap_atomic(dst);
 		ret = 0;
 	} else {
-		struct zcomp_strm *zstrm = zcomp_stream_get(zram->comp);
 
 		dst = kmap_atomic(page);
 		ret = zcomp_decompress(zstrm, src, size, dst);
 		kunmap_atomic(dst);
-		zcomp_stream_put(zram->comp);
 	}
 	zs_unmap_object(zram->mem_pool, handle);
+	zcomp_stream_put(zram->comp);
 	zram_slot_unlock(zram, index);
 
 	/* Should NEVER happen. Return bio error if it does. */
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index f2fd46daa7604..7e4dd447e1ddd 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -63,6 +63,7 @@ struct zram_table_entry {
 		unsigned long element;
 	};
 	unsigned long flags;
+	spinlock_t lock;
 #ifdef CONFIG_ZRAM_MEMORY_TRACKING
 	ktime_t ac_time;
 #endif
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 01b8868b9bed2..d5ac183bf39c9 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1305,28 +1305,27 @@ static __u32 get_reg(struct fast_pool *f, struct pt_regs *regs)
 	return *ptr;
 }
 
-void add_interrupt_randomness(int irq, int irq_flags)
+void add_interrupt_randomness(int irq, int irq_flags, __u64 ip)
 {
 	struct entropy_store	*r;
 	struct fast_pool	*fast_pool = this_cpu_ptr(&irq_randomness);
-	struct pt_regs		*regs = get_irq_regs();
 	unsigned long		now = jiffies;
 	cycles_t		cycles = random_get_entropy();
 	__u32			c_high, j_high;
-	__u64			ip;
 	unsigned long		seed;
 	int			credit = 0;
 
 	if (cycles == 0)
-		cycles = get_reg(fast_pool, regs);
+		cycles = get_reg(fast_pool, NULL);
 	c_high = (sizeof(cycles) > 4) ? cycles >> 32 : 0;
 	j_high = (sizeof(now) > 4) ? now >> 32 : 0;
 	fast_pool->pool[0] ^= cycles ^ j_high ^ irq;
 	fast_pool->pool[1] ^= now ^ c_high;
-	ip = regs ? instruction_pointer(regs) : _RET_IP_;
+	if (!ip)
+		ip = _RET_IP_;
 	fast_pool->pool[2] ^= ip;
 	fast_pool->pool[3] ^= (sizeof(ip) > 4) ? ip >> 32 :
-		get_reg(fast_pool, regs);
+		get_reg(fast_pool, NULL);
 
 	fast_mix(fast_pool);
 	add_interrupt_bench(cycles);
diff --git a/drivers/char/tpm/tpm-dev-common.c b/drivers/char/tpm/tpm-dev-common.c
index 2ec47a69a2a6c..40d0a780882cf 100644
--- a/drivers/char/tpm/tpm-dev-common.c
+++ b/drivers/char/tpm/tpm-dev-common.c
@@ -20,7 +20,6 @@
 #include "tpm-dev.h"
 
 static struct workqueue_struct *tpm_dev_wq;
-static DEFINE_MUTEX(tpm_dev_wq_lock);
 
 static ssize_t tpm_dev_transmit(struct tpm_chip *chip, struct tpm_space *space,
 				u8 *buf, size_t bufsiz)
diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c
index e7df342a317d6..f89057fdc0536 100644
--- a/drivers/char/tpm/tpm_tis.c
+++ b/drivers/char/tpm/tpm_tis.c
@@ -49,6 +49,31 @@ static inline struct tpm_tis_tcg_phy *to_tpm_tis_tcg_phy(struct tpm_tis_data *da
 	return container_of(data, struct tpm_tis_tcg_phy, priv);
 }
 
+#ifdef CONFIG_PREEMPT_RT
+/*
+ * Flushes previous write operations to chip so that a subsequent
+ * ioread*()s won't stall a cpu.
+ */
+static inline void tpm_tis_flush(void __iomem *iobase)
+{
+	ioread8(iobase + TPM_ACCESS(0));
+}
+#else
+#define tpm_tis_flush(iobase) do { } while (0)
+#endif
+
+static inline void tpm_tis_iowrite8(u8 b, void __iomem *iobase, u32 addr)
+{
+	iowrite8(b, iobase + addr);
+	tpm_tis_flush(iobase);
+}
+
+static inline void tpm_tis_iowrite32(u32 b, void __iomem *iobase, u32 addr)
+{
+	iowrite32(b, iobase + addr);
+	tpm_tis_flush(iobase);
+}
+
 static bool interrupts = true;
 module_param(interrupts, bool, 0444);
 MODULE_PARM_DESC(interrupts, "Enable interrupts");
@@ -146,7 +171,7 @@ static int tpm_tcg_write_bytes(struct tpm_tis_data *data, u32 addr, u16 len,
 	struct tpm_tis_tcg_phy *phy = to_tpm_tis_tcg_phy(data);
 
 	while (len--)
-		iowrite8(*value++, phy->iobase + addr);
+		tpm_tis_iowrite8(*value++, phy->iobase, addr);
 
 	return 0;
 }
@@ -173,7 +198,7 @@ static int tpm_tcg_write32(struct tpm_tis_data *data, u32 addr, u32 value)
 {
 	struct tpm_tis_tcg_phy *phy = to_tpm_tis_tcg_phy(data);
 
-	iowrite32(value, phy->iobase + addr);
+	tpm_tis_iowrite32(value, phy->iobase, addr);
 
 	return 0;
 }
diff --git a/drivers/clocksource/Kconfig b/drivers/clocksource/Kconfig
index f35a53ce8988a..d02f9c8d28487 100644
--- a/drivers/clocksource/Kconfig
+++ b/drivers/clocksource/Kconfig
@@ -434,6 +434,13 @@ config ATMEL_TCB_CLKSRC
 	help
 	  Support for Timer Counter Blocks on Atmel SoCs.
 
+config ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK
+	bool "TC Block use 32 KiHz clock"
+	depends on ATMEL_TCB_CLKSRC
+	default y
+	help
+	  Select this to use 32 KiHz base clock rate as TC block clock.
+
 config CLKSRC_EXYNOS_MCT
 	bool "Exynos multi core timer driver" if COMPILE_TEST
 	depends on ARM || ARM64
diff --git a/drivers/clocksource/timer-atmel-tcb.c b/drivers/clocksource/timer-atmel-tcb.c
index 7427b07495a89..ce6627ee161fe 100644
--- a/drivers/clocksource/timer-atmel-tcb.c
+++ b/drivers/clocksource/timer-atmel-tcb.c
@@ -28,8 +28,7 @@
  *     this 32 bit free-running counter. the second channel is not used.
  *
  *   - The third channel may be used to provide a 16-bit clockevent
- *     source, used in either periodic or oneshot mode.  This runs
- *     at 32 KiHZ, and can handle delays of up to two seconds.
+ *     source, used in either periodic or oneshot mode.
  *
  * REVISIT behavior during system suspend states... we should disable
  * all clocks and save the power.  Easily done for clockevent devices,
@@ -143,6 +142,8 @@ static unsigned long notrace tc_delay_timer_read32(void)
 struct tc_clkevt_device {
 	struct clock_event_device	clkevt;
 	struct clk			*clk;
+	bool				clk_enabled;
+	u32				freq;
 	void __iomem			*regs;
 };
 
@@ -151,15 +152,26 @@ static struct tc_clkevt_device *to_tc_clkevt(struct clock_event_device *clkevt)
 	return container_of(clkevt, struct tc_clkevt_device, clkevt);
 }
 
-/* For now, we always use the 32K clock ... this optimizes for NO_HZ,
- * because using one of the divided clocks would usually mean the
- * tick rate can never be less than several dozen Hz (vs 0.5 Hz).
- *
- * A divided clock could be good for high resolution timers, since
- * 30.5 usec resolution can seem "low".
- */
 static u32 timer_clock;
 
+static void tc_clk_disable(struct clock_event_device *d)
+{
+	struct tc_clkevt_device *tcd = to_tc_clkevt(d);
+
+	clk_disable(tcd->clk);
+	tcd->clk_enabled = false;
+}
+
+static void tc_clk_enable(struct clock_event_device *d)
+{
+	struct tc_clkevt_device *tcd = to_tc_clkevt(d);
+
+	if (tcd->clk_enabled)
+		return;
+	clk_enable(tcd->clk);
+	tcd->clk_enabled = true;
+}
+
 static int tc_shutdown(struct clock_event_device *d)
 {
 	struct tc_clkevt_device *tcd = to_tc_clkevt(d);
@@ -167,8 +179,14 @@ static int tc_shutdown(struct clock_event_device *d)
 
 	writel(0xff, regs + ATMEL_TC_REG(2, IDR));
 	writel(ATMEL_TC_CLKDIS, regs + ATMEL_TC_REG(2, CCR));
+	return 0;
+}
+
+static int tc_shutdown_clk_off(struct clock_event_device *d)
+{
+	tc_shutdown(d);
 	if (!clockevent_state_detached(d))
-		clk_disable(tcd->clk);
+		tc_clk_disable(d);
 
 	return 0;
 }
@@ -181,9 +199,9 @@ static int tc_set_oneshot(struct clock_event_device *d)
 	if (clockevent_state_oneshot(d) || clockevent_state_periodic(d))
 		tc_shutdown(d);
 
-	clk_enable(tcd->clk);
+	tc_clk_enable(d);
 
-	/* slow clock, count up to RC, then irq and stop */
+	/* count up to RC, then irq and stop */
 	writel(timer_clock | ATMEL_TC_CPCSTOP | ATMEL_TC_WAVE |
 		     ATMEL_TC_WAVESEL_UP_AUTO, regs + ATMEL_TC_REG(2, CMR));
 	writel(ATMEL_TC_CPCS, regs + ATMEL_TC_REG(2, IER));
@@ -203,12 +221,12 @@ static int tc_set_periodic(struct clock_event_device *d)
 	/* By not making the gentime core emulate periodic mode on top
 	 * of oneshot, we get lower overhead and improved accuracy.
 	 */
-	clk_enable(tcd->clk);
+	tc_clk_enable(d);
 
-	/* slow clock, count up to RC, then irq and restart */
+	/* count up to RC, then irq and restart */
 	writel(timer_clock | ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP_AUTO,
 		     regs + ATMEL_TC_REG(2, CMR));
-	writel((32768 + HZ / 2) / HZ, tcaddr + ATMEL_TC_REG(2, RC));
+	writel((tcd->freq + HZ / 2) / HZ, tcaddr + ATMEL_TC_REG(2, RC));
 
 	/* Enable clock and interrupts on RC compare */
 	writel(ATMEL_TC_CPCS, regs + ATMEL_TC_REG(2, IER));
@@ -234,9 +252,13 @@ static struct tc_clkevt_device clkevt = {
 		.features		= CLOCK_EVT_FEAT_PERIODIC |
 					  CLOCK_EVT_FEAT_ONESHOT,
 		/* Should be lower than at91rm9200's system timer */
+#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK
 		.rating			= 125,
+#else
+		.rating			= 200,
+#endif
 		.set_next_event		= tc_next_event,
-		.set_state_shutdown	= tc_shutdown,
+		.set_state_shutdown	= tc_shutdown_clk_off,
 		.set_state_periodic	= tc_set_periodic,
 		.set_state_oneshot	= tc_set_oneshot,
 	},
@@ -256,8 +278,11 @@ static irqreturn_t ch2_irq(int irq, void *handle)
 	return IRQ_NONE;
 }
 
-static int __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx)
+static const u8 atmel_tcb_divisors[5] = { 2, 8, 32, 128, 0, };
+
+static int __init setup_clkevents(struct atmel_tc *tc, int divisor_idx)
 {
+	unsigned divisor = atmel_tcb_divisors[divisor_idx];
 	int ret;
 	struct clk *t2_clk = tc->clk[2];
 	int irq = tc->irq[2];
@@ -278,7 +303,11 @@ static int __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx)
 	clkevt.regs = tc->regs;
 	clkevt.clk = t2_clk;
 
-	timer_clock = clk32k_divisor_idx;
+	timer_clock = divisor_idx;
+	if (!divisor)
+		clkevt.freq = 32768;
+	else
+		clkevt.freq = clk_get_rate(t2_clk) / divisor;
 
 	clkevt.clkevt.cpumask = cpumask_of(0);
 
@@ -289,7 +318,7 @@ static int __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx)
 		return ret;
 	}
 
-	clockevents_config_and_register(&clkevt.clkevt, 32768, 1, 0xffff);
+	clockevents_config_and_register(&clkevt.clkevt, clkevt.freq, 1, 0xffff);
 
 	return ret;
 }
@@ -346,8 +375,6 @@ static void __init tcb_setup_single_chan(struct atmel_tc *tc, int mck_divisor_id
 	writel(ATMEL_TC_SYNC, tcaddr + ATMEL_TC_BCR);
 }
 
-static const u8 atmel_tcb_divisors[5] = { 2, 8, 32, 128, 0, };
-
 static const struct of_device_id atmel_tcb_of_match[] = {
 	{ .compatible = "atmel,at91rm9200-tcb", .data = (void *)16, },
 	{ .compatible = "atmel,at91sam9x5-tcb", .data = (void *)32, },
@@ -467,7 +494,11 @@ static int __init tcb_clksrc_init(struct device_node *node)
 		goto err_disable_t1;
 
 	/* channel 2:  periodic and oneshot timer support */
+#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK
 	ret = setup_clkevents(&tc, clk32k_divisor_idx);
+#else
+	ret = setup_clkevents(&tc, best_divisor_idx);
+#endif
 	if (ret)
 		goto err_unregister_clksrc;
 
diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c
index d58ce664da843..1b2e9f19c98df 100644
--- a/drivers/connector/cn_proc.c
+++ b/drivers/connector/cn_proc.c
@@ -18,6 +18,7 @@
 #include <linux/pid_namespace.h>
 
 #include <linux/cn_proc.h>
+#include <linux/locallock.h>
 
 /*
  * Size of a cn_msg followed by a proc_event structure.  Since the
@@ -40,10 +41,11 @@ static struct cb_id cn_proc_event_id = { CN_IDX_PROC, CN_VAL_PROC };
 
 /* proc_event_counts is used as the sequence number of the netlink message */
 static DEFINE_PER_CPU(__u32, proc_event_counts) = { 0 };
+static DEFINE_LOCAL_IRQ_LOCK(send_msg_lock);
 
 static inline void send_msg(struct cn_msg *msg)
 {
-	preempt_disable();
+	local_lock(send_msg_lock);
 
 	msg->seq = __this_cpu_inc_return(proc_event_counts) - 1;
 	((struct proc_event *)msg->data)->cpu = smp_processor_id();
@@ -56,7 +58,7 @@ static inline void send_msg(struct cn_msg *msg)
 	 */
 	cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_NOWAIT);
 
-	preempt_enable();
+	local_unlock(send_msg_lock);
 }
 
 void proc_fork_connector(struct task_struct *task)
diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 433d91d710e4e..03d216e3dc548 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -214,7 +214,7 @@ static __poll_t dma_buf_poll(struct file *file, poll_table *poll)
 		return 0;
 
 retry:
-	seq = read_seqcount_begin(&resv->seq);
+	seq = read_seqbegin(&resv->seq);
 	rcu_read_lock();
 
 	fobj = rcu_dereference(resv->fence);
@@ -223,7 +223,7 @@ static __poll_t dma_buf_poll(struct file *file, poll_table *poll)
 	else
 		shared_count = 0;
 	fence_excl = rcu_dereference(resv->fence_excl);
-	if (read_seqcount_retry(&resv->seq, seq)) {
+	if (read_seqretry(&resv->seq, seq)) {
 		rcu_read_unlock();
 		goto retry;
 	}
@@ -1189,12 +1189,12 @@ static int dma_buf_debug_show(struct seq_file *s, void *unused)
 
 		robj = buf_obj->resv;
 		while (true) {
-			seq = read_seqcount_begin(&robj->seq);
+			seq = read_seqbegin(&robj->seq);
 			rcu_read_lock();
 			fobj = rcu_dereference(robj->fence);
 			shared_count = fobj ? fobj->shared_count : 0;
 			fence = rcu_dereference(robj->fence_excl);
-			if (!read_seqcount_retry(&robj->seq, seq))
+			if (!read_seqretry(&robj->seq, seq))
 				break;
 			rcu_read_unlock();
 		}
diff --git a/drivers/dma-buf/dma-resv.c b/drivers/dma-buf/dma-resv.c
index 709002515550c..b0c0d4fe0b331 100644
--- a/drivers/dma-buf/dma-resv.c
+++ b/drivers/dma-buf/dma-resv.c
@@ -49,12 +49,6 @@
 DEFINE_WD_CLASS(reservation_ww_class);
 EXPORT_SYMBOL(reservation_ww_class);
 
-struct lock_class_key reservation_seqcount_class;
-EXPORT_SYMBOL(reservation_seqcount_class);
-
-const char reservation_seqcount_string[] = "reservation_seqcount";
-EXPORT_SYMBOL(reservation_seqcount_string);
-
 /**
  * dma_resv_list_alloc - allocate fence list
  * @shared_max: number of fences we need space for
@@ -103,8 +97,7 @@ void dma_resv_init(struct dma_resv *obj)
 {
 	ww_mutex_init(&obj->lock, &reservation_ww_class);
 
-	__seqcount_init(&obj->seq, reservation_seqcount_string,
-			&reservation_seqcount_class);
+	seqlock_init(&obj->seq);
 	RCU_INIT_POINTER(obj->fence, NULL);
 	RCU_INIT_POINTER(obj->fence_excl, NULL);
 }
@@ -234,8 +227,7 @@ void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence)
 	fobj = dma_resv_get_list(obj);
 	count = fobj->shared_count;
 
-	preempt_disable();
-	write_seqcount_begin(&obj->seq);
+	write_seqlock(&obj->seq);
 
 	for (i = 0; i < count; ++i) {
 
@@ -255,8 +247,7 @@ void dma_resv_add_shared_fence(struct dma_resv *obj, struct dma_fence *fence)
 	/* pointer update must be visible before we extend the shared_count */
 	smp_store_mb(fobj->shared_count, count);
 
-	write_seqcount_end(&obj->seq);
-	preempt_enable();
+	write_sequnlock(&obj->seq);
 	dma_fence_put(old);
 }
 EXPORT_SYMBOL(dma_resv_add_shared_fence);
@@ -283,14 +274,12 @@ void dma_resv_add_excl_fence(struct dma_resv *obj, struct dma_fence *fence)
 	if (fence)
 		dma_fence_get(fence);
 
-	preempt_disable();
-	write_seqcount_begin(&obj->seq);
-	/* write_seqcount_begin provides the necessary memory barrier */
+	write_seqlock(&obj->seq);
+	/* write_seqlock provides the necessary memory barrier */
 	RCU_INIT_POINTER(obj->fence_excl, fence);
 	if (old)
 		old->shared_count = 0;
-	write_seqcount_end(&obj->seq);
-	preempt_enable();
+	write_sequnlock(&obj->seq);
 
 	/* inplace update, no shared fences */
 	while (i--)
@@ -368,13 +357,11 @@ int dma_resv_copy_fences(struct dma_resv *dst, struct dma_resv *src)
 	src_list = dma_resv_get_list(dst);
 	old = dma_resv_get_excl(dst);
 
-	preempt_disable();
-	write_seqcount_begin(&dst->seq);
-	/* write_seqcount_begin provides the necessary memory barrier */
+	write_seqlock(&dst->seq);
+	/* write_seqlock provides the necessary memory barrier */
 	RCU_INIT_POINTER(dst->fence_excl, new);
 	RCU_INIT_POINTER(dst->fence, dst_list);
-	write_seqcount_end(&dst->seq);
-	preempt_enable();
+	write_sequnlock(&dst->seq);
 
 	dma_resv_list_free(src_list);
 	dma_fence_put(old);
@@ -414,7 +401,7 @@ int dma_resv_get_fences_rcu(struct dma_resv *obj,
 		shared_count = i = 0;
 
 		rcu_read_lock();
-		seq = read_seqcount_begin(&obj->seq);
+		seq = read_seqbegin(&obj->seq);
 
 		fence_excl = rcu_dereference(obj->fence_excl);
 		if (fence_excl && !dma_fence_get_rcu(fence_excl))
@@ -456,7 +443,7 @@ int dma_resv_get_fences_rcu(struct dma_resv *obj,
 			}
 		}
 
-		if (i != shared_count || read_seqcount_retry(&obj->seq, seq)) {
+		if (i != shared_count || read_seqretry(&obj->seq, seq)) {
 			while (i--)
 				dma_fence_put(shared[i]);
 			dma_fence_put(fence_excl);
@@ -507,7 +494,7 @@ long dma_resv_wait_timeout_rcu(struct dma_resv *obj,
 
 retry:
 	shared_count = 0;
-	seq = read_seqcount_begin(&obj->seq);
+	seq = read_seqbegin(&obj->seq);
 	rcu_read_lock();
 	i = -1;
 
@@ -553,7 +540,7 @@ long dma_resv_wait_timeout_rcu(struct dma_resv *obj,
 
 	rcu_read_unlock();
 	if (fence) {
-		if (read_seqcount_retry(&obj->seq, seq)) {
+		if (read_seqretry(&obj->seq, seq)) {
 			dma_fence_put(fence);
 			goto retry;
 		}
@@ -607,7 +594,7 @@ bool dma_resv_test_signaled_rcu(struct dma_resv *obj, bool test_all)
 retry:
 	ret = true;
 	shared_count = 0;
-	seq = read_seqcount_begin(&obj->seq);
+	seq = read_seqbegin(&obj->seq);
 
 	if (test_all) {
 		unsigned i;
@@ -627,7 +614,7 @@ bool dma_resv_test_signaled_rcu(struct dma_resv *obj, bool test_all)
 				break;
 		}
 
-		if (read_seqcount_retry(&obj->seq, seq))
+		if (read_seqretry(&obj->seq, seq))
 			goto retry;
 	}
 
@@ -639,7 +626,7 @@ bool dma_resv_test_signaled_rcu(struct dma_resv *obj, bool test_all)
 			if (ret < 0)
 				goto retry;
 
-			if (read_seqcount_retry(&obj->seq, seq))
+			if (read_seqretry(&obj->seq, seq))
 				goto retry;
 		}
 	}
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index e98bbf8e56d9b..c5caff393767d 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -68,7 +68,7 @@ struct mm_struct efi_mm = {
 
 struct workqueue_struct *efi_rts_wq;
 
-static bool disable_runtime;
+static bool disable_runtime = IS_ENABLED(CONFIG_PREEMPT_RT);
 static int __init setup_noefi(char *arg)
 {
 	disable_runtime = true;
@@ -94,6 +94,9 @@ static int __init parse_efi_cmdline(char *str)
 	if (parse_option_str(str, "noruntime"))
 		disable_runtime = true;
 
+	if (parse_option_str(str, "runtime"))
+		disable_runtime = false;
+
 	return 0;
 }
 early_param("efi", parse_efi_cmdline);
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index e67c194c2acad..5f6dcbbeb0c1b 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -397,7 +397,7 @@ config DRM_R128
 
 config DRM_I810
 	tristate "Intel I810"
-	# !PREEMPT because of missing ioctl locking
+	# !PREEMPTION because of missing ioctl locking
 	depends on DRM && AGP && AGP_INTEL && (!PREEMPTION || BROKEN)
 	help
 	  Choose this option if you have an Intel I810 graphics card.  If M is
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 6d021ecc8d598..52f77b7701c03 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -252,11 +252,9 @@ static int amdgpu_amdkfd_remove_eviction_fence(struct amdgpu_bo *bo,
 	new->shared_count = k;
 
 	/* Install the new fence list, seqcount provides the barriers */
-	preempt_disable();
-	write_seqcount_begin(&resv->seq);
+	write_seqlock(&resv->seq);
 	RCU_INIT_POINTER(resv->fence, new);
-	write_seqcount_end(&resv->seq);
-	preempt_enable();
+	write_sequnlock(&resv->seq);
 
 	/* Drop the references to the removed fences or move them to ef_list */
 	for (i = j, k = 0; i < old->shared_count; ++i) {
diff --git a/drivers/gpu/drm/i915/display/intel_sprite.c b/drivers/gpu/drm/i915/display/intel_sprite.c
index cae25e493128d..da71ac8dea356 100644
--- a/drivers/gpu/drm/i915/display/intel_sprite.c
+++ b/drivers/gpu/drm/i915/display/intel_sprite.c
@@ -38,6 +38,7 @@
 #include <drm/drm_plane_helper.h>
 #include <drm/drm_rect.h>
 #include <drm/i915_drm.h>
+#include <linux/locallock.h>
 
 #include "i915_drv.h"
 #include "i915_trace.h"
@@ -80,6 +81,8 @@ int intel_usecs_to_scanlines(const struct drm_display_mode *adjusted_mode,
 #define VBLANK_EVASION_TIME_US 100
 #endif
 
+static DEFINE_LOCAL_IRQ_LOCK(pipe_update_lock);
+
 /**
  * intel_pipe_update_start() - start update of a set of display registers
  * @new_crtc_state: the new crtc state
@@ -129,7 +132,7 @@ void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state)
 		DRM_ERROR("PSR idle timed out 0x%x, atomic update may fail\n",
 			  psr_status);
 
-	local_irq_disable();
+	local_lock_irq(pipe_update_lock);
 
 	crtc->debug.min_vbl = min;
 	crtc->debug.max_vbl = max;
@@ -153,11 +156,11 @@ void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state)
 			break;
 		}
 
-		local_irq_enable();
+		local_unlock_irq(pipe_update_lock);
 
 		timeout = schedule_timeout(timeout);
 
-		local_irq_disable();
+		local_lock_irq(pipe_update_lock);
 	}
 
 	finish_wait(wq, &wait);
@@ -190,7 +193,7 @@ void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state)
 	return;
 
 irq_disable:
-	local_irq_disable();
+	local_lock_irq(pipe_update_lock);
 }
 
 /**
@@ -226,7 +229,7 @@ void intel_pipe_update_end(struct intel_crtc_state *new_crtc_state)
 		new_crtc_state->base.event = NULL;
 	}
 
-	local_irq_enable();
+	local_unlock_irq(pipe_update_lock);
 
 	if (intel_vgpu_active(dev_priv))
 		return;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_busy.c b/drivers/gpu/drm/i915/gem/i915_gem_busy.c
index 3d4f5775a4baa..c77bca239fca4 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_busy.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_busy.c
@@ -75,7 +75,6 @@ busy_check_writer(const struct dma_fence *fence)
 
 	return __busy_set_if_active(fence, __busy_write_id);
 }
-
 int
 i915_gem_busy_ioctl(struct drm_device *dev, void *data,
 		    struct drm_file *file)
@@ -110,7 +109,8 @@ i915_gem_busy_ioctl(struct drm_device *dev, void *data,
 	 *
 	 */
 retry:
-	seq = raw_read_seqcount(&obj->base.resv->seq);
+	/* XXX raw_read_seqcount() does not wait for the WRTIE to finish */
+	seq = read_seqbegin(&obj->base.resv->seq);
 
 	/* Translate the exclusive fence to the READ *and* WRITE engine */
 	args->busy =
@@ -129,7 +129,7 @@ i915_gem_busy_ioctl(struct drm_device *dev, void *data,
 		}
 	}
 
-	if (args->busy && read_seqcount_retry(&obj->base.resv->seq, seq))
+	if (args->busy && read_seqretry(&obj->base.resv->seq, seq))
 		goto retry;
 
 	err = 0;
diff --git a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
index 09c68dda20988..55317081d48b0 100644
--- a/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/gt/intel_breadcrumbs.c
@@ -120,7 +120,6 @@ __dma_fence_signal__notify(struct dma_fence *fence,
 	struct dma_fence_cb *cur, *tmp;
 
 	lockdep_assert_held(fence->lock);
-	lockdep_assert_irqs_disabled();
 
 	list_for_each_entry_safe(cur, tmp, list, node) {
 		INIT_LIST_HEAD(&cur->node);
@@ -134,9 +133,10 @@ void intel_engine_breadcrumbs_irq(struct intel_engine_cs *engine)
 	const ktime_t timestamp = ktime_get();
 	struct intel_context *ce, *cn;
 	struct list_head *pos, *next;
+	unsigned long flags;
 	LIST_HEAD(signal);
 
-	spin_lock(&b->irq_lock);
+	spin_lock_irqsave(&b->irq_lock, flags);
 
 	if (b->irq_armed && list_empty(&b->signalers))
 		__intel_breadcrumbs_disarm_irq(b);
@@ -182,30 +182,23 @@ void intel_engine_breadcrumbs_irq(struct intel_engine_cs *engine)
 		}
 	}
 
-	spin_unlock(&b->irq_lock);
+	spin_unlock_irqrestore(&b->irq_lock, flags);
 
 	list_for_each_safe(pos, next, &signal) {
 		struct i915_request *rq =
 			list_entry(pos, typeof(*rq), signal_link);
 		struct list_head cb_list;
 
-		spin_lock(&rq->lock);
+		spin_lock_irqsave(&rq->lock, flags);
 		list_replace(&rq->fence.cb_list, &cb_list);
 		__dma_fence_signal__timestamp(&rq->fence, timestamp);
 		__dma_fence_signal__notify(&rq->fence, &cb_list);
-		spin_unlock(&rq->lock);
+		spin_unlock_irqrestore(&rq->lock, flags);
 
 		i915_request_put(rq);
 	}
 }
 
-void intel_engine_signal_breadcrumbs(struct intel_engine_cs *engine)
-{
-	local_irq_disable();
-	intel_engine_breadcrumbs_irq(engine);
-	local_irq_enable();
-}
-
 static void signal_irq_work(struct irq_work *work)
 {
 	struct intel_engine_cs *engine =
@@ -275,7 +268,6 @@ void intel_engine_fini_breadcrumbs(struct intel_engine_cs *engine)
 bool i915_request_enable_breadcrumb(struct i915_request *rq)
 {
 	lockdep_assert_held(&rq->lock);
-	lockdep_assert_irqs_disabled();
 
 	if (test_bit(I915_FENCE_FLAG_ACTIVE, &rq->fence.flags)) {
 		struct intel_breadcrumbs *b = &rq->engine->breadcrumbs;
@@ -325,7 +317,6 @@ void i915_request_cancel_breadcrumb(struct i915_request *rq)
 	struct intel_breadcrumbs *b = &rq->engine->breadcrumbs;
 
 	lockdep_assert_held(&rq->lock);
-	lockdep_assert_irqs_disabled();
 
 	/*
 	 * We must wait for b->irq_lock so that we know the interrupt handler
diff --git a/drivers/gpu/drm/i915/gt/intel_engine.h b/drivers/gpu/drm/i915/gt/intel_engine.h
index 22aab8593abfa..316dccb41da80 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine.h
+++ b/drivers/gpu/drm/i915/gt/intel_engine.h
@@ -349,7 +349,6 @@ void intel_engine_init_execlists(struct intel_engine_cs *engine);
 void intel_engine_init_breadcrumbs(struct intel_engine_cs *engine);
 void intel_engine_fini_breadcrumbs(struct intel_engine_cs *engine);
 
-void intel_engine_signal_breadcrumbs(struct intel_engine_cs *engine);
 void intel_engine_disarm_breadcrumbs(struct intel_engine_cs *engine);
 
 static inline void
diff --git a/drivers/gpu/drm/i915/gt/intel_hangcheck.c b/drivers/gpu/drm/i915/gt/intel_hangcheck.c
index 05d042cdefe24..7ca67aac27d4d 100644
--- a/drivers/gpu/drm/i915/gt/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/gt/intel_hangcheck.c
@@ -283,7 +283,7 @@ static void hangcheck_elapsed(struct work_struct *work)
 	for_each_engine(engine, gt->i915, id) {
 		struct hangcheck hc;
 
-		intel_engine_signal_breadcrumbs(engine);
+		intel_engine_breadcrumbs_irq(engine);
 
 		hangcheck_load_sample(engine, &hc);
 		hangcheck_accumulate_sample(engine, &hc);
diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
index 8cea42379dd79..05f965e2e132e 100644
--- a/drivers/gpu/drm/i915/gt/intel_reset.c
+++ b/drivers/gpu/drm/i915/gt/intel_reset.c
@@ -695,7 +695,7 @@ static void reset_finish_engine(struct intel_engine_cs *engine)
 	engine->reset.finish(engine);
 	intel_uncore_forcewake_put(engine->uncore, FORCEWAKE_ALL);
 
-	intel_engine_signal_breadcrumbs(engine);
+	intel_engine_breadcrumbs_irq(engine);
 }
 
 static void reset_finish(struct intel_gt *gt, intel_engine_mask_t awake)
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 37e3dd3c1a9dc..9a482fb0f4afa 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -983,6 +983,7 @@ bool i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
 	spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
 
 	/* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */
+	preempt_disable_rt();
 
 	/* Get optional system timestamp before query. */
 	if (stime)
@@ -1034,6 +1035,7 @@ bool i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
 		*etime = ktime_get();
 
 	/* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */
+	preempt_enable_rt();
 
 	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
 
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 1c5506822dc72..cf10246fb01ad 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -205,14 +205,14 @@ static void remove_from_engine(struct i915_request *rq)
 	 * check that the rq still belongs to the newly locked engine.
 	 */
 	locked = READ_ONCE(rq->engine);
-	spin_lock(&locked->active.lock);
+	spin_lock_irq(&locked->active.lock);
 	while (unlikely(locked != (engine = READ_ONCE(rq->engine)))) {
 		spin_unlock(&locked->active.lock);
 		spin_lock(&engine->active.lock);
 		locked = engine;
 	}
 	list_del(&rq->sched.link);
-	spin_unlock(&locked->active.lock);
+	spin_unlock_irq(&locked->active.lock);
 }
 
 static bool i915_request_retire(struct i915_request *rq)
@@ -272,8 +272,6 @@ static bool i915_request_retire(struct i915_request *rq)
 		active->retire(active, rq);
 	}
 
-	local_irq_disable();
-
 	/*
 	 * We only loosely track inflight requests across preemption,
 	 * and so we may find ourselves attempting to retire a _completed_
@@ -282,7 +280,7 @@ static bool i915_request_retire(struct i915_request *rq)
 	 */
 	remove_from_engine(rq);
 
-	spin_lock(&rq->lock);
+	spin_lock_irq(&rq->lock);
 	i915_request_mark_complete(rq);
 	if (!i915_request_signaled(rq))
 		dma_fence_signal_locked(&rq->fence);
@@ -297,9 +295,7 @@ static bool i915_request_retire(struct i915_request *rq)
 		__notify_execute_cb(rq);
 	}
 	GEM_BUG_ON(!list_empty(&rq->execute_cb));
-	spin_unlock(&rq->lock);
-
-	local_irq_enable();
+	spin_unlock_irq(&rq->lock);
 
 	remove_from_client(rq);
 	list_del(&rq->link);
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 24f2944da09de..b8ee3cd14323d 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -2,6 +2,10 @@
 #if !defined(_I915_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
 #define _I915_TRACE_H_
 
+#ifdef CONFIG_PREEMPT_RT
+#define NOTRACE
+#endif
+
 #include <linux/stringify.h>
 #include <linux/types.h>
 #include <linux/tracepoint.h>
@@ -721,7 +725,7 @@ DEFINE_EVENT(i915_request, i915_request_add,
 	    TP_ARGS(rq)
 );
 
-#if defined(CONFIG_DRM_I915_LOW_LEVEL_TRACEPOINTS)
+#if defined(CONFIG_DRM_I915_LOW_LEVEL_TRACEPOINTS) && !defined(NOTRACE)
 DEFINE_EVENT(i915_request, i915_request_submit,
 	     TP_PROTO(struct i915_request *rq),
 	     TP_ARGS(rq)
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index e81b01f8db90e..b07e4684c2c40 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -1819,6 +1819,7 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
 	struct radeon_device *rdev = dev->dev_private;
 
 	/* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */
+	preempt_disable_rt();
 
 	/* Get optional system timestamp before query. */
 	if (stime)
@@ -1911,6 +1912,7 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
 		*etime = ktime_get();
 
 	/* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */
+	preempt_enable_rt();
 
 	/* Decode into vertical and horizontal scanout position. */
 	*vpos = position & 0x1fff;
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index af9379a3bf899..0b1ef04302d4a 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -18,6 +18,7 @@
 #include <linux/atomic.h>
 #include <linux/hyperv.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 
 #include "hv_trace.h"
 
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 53a60c81e220d..146453c4450a3 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -22,6 +22,7 @@
 #include <linux/clockchips.h>
 #include <linux/cpu.h>
 #include <linux/sched/task_stack.h>
+#include <linux/irq.h>
 
 #include <asm/mshyperv.h>
 #include <linux/delay.h>
@@ -1199,6 +1200,8 @@ static void vmbus_isr(void)
 	void *page_addr = hv_cpu->synic_event_page;
 	struct hv_message *msg;
 	union hv_synic_event_flags *event;
+	struct pt_regs *regs = get_irq_regs();
+	u64 ip = regs ? instruction_pointer(regs) : 0;
 	bool handled = false;
 
 	if (unlikely(page_addr == NULL))
@@ -1243,7 +1246,7 @@ static void vmbus_isr(void)
 			tasklet_schedule(&hv_cpu->msg_dpc);
 	}
 
-	add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0);
+	add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0, ip);
 }
 
 /*
diff --git a/drivers/leds/trigger/Kconfig b/drivers/leds/trigger/Kconfig
index ce9429ca6ddea..29ccbd6acf43f 100644
--- a/drivers/leds/trigger/Kconfig
+++ b/drivers/leds/trigger/Kconfig
@@ -64,6 +64,7 @@ config LEDS_TRIGGER_BACKLIGHT
 
 config LEDS_TRIGGER_CPU
 	bool "LED CPU Trigger"
+	depends on !PREEMPT_RT
 	help
 	  This allows LEDs to be controlled by active CPUs. This shows
 	  the active CPUs across an array of LEDs so you can see which
diff --git a/drivers/md/bcache/Kconfig b/drivers/md/bcache/Kconfig
index 6dfa653d30db7..29c35eb524148 100644
--- a/drivers/md/bcache/Kconfig
+++ b/drivers/md/bcache/Kconfig
@@ -2,6 +2,7 @@
 
 config BCACHE
 	tristate "Block device as cache"
+	depends on !PREEMPT_RT
 	select CRC64
 	help
 	Allows a block device to be used as cache for other devices; uses
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 12a8ce83786ea..74f3e4aa2b817 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2058,8 +2058,9 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
 	struct raid5_percpu *percpu;
 	unsigned long cpu;
 
-	cpu = get_cpu();
+	cpu = get_cpu_light();
 	percpu = per_cpu_ptr(conf->percpu, cpu);
+	spin_lock(&percpu->lock);
 	if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) {
 		ops_run_biofill(sh);
 		overlap_clear++;
@@ -2118,7 +2119,8 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
 			if (test_and_clear_bit(R5_Overlap, &dev->flags))
 				wake_up(&sh->raid_conf->wait_for_overlap);
 		}
-	put_cpu();
+	spin_unlock(&percpu->lock);
+	put_cpu_light();
 }
 
 static void free_stripe(struct kmem_cache *sc, struct stripe_head *sh)
@@ -6821,6 +6823,7 @@ static int raid456_cpu_up_prepare(unsigned int cpu, struct hlist_node *node)
 			__func__, cpu);
 		return -ENOMEM;
 	}
+	spin_lock_init(&per_cpu_ptr(conf->percpu, cpu)->lock);
 	return 0;
 }
 
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index f90e0704bed99..cca69edd669da 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -634,6 +634,7 @@ struct r5conf {
 	int			recovery_disabled;
 	/* per cpu variables */
 	struct raid5_percpu {
+		spinlock_t	lock;		/* Protection for -RT */
 		struct page	*spare_page; /* Used when checking P/Q in raid6 */
 		void		*scribble;  /* space for constructing buffer
 					     * lists and performing address
diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig
index f1f61419fd292..56d4c1e91c276 100644
--- a/drivers/media/platform/Kconfig
+++ b/drivers/media/platform/Kconfig
@@ -585,7 +585,7 @@ config VIDEO_MESON_G12A_AO_CEC
 
 config CEC_GPIO
 	tristate "Generic GPIO-based CEC driver"
-	depends on PREEMPT || COMPILE_TEST
+	depends on PREEMPTION || COMPILE_TEST
 	select CEC_CORE
 	select CEC_PIN
 	select GPIOLIB
diff --git a/drivers/net/wireless/intersil/orinoco/orinoco_usb.c b/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
index 40a8b941ad5cc..6cb1b8bb83ec5 100644
--- a/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
+++ b/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
@@ -693,8 +693,8 @@ static void ezusb_req_ctx_wait(struct ezusb_priv *upriv,
 			while (!ctx->done.done && msecs--)
 				udelay(1000);
 		} else {
-			wait_event_interruptible(ctx->done.wait,
-						 ctx->done.done);
+			swait_event_interruptible_exclusive(ctx->done.wait,
+							    ctx->done.done);
 		}
 		break;
 	default:
diff --git a/drivers/of/base.c b/drivers/of/base.c
index 1d667eb730e19..a82b8c05169e7 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -123,115 +123,38 @@ int __weak of_node_to_nid(struct device_node *np)
 }
 #endif
 
-/*
- * Assumptions behind phandle_cache implementation:
- *   - phandle property values are in a contiguous range of 1..n
- *
- * If the assumptions do not hold, then
- *   - the phandle lookup overhead reduction provided by the cache
- *     will likely be less
- */
+#define OF_PHANDLE_CACHE_BITS	7
+#define OF_PHANDLE_CACHE_SZ	BIT(OF_PHANDLE_CACHE_BITS)
 
-static struct device_node **phandle_cache;
-static u32 phandle_cache_mask;
+static struct device_node *phandle_cache[OF_PHANDLE_CACHE_SZ];
+
+static u32 of_phandle_cache_hash(phandle handle)
+{
+	return hash_32(handle, OF_PHANDLE_CACHE_BITS);
+}
 
 /*
  * Caller must hold devtree_lock.
  */
-static void __of_free_phandle_cache(void)
+void __of_phandle_cache_inv_entry(phandle handle)
 {
-	u32 cache_entries = phandle_cache_mask + 1;
-	u32 k;
-
-	if (!phandle_cache)
-		return;
-
-	for (k = 0; k < cache_entries; k++)
-		of_node_put(phandle_cache[k]);
-
-	kfree(phandle_cache);
-	phandle_cache = NULL;
-}
-
-int of_free_phandle_cache(void)
-{
-	unsigned long flags;
-
-	raw_spin_lock_irqsave(&devtree_lock, flags);
-
-	__of_free_phandle_cache();
-
-	raw_spin_unlock_irqrestore(&devtree_lock, flags);
-
-	return 0;
-}
-#if !defined(CONFIG_MODULES)
-late_initcall_sync(of_free_phandle_cache);
-#endif
-
-/*
- * Caller must hold devtree_lock.
- */
-void __of_free_phandle_cache_entry(phandle handle)
-{
-	phandle masked_handle;
+	u32 handle_hash;
 	struct device_node *np;
 
 	if (!handle)
 		return;
 
-	masked_handle = handle & phandle_cache_mask;
+	handle_hash = of_phandle_cache_hash(handle);
 
-	if (phandle_cache) {
-		np = phandle_cache[masked_handle];
-		if (np && handle == np->phandle) {
-			of_node_put(np);
-			phandle_cache[masked_handle] = NULL;
-		}
-	}
-}
-
-void of_populate_phandle_cache(void)
-{
-	unsigned long flags;
-	u32 cache_entries;
-	struct device_node *np;
-	u32 phandles = 0;
-
-	raw_spin_lock_irqsave(&devtree_lock, flags);
-
-	__of_free_phandle_cache();
-
-	for_each_of_allnodes(np)
-		if (np->phandle && np->phandle != OF_PHANDLE_ILLEGAL)
-			phandles++;
-
-	if (!phandles)
-		goto out;
-
-	cache_entries = roundup_pow_of_two(phandles);
-	phandle_cache_mask = cache_entries - 1;
-
-	phandle_cache = kcalloc(cache_entries, sizeof(*phandle_cache),
-				GFP_ATOMIC);
-	if (!phandle_cache)
-		goto out;
-
-	for_each_of_allnodes(np)
-		if (np->phandle && np->phandle != OF_PHANDLE_ILLEGAL) {
-			of_node_get(np);
-			phandle_cache[np->phandle & phandle_cache_mask] = np;
-		}
-
-out:
-	raw_spin_unlock_irqrestore(&devtree_lock, flags);
+	np = phandle_cache[handle_hash];
+	if (np && handle == np->phandle)
+		phandle_cache[handle_hash] = NULL;
 }
 
 void __init of_core_init(void)
 {
 	struct device_node *np;
 
-	of_populate_phandle_cache();
 
 	/* Create the kset, and register existing nodes */
 	mutex_lock(&of_mutex);
@@ -241,8 +164,11 @@ void __init of_core_init(void)
 		pr_err("failed to register existing nodes\n");
 		return;
 	}
-	for_each_of_allnodes(np)
+	for_each_of_allnodes(np) {
 		__of_attach_node_sysfs(np);
+		if (np->phandle && !phandle_cache[of_phandle_cache_hash(np->phandle)])
+			phandle_cache[of_phandle_cache_hash(np->phandle)] = np;
+	}
 	mutex_unlock(&of_mutex);
 
 	/* Symlink in /proc as required by userspace ABI */
@@ -1223,36 +1149,29 @@ struct device_node *of_find_node_by_phandle(phandle handle)
 {
 	struct device_node *np = NULL;
 	unsigned long flags;
-	phandle masked_handle;
+	u32 handle_hash;
 
 	if (!handle)
 		return NULL;
 
+	handle_hash = of_phandle_cache_hash(handle);
+
 	raw_spin_lock_irqsave(&devtree_lock, flags);
 
-	masked_handle = handle & phandle_cache_mask;
-
-	if (phandle_cache) {
-		if (phandle_cache[masked_handle] &&
-		    handle == phandle_cache[masked_handle]->phandle)
-			np = phandle_cache[masked_handle];
-		if (np && of_node_check_flag(np, OF_DETACHED)) {
-			WARN_ON(1); /* did not uncache np on node removal */
-			of_node_put(np);
-			phandle_cache[masked_handle] = NULL;
-			np = NULL;
-		}
+	if (phandle_cache[handle_hash] &&
+	    handle == phandle_cache[handle_hash]->phandle)
+		np = phandle_cache[handle_hash];
+	if (np && of_node_check_flag(np, OF_DETACHED)) {
+		WARN_ON(1); /* did not uncache np on node removal */
+		phandle_cache[handle_hash] = NULL;
+		np = NULL;
 	}
 
 	if (!np) {
 		for_each_of_allnodes(np)
 			if (np->phandle == handle &&
 			    !of_node_check_flag(np, OF_DETACHED)) {
-				if (phandle_cache) {
-					/* will put when removed from cache */
-					of_node_get(np);
-					phandle_cache[masked_handle] = np;
-				}
+				phandle_cache[handle_hash] = np;
 				break;
 			}
 	}
diff --git a/drivers/of/dynamic.c b/drivers/of/dynamic.c
index 49b16f76d78e8..08fd823edac9d 100644
--- a/drivers/of/dynamic.c
+++ b/drivers/of/dynamic.c
@@ -276,7 +276,7 @@ void __of_detach_node(struct device_node *np)
 	of_node_set_flag(np, OF_DETACHED);
 
 	/* race with of_find_node_by_phandle() prevented by devtree_lock */
-	__of_free_phandle_cache_entry(np->phandle);
+	__of_phandle_cache_inv_entry(np->phandle);
 }
 
 /**
diff --git a/drivers/of/of_private.h b/drivers/of/of_private.h
index 24786818e32e5..de0042bc77015 100644
--- a/drivers/of/of_private.h
+++ b/drivers/of/of_private.h
@@ -85,14 +85,12 @@ int of_resolve_phandles(struct device_node *tree);
 #endif
 
 #if defined(CONFIG_OF_DYNAMIC)
-void __of_free_phandle_cache_entry(phandle handle);
+void __of_phandle_cache_inv_entry(phandle handle);
 #endif
 
 #if defined(CONFIG_OF_OVERLAY)
 void of_overlay_mutex_lock(void);
 void of_overlay_mutex_unlock(void);
-int of_free_phandle_cache(void);
-void of_populate_phandle_cache(void);
 #else
 static inline void of_overlay_mutex_lock(void) {};
 static inline void of_overlay_mutex_unlock(void) {};
diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c
index c423e94baf0f0..14fa7804b0d10 100644
--- a/drivers/of/overlay.c
+++ b/drivers/of/overlay.c
@@ -971,8 +971,6 @@ static int of_overlay_apply(const void *fdt, struct device_node *tree,
 		goto err_free_overlay_changeset;
 	}
 
-	of_populate_phandle_cache();
-
 	ret = __of_changeset_apply_notify(&ovcs->cset);
 	if (ret)
 		pr_err("overlay apply changeset entry notify error %d\n", ret);
@@ -1215,17 +1213,9 @@ int of_overlay_remove(int *ovcs_id)
 
 	list_del(&ovcs->ovcs_list);
 
-	/*
-	 * Disable phandle cache.  Avoids race condition that would arise
-	 * from removing cache entry when the associated node is deleted.
-	 */
-	of_free_phandle_cache();
-
 	ret_apply = 0;
 	ret = __of_changeset_revert_entries(&ovcs->cset, &ret_apply);
 
-	of_populate_phandle_cache();
-
 	if (ret) {
 		if (ret_apply)
 			devicetree_state_flags |= DTSF_REVERT_FAIL;
diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c
index 8c94cd3fd1f21..93d091732a142 100644
--- a/drivers/pci/switch/switchtec.c
+++ b/drivers/pci/switch/switchtec.c
@@ -52,10 +52,11 @@ struct switchtec_user {
 
 	enum mrpc_state state;
 
-	struct completion comp;
+	wait_queue_head_t cmd_comp;
 	struct kref kref;
 	struct list_head list;
 
+	bool cmd_done;
 	u32 cmd;
 	u32 status;
 	u32 return_code;
@@ -77,7 +78,7 @@ static struct switchtec_user *stuser_create(struct switchtec_dev *stdev)
 	stuser->stdev = stdev;
 	kref_init(&stuser->kref);
 	INIT_LIST_HEAD(&stuser->list);
-	init_completion(&stuser->comp);
+	init_waitqueue_head(&stuser->cmd_comp);
 	stuser->event_cnt = atomic_read(&stdev->event_cnt);
 
 	dev_dbg(&stdev->dev, "%s: %p\n", __func__, stuser);
@@ -175,7 +176,7 @@ static int mrpc_queue_cmd(struct switchtec_user *stuser)
 	kref_get(&stuser->kref);
 	stuser->read_len = sizeof(stuser->data);
 	stuser_set_state(stuser, MRPC_QUEUED);
-	init_completion(&stuser->comp);
+	stuser->cmd_done = false;
 	list_add_tail(&stuser->list, &stdev->mrpc_queue);
 
 	mrpc_cmd_submit(stdev);
@@ -222,7 +223,8 @@ static void mrpc_complete_cmd(struct switchtec_dev *stdev)
 		memcpy_fromio(stuser->data, &stdev->mmio_mrpc->output_data,
 			      stuser->read_len);
 out:
-	complete_all(&stuser->comp);
+	stuser->cmd_done = true;
+	wake_up_interruptible(&stuser->cmd_comp);
 	list_del_init(&stuser->list);
 	stuser_put(stuser);
 	stdev->mrpc_busy = 0;
@@ -494,10 +496,11 @@ static ssize_t switchtec_dev_read(struct file *filp, char __user *data,
 	mutex_unlock(&stdev->mrpc_mutex);
 
 	if (filp->f_flags & O_NONBLOCK) {
-		if (!try_wait_for_completion(&stuser->comp))
+		if (!READ_ONCE(stuser->cmd_done))
 			return -EAGAIN;
 	} else {
-		rc = wait_for_completion_interruptible(&stuser->comp);
+		rc = wait_event_interruptible(stuser->cmd_comp,
+					      stuser->cmd_done);
 		if (rc < 0)
 			return rc;
 	}
@@ -545,7 +548,7 @@ static __poll_t switchtec_dev_poll(struct file *filp, poll_table *wait)
 	struct switchtec_dev *stdev = stuser->stdev;
 	__poll_t ret = 0;
 
-	poll_wait(filp, &stuser->comp.wait, wait);
+	poll_wait(filp, &stuser->cmd_comp, wait);
 	poll_wait(filp, &stdev->event_wq, wait);
 
 	if (lock_mutex_and_test_alive(stdev))
@@ -553,7 +556,7 @@ static __poll_t switchtec_dev_poll(struct file *filp, poll_table *wait)
 
 	mutex_unlock(&stdev->mrpc_mutex);
 
-	if (try_wait_for_completion(&stuser->comp))
+	if (READ_ONCE(stuser->cmd_done))
 		ret |= EPOLLIN | EPOLLRDNORM;
 
 	if (stuser->event_cnt != atomic_read(&stdev->event_cnt))
@@ -1106,7 +1109,8 @@ static void stdev_kill(struct switchtec_dev *stdev)
 
 	/* Wake up and kill any users waiting on an MRPC request */
 	list_for_each_entry_safe(stuser, tmpuser, &stdev->mrpc_queue, list) {
-		complete_all(&stuser->comp);
+		stuser->cmd_done = true;
+		wake_up_interruptible(&stuser->cmd_comp);
 		list_del_init(&stuser->list);
 		stuser_put(stuser);
 	}
diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
index 25dae9f0b2055..2acc1f6da9020 100644
--- a/drivers/scsi/fcoe/fcoe.c
+++ b/drivers/scsi/fcoe/fcoe.c
@@ -1452,11 +1452,11 @@ static int fcoe_rcv(struct sk_buff *skb, struct net_device *netdev,
 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;
 }
@@ -1641,11 +1641,11 @@ static inline int fcoe_filter_frames(struct fc_lport *lport,
 		return 0;
 	}
 
-	stats = per_cpu_ptr(lport->stats, get_cpu());
+	stats = per_cpu_ptr(lport->stats, get_cpu_light());
 	stats->InvalidCRCCount++;
 	if (stats->InvalidCRCCount < 5)
 		printk(KERN_WARNING "fcoe: dropping frame with CRC error\n");
-	put_cpu();
+	put_cpu_light();
 	return -EINVAL;
 }
 
@@ -1686,7 +1686,7 @@ static void fcoe_recv_frame(struct sk_buff *skb)
 	 */
 	hp = (struct fcoe_hdr *) skb_network_header(skb);
 
-	stats = per_cpu_ptr(lport->stats, get_cpu());
+	stats = per_cpu_ptr(lport->stats, get_cpu_light());
 	if (unlikely(FC_FCOE_DECAPS_VER(hp) != FC_FCOE_VER)) {
 		if (stats->ErrorFrames < 5)
 			printk(KERN_WARNING "fcoe: FCoE version "
@@ -1718,13 +1718,13 @@ static void fcoe_recv_frame(struct sk_buff *skb)
 		goto drop;
 
 	if (!fcoe_filter_frames(lport, fp)) {
-		put_cpu();
+		put_cpu_light();
 		fc_exch_recv(lport, fp);
 		return;
 	}
 drop:
 	stats->ErrorFrames++;
-	put_cpu();
+	put_cpu_light();
 	kfree_skb(skb);
 }
 
diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c
index 1791a393795da..8fdfae2b8782f 100644
--- a/drivers/scsi/fcoe/fcoe_ctlr.c
+++ b/drivers/scsi/fcoe/fcoe_ctlr.c
@@ -826,7 +826,7 @@ static unsigned long fcoe_ctlr_age_fcfs(struct fcoe_ctlr *fip)
 
 	INIT_LIST_HEAD(&del_list);
 
-	stats = per_cpu_ptr(fip->lp->stats, get_cpu());
+	stats = per_cpu_ptr(fip->lp->stats, get_cpu_light());
 
 	list_for_each_entry_safe(fcf, next, &fip->fcfs, list) {
 		deadline = fcf->time + fcf->fka_period + fcf->fka_period / 2;
@@ -862,7 +862,7 @@ static unsigned long fcoe_ctlr_age_fcfs(struct fcoe_ctlr *fip)
 				sel_time = fcf->time;
 		}
 	}
-	put_cpu();
+	put_cpu_light();
 
 	list_for_each_entry_safe(fcf, next, &del_list, list) {
 		/* Removes fcf from current list */
diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c
index 52e8666598531..78c75a2314228 100644
--- a/drivers/scsi/libfc/fc_exch.c
+++ b/drivers/scsi/libfc/fc_exch.c
@@ -821,10 +821,10 @@ static struct fc_exch *fc_exch_em_alloc(struct fc_lport *lport,
 	}
 	memset(ep, 0, sizeof(*ep));
 
-	cpu = get_cpu();
+	cpu = get_cpu_light();
 	pool = per_cpu_ptr(mp->pool, cpu);
 	spin_lock_bh(&pool->lock);
-	put_cpu();
+	put_cpu_light();
 
 	/* peek cache of free slot */
 	if (pool->left != FC_XID_UNKNOWN) {
diff --git a/drivers/thermal/intel/x86_pkg_temp_thermal.c b/drivers/thermal/intel/x86_pkg_temp_thermal.c
index ddb4a973c6986..e18758a8e911a 100644
--- a/drivers/thermal/intel/x86_pkg_temp_thermal.c
+++ b/drivers/thermal/intel/x86_pkg_temp_thermal.c
@@ -63,7 +63,7 @@ static int max_id __read_mostly;
 /* Array of zone pointers */
 static struct zone_device **zones;
 /* Serializes interrupt notification, work and hotplug */
-static DEFINE_SPINLOCK(pkg_temp_lock);
+static DEFINE_RAW_SPINLOCK(pkg_temp_lock);
 /* Protects zone operation in the work function against hotplug removal */
 static DEFINE_MUTEX(thermal_zone_mutex);
 
@@ -266,12 +266,12 @@ static void pkg_temp_thermal_threshold_work_fn(struct work_struct *work)
 	u64 msr_val, wr_val;
 
 	mutex_lock(&thermal_zone_mutex);
-	spin_lock_irq(&pkg_temp_lock);
+	raw_spin_lock_irq(&pkg_temp_lock);
 	++pkg_work_cnt;
 
 	zonedev = pkg_temp_thermal_get_dev(cpu);
 	if (!zonedev) {
-		spin_unlock_irq(&pkg_temp_lock);
+		raw_spin_unlock_irq(&pkg_temp_lock);
 		mutex_unlock(&thermal_zone_mutex);
 		return;
 	}
@@ -285,7 +285,7 @@ static void pkg_temp_thermal_threshold_work_fn(struct work_struct *work)
 	}
 
 	enable_pkg_thres_interrupt();
-	spin_unlock_irq(&pkg_temp_lock);
+	raw_spin_unlock_irq(&pkg_temp_lock);
 
 	/*
 	 * If tzone is not NULL, then thermal_zone_mutex will prevent the
@@ -310,7 +310,7 @@ static int pkg_thermal_notify(u64 msr_val)
 	struct zone_device *zonedev;
 	unsigned long flags;
 
-	spin_lock_irqsave(&pkg_temp_lock, flags);
+	raw_spin_lock_irqsave(&pkg_temp_lock, flags);
 	++pkg_interrupt_cnt;
 
 	disable_pkg_thres_interrupt();
@@ -322,7 +322,7 @@ static int pkg_thermal_notify(u64 msr_val)
 		pkg_thermal_schedule_work(zonedev->cpu, &zonedev->work);
 	}
 
-	spin_unlock_irqrestore(&pkg_temp_lock, flags);
+	raw_spin_unlock_irqrestore(&pkg_temp_lock, flags);
 	return 0;
 }
 
@@ -368,9 +368,9 @@ static int pkg_temp_thermal_device_add(unsigned int cpu)
 	      zonedev->msr_pkg_therm_high);
 
 	cpumask_set_cpu(cpu, &zonedev->cpumask);
-	spin_lock_irq(&pkg_temp_lock);
+	raw_spin_lock_irq(&pkg_temp_lock);
 	zones[id] = zonedev;
-	spin_unlock_irq(&pkg_temp_lock);
+	raw_spin_unlock_irq(&pkg_temp_lock);
 	return 0;
 }
 
@@ -407,7 +407,7 @@ static int pkg_thermal_cpu_offline(unsigned int cpu)
 	}
 
 	/* Protect against work and interrupts */
-	spin_lock_irq(&pkg_temp_lock);
+	raw_spin_lock_irq(&pkg_temp_lock);
 
 	/*
 	 * Check whether this cpu was the current target and store the new
@@ -439,9 +439,9 @@ static int pkg_thermal_cpu_offline(unsigned int cpu)
 		 * To cancel the work we need to drop the lock, otherwise
 		 * we might deadlock if the work needs to be flushed.
 		 */
-		spin_unlock_irq(&pkg_temp_lock);
+		raw_spin_unlock_irq(&pkg_temp_lock);
 		cancel_delayed_work_sync(&zonedev->work);
-		spin_lock_irq(&pkg_temp_lock);
+		raw_spin_lock_irq(&pkg_temp_lock);
 		/*
 		 * If this is not the last cpu in the package and the work
 		 * did not run after we dropped the lock above, then we
@@ -452,7 +452,7 @@ static int pkg_thermal_cpu_offline(unsigned int cpu)
 			pkg_thermal_schedule_work(target, &zonedev->work);
 	}
 
-	spin_unlock_irq(&pkg_temp_lock);
+	raw_spin_unlock_irq(&pkg_temp_lock);
 
 	/* Final cleanup if this is the last cpu */
 	if (lastcpu)
diff --git a/drivers/tty/serial/8250/8250.h b/drivers/tty/serial/8250/8250.h
index 33ad9d6de5323..4e6c74330829d 100644
--- a/drivers/tty/serial/8250/8250.h
+++ b/drivers/tty/serial/8250/8250.h
@@ -96,6 +96,10 @@ struct serial8250_config {
 #define SERIAL8250_SHARE_IRQS 0
 #endif
 
+void set_ier(struct uart_8250_port *up, unsigned char ier);
+void clear_ier(struct uart_8250_port *up);
+void restore_ier(struct uart_8250_port *up);
+
 #define SERIAL8250_PORT_FLAGS(_base, _irq, _flags)		\
 	{							\
 		.iobase		= _base,			\
@@ -139,6 +143,15 @@ static inline bool serial8250_set_THRI(struct uart_8250_port *up)
 	return true;
 }
 
+static inline bool serial8250_set_THRI_sier(struct uart_8250_port *up)
+{
+	if (up->ier & UART_IER_THRI)
+		return false;
+	up->ier |= UART_IER_THRI;
+	set_ier(up, up->ier);
+	return true;
+}
+
 static inline bool serial8250_clear_THRI(struct uart_8250_port *up)
 {
 	if (!(up->ier & UART_IER_THRI))
@@ -148,6 +161,15 @@ static inline bool serial8250_clear_THRI(struct uart_8250_port *up)
 	return true;
 }
 
+static inline bool serial8250_clear_THRI_sier(struct uart_8250_port *up)
+{
+	if (!(up->ier & UART_IER_THRI))
+		return false;
+	up->ier &= ~UART_IER_THRI;
+	set_ier(up, up->ier);
+	return true;
+}
+
 struct uart_8250_port *serial8250_get_port(int line);
 
 void serial8250_rpm_get(struct uart_8250_port *p);
diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index e682390ce0dea..8c40472eff194 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -55,7 +55,16 @@ static struct uart_driver serial8250_reg;
 
 static unsigned int skip_txen_test; /* force skip of txen test at init time */
 
-#define PASS_LIMIT	512
+/*
+ * On -rt we can have a more delays, and legitimately
+ * so - so don't drop work spuriously and spam the
+ * syslog:
+ */
+#ifdef CONFIG_PREEMPT_RT
+# define PASS_LIMIT	1000000
+#else
+# define PASS_LIMIT	512
+#endif
 
 #include <asm/serial.h>
 /*
@@ -266,7 +275,7 @@ static void serial8250_timeout(struct timer_list *t)
 static void serial8250_backup_timeout(struct timer_list *t)
 {
 	struct uart_8250_port *up = from_timer(up, t, timer);
-	unsigned int iir, ier = 0, lsr;
+	unsigned int iir, lsr;
 	unsigned long flags;
 
 	spin_lock_irqsave(&up->port.lock, flags);
@@ -275,10 +284,8 @@ static void serial8250_backup_timeout(struct timer_list *t)
 	 * Must disable interrupts or else we risk racing with the interrupt
 	 * based handler.
 	 */
-	if (up->port.irq) {
-		ier = serial_in(up, UART_IER);
-		serial_out(up, UART_IER, 0);
-	}
+	if (up->port.irq)
+		clear_ier(up);
 
 	iir = serial_in(up, UART_IIR);
 
@@ -301,7 +308,7 @@ static void serial8250_backup_timeout(struct timer_list *t)
 		serial8250_tx_chars(up);
 
 	if (up->port.irq)
-		serial_out(up, UART_IER, ier);
+		restore_ier(up);
 
 	spin_unlock_irqrestore(&up->port.lock, flags);
 
@@ -579,6 +586,14 @@ serial8250_register_ports(struct uart_driver *drv, struct device *dev)
 
 #ifdef CONFIG_SERIAL_8250_CONSOLE
 
+static void univ8250_console_write_atomic(struct console *co, const char *s,
+					  unsigned int count)
+{
+	struct uart_8250_port *up = &serial8250_ports[co->index];
+
+	serial8250_console_write_atomic(up, s, count);
+}
+
 static void univ8250_console_write(struct console *co, const char *s,
 				   unsigned int count)
 {
@@ -664,6 +679,7 @@ static int univ8250_console_match(struct console *co, char *name, int idx,
 
 static struct console univ8250_console = {
 	.name		= "ttyS",
+	.write_atomic	= univ8250_console_write_atomic,
 	.write		= univ8250_console_write,
 	.device		= uart_console_device,
 	.setup		= univ8250_console_setup,
diff --git a/drivers/tty/serial/8250/8250_dma.c b/drivers/tty/serial/8250/8250_dma.c
index 890fa7ddaa7f3..c91dafbca57c9 100644
--- a/drivers/tty/serial/8250/8250_dma.c
+++ b/drivers/tty/serial/8250/8250_dma.c
@@ -35,7 +35,7 @@ static void __dma_tx_complete(void *param)
 
 	ret = serial8250_tx_dma(p);
 	if (ret)
-		serial8250_set_THRI(p);
+		serial8250_set_THRI_sier(p);
 
 	spin_unlock_irqrestore(&p->port.lock, flags);
 }
@@ -98,7 +98,7 @@ int serial8250_tx_dma(struct uart_8250_port *p)
 	dma_async_issue_pending(dma->txchan);
 	if (dma->tx_err) {
 		dma->tx_err = 0;
-		serial8250_clear_THRI(p);
+		serial8250_clear_THRI_sier(p);
 	}
 	return 0;
 err:
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index 8407166610ce7..51d9a79b70db3 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -721,7 +721,7 @@ static void serial8250_set_sleep(struct uart_8250_port *p, int sleep)
 			serial_out(p, UART_EFR, UART_EFR_ECB);
 			serial_out(p, UART_LCR, 0);
 		}
-		serial_out(p, UART_IER, sleep ? UART_IERX_SLEEP : 0);
+		set_ier(p, sleep ? UART_IERX_SLEEP : 0);
 		if (p->capabilities & UART_CAP_EFR) {
 			serial_out(p, UART_LCR, UART_LCR_CONF_MODE_B);
 			serial_out(p, UART_EFR, efr);
@@ -1390,7 +1390,7 @@ static void serial8250_stop_rx(struct uart_port *port)
 
 	up->ier &= ~(UART_IER_RLSI | UART_IER_RDI);
 	up->port.read_status_mask &= ~UART_LSR_DR;
-	serial_port_out(port, UART_IER, up->ier);
+	set_ier(up, up->ier);
 
 	serial8250_rpm_put(up);
 }
@@ -1408,7 +1408,7 @@ static void __do_stop_tx_rs485(struct uart_8250_port *p)
 		serial8250_clear_and_reinit_fifos(p);
 
 		p->ier |= UART_IER_RLSI | UART_IER_RDI;
-		serial_port_out(&p->port, UART_IER, p->ier);
+		set_ier(p, p->ier);
 	}
 }
 static enum hrtimer_restart serial8250_em485_handle_stop_tx(struct hrtimer *t)
@@ -1459,7 +1459,7 @@ static void __stop_tx_rs485(struct uart_8250_port *p)
 
 static inline void __do_stop_tx(struct uart_8250_port *p)
 {
-	if (serial8250_clear_THRI(p))
+	if (serial8250_clear_THRI_sier(p))
 		serial8250_rpm_put_tx(p);
 }
 
@@ -1509,7 +1509,7 @@ static inline void __start_tx(struct uart_port *port)
 	if (up->dma && !up->dma->tx_dma(up))
 		return;
 
-	if (serial8250_set_THRI(up)) {
+	if (serial8250_set_THRI_sier(up)) {
 		if (up->bugs & UART_BUG_TXEN) {
 			unsigned char lsr;
 
@@ -1616,7 +1616,7 @@ static void serial8250_disable_ms(struct uart_port *port)
 	mctrl_gpio_disable_ms(up->gpios);
 
 	up->ier &= ~UART_IER_MSI;
-	serial_port_out(port, UART_IER, up->ier);
+	set_ier(up, up->ier);
 }
 
 static void serial8250_enable_ms(struct uart_port *port)
@@ -1632,7 +1632,7 @@ static void serial8250_enable_ms(struct uart_port *port)
 	up->ier |= UART_IER_MSI;
 
 	serial8250_rpm_get(up);
-	serial_port_out(port, UART_IER, up->ier);
+	set_ier(up, up->ier);
 	serial8250_rpm_put(up);
 }
 
@@ -1991,6 +1991,54 @@ static void wait_for_xmitr(struct uart_8250_port *up, int bits)
 	}
 }
 
+static atomic_t ier_counter = ATOMIC_INIT(0);
+static atomic_t ier_value = ATOMIC_INIT(0);
+
+void set_ier(struct uart_8250_port *up, unsigned char ier)
+{
+	struct uart_port *port = &up->port;
+	unsigned int flags;
+
+	console_atomic_lock(&flags);
+	if (atomic_read(&ier_counter) > 0)
+		atomic_set(&ier_value, ier);
+	else
+		serial_port_out(port, UART_IER, ier);
+	console_atomic_unlock(flags);
+}
+
+void clear_ier(struct uart_8250_port *up)
+{
+	struct uart_port *port = &up->port;
+	unsigned int ier_cleared = 0;
+	unsigned int flags;
+	unsigned int ier;
+
+	console_atomic_lock(&flags);
+	atomic_inc(&ier_counter);
+	ier = serial_port_in(port, UART_IER);
+	if (up->capabilities & UART_CAP_UUE)
+		ier_cleared = UART_IER_UUE;
+	if (ier != ier_cleared) {
+		serial_port_out(port, UART_IER, ier_cleared);
+		atomic_set(&ier_value, ier);
+	}
+	console_atomic_unlock(flags);
+}
+EXPORT_SYMBOL_GPL(clear_ier);
+
+void restore_ier(struct uart_8250_port *up)
+{
+	struct uart_port *port = &up->port;
+	unsigned int flags;
+
+	console_atomic_lock(&flags);
+	if (atomic_fetch_dec(&ier_counter) == 1)
+		serial_port_out(port, UART_IER, atomic_read(&ier_value));
+	console_atomic_unlock(flags);
+}
+EXPORT_SYMBOL_GPL(restore_ier);
+
 #ifdef CONFIG_CONSOLE_POLL
 /*
  * Console polling routines for writing and reading from the uart while
@@ -2022,18 +2070,10 @@ static int serial8250_get_poll_char(struct uart_port *port)
 static void serial8250_put_poll_char(struct uart_port *port,
 			 unsigned char c)
 {
-	unsigned int ier;
 	struct uart_8250_port *up = up_to_u8250p(port);
 
 	serial8250_rpm_get(up);
-	/*
-	 *	First save the IER then disable the interrupts
-	 */
-	ier = serial_port_in(port, UART_IER);
-	if (up->capabilities & UART_CAP_UUE)
-		serial_port_out(port, UART_IER, UART_IER_UUE);
-	else
-		serial_port_out(port, UART_IER, 0);
+	clear_ier(up);
 
 	wait_for_xmitr(up, BOTH_EMPTY);
 	/*
@@ -2046,7 +2086,7 @@ static void serial8250_put_poll_char(struct uart_port *port,
 	 *	and restore the IER
 	 */
 	wait_for_xmitr(up, BOTH_EMPTY);
-	serial_port_out(port, UART_IER, ier);
+	restore_ier(up);
 	serial8250_rpm_put(up);
 }
 
@@ -2354,7 +2394,7 @@ void serial8250_do_shutdown(struct uart_port *port)
 	 */
 	spin_lock_irqsave(&port->lock, flags);
 	up->ier = 0;
-	serial_port_out(port, UART_IER, 0);
+	set_ier(up, 0);
 	spin_unlock_irqrestore(&port->lock, flags);
 
 	synchronize_irq(port->irq);
@@ -2639,7 +2679,7 @@ serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios,
 	if (up->capabilities & UART_CAP_RTOIE)
 		up->ier |= UART_IER_RTOIE;
 
-	serial_port_out(port, UART_IER, up->ier);
+	set_ier(up, up->ier);
 
 	if (up->capabilities & UART_CAP_EFR) {
 		unsigned char efr = 0;
@@ -3103,7 +3143,7 @@ EXPORT_SYMBOL_GPL(serial8250_set_defaults);
 
 #ifdef CONFIG_SERIAL_8250_CONSOLE
 
-static void serial8250_console_putchar(struct uart_port *port, int ch)
+static void serial8250_console_putchar_locked(struct uart_port *port, int ch)
 {
 	struct uart_8250_port *up = up_to_u8250p(port);
 
@@ -3111,6 +3151,18 @@ static void serial8250_console_putchar(struct uart_port *port, int ch)
 	serial_port_out(port, UART_TX, ch);
 }
 
+static void serial8250_console_putchar(struct uart_port *port, int ch)
+{
+	struct uart_8250_port *up = up_to_u8250p(port);
+	unsigned int flags;
+
+	wait_for_xmitr(up, UART_LSR_THRE);
+
+	console_atomic_lock(&flags);
+	serial8250_console_putchar_locked(port, ch);
+	console_atomic_unlock(flags);
+}
+
 /*
  *	Restore serial console when h/w power-off detected
  */
@@ -3132,6 +3184,31 @@ static void serial8250_console_restore(struct uart_8250_port *up)
 	serial8250_out_MCR(up, UART_MCR_DTR | UART_MCR_RTS);
 }
 
+void serial8250_console_write_atomic(struct uart_8250_port *up,
+				     const char *s, unsigned int count)
+{
+	struct uart_port *port = &up->port;
+	unsigned int flags;
+
+	console_atomic_lock(&flags);
+
+	touch_nmi_watchdog();
+
+	clear_ier(up);
+
+	if (atomic_fetch_inc(&up->console_printing)) {
+		uart_console_write(port, "\n", 1,
+				   serial8250_console_putchar_locked);
+	}
+	uart_console_write(port, s, count, serial8250_console_putchar_locked);
+	atomic_dec(&up->console_printing);
+
+	wait_for_xmitr(up, BOTH_EMPTY);
+	restore_ier(up);
+
+	console_atomic_unlock(flags);
+}
+
 /*
  *	Print a string to the serial port trying not to disturb
  *	any possible real use of the port...
@@ -3143,27 +3220,13 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s,
 {
 	struct uart_port *port = &up->port;
 	unsigned long flags;
-	unsigned int ier;
-	int locked = 1;
 
 	touch_nmi_watchdog();
 
 	serial8250_rpm_get(up);
+	spin_lock_irqsave(&port->lock, flags);
 
-	if (oops_in_progress)
-		locked = spin_trylock_irqsave(&port->lock, flags);
-	else
-		spin_lock_irqsave(&port->lock, flags);
-
-	/*
-	 *	First save the IER then disable the interrupts
-	 */
-	ier = serial_port_in(port, UART_IER);
-
-	if (up->capabilities & UART_CAP_UUE)
-		serial_port_out(port, UART_IER, UART_IER_UUE);
-	else
-		serial_port_out(port, UART_IER, 0);
+	clear_ier(up);
 
 	/* check scratch reg to see if port powered off during system sleep */
 	if (up->canary && (up->canary != serial_port_in(port, UART_SCR))) {
@@ -3171,14 +3234,16 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s,
 		up->canary = 0;
 	}
 
+	atomic_inc(&up->console_printing);
 	uart_console_write(port, s, count, serial8250_console_putchar);
+	atomic_dec(&up->console_printing);
 
 	/*
 	 *	Finally, wait for transmitter to become empty
 	 *	and restore the IER
 	 */
 	wait_for_xmitr(up, BOTH_EMPTY);
-	serial_port_out(port, UART_IER, ier);
+	restore_ier(up);
 
 	/*
 	 *	The receive handling will happen properly because the
@@ -3190,8 +3255,7 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s,
 	if (up->msr_saved_flags)
 		serial8250_modem_status(up);
 
-	if (locked)
-		spin_unlock_irqrestore(&port->lock, flags);
+	spin_unlock_irqrestore(&port->lock, flags);
 	serial8250_rpm_put(up);
 }
 
@@ -3212,6 +3276,7 @@ static unsigned int probe_baud(struct uart_port *port)
 
 int serial8250_console_setup(struct uart_port *port, char *options, bool probe)
 {
+	struct uart_8250_port *up = up_to_u8250p(port);
 	int baud = 9600;
 	int bits = 8;
 	int parity = 'n';
@@ -3220,6 +3285,8 @@ int serial8250_console_setup(struct uart_port *port, char *options, bool probe)
 	if (!port->iobase && !port->membase)
 		return -ENODEV;
 
+	atomic_set(&up->console_printing, 0);
+
 	if (options)
 		uart_parse_options(options, &baud, &parity, &bits, &flow);
 	else if (probe)
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index b0b6895463952..3cd2687cbb8d0 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -2209,18 +2209,24 @@ pl011_console_write(struct console *co, const char *s, unsigned int count)
 {
 	struct uart_amba_port *uap = amba_ports[co->index];
 	unsigned int old_cr = 0, new_cr;
-	unsigned long flags;
+	unsigned long flags = 0;
 	int locked = 1;
 
 	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
@@ -2246,8 +2252,7 @@ pl011_console_write(struct console *co, const char *s, unsigned int count)
 		pl011_write(old_cr, uap, REG_CR);
 
 	if (locked)
-		spin_unlock(&uap->port.lock);
-	local_irq_restore(flags);
+		spin_unlock_irqrestore(&uap->port.lock, flags);
 
 	clk_disable(uap->clk);
 }
diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c
index 6420ae581a802..0f4f41ed9ffa5 100644
--- a/drivers/tty/serial/omap-serial.c
+++ b/drivers/tty/serial/omap-serial.c
@@ -1307,13 +1307,10 @@ serial_omap_console_write(struct console *co, const char *s,
 
 	pm_runtime_get_sync(up->dev);
 
-	local_irq_save(flags);
-	if (up->port.sysrq)
-		locked = 0;
-	else if (oops_in_progress)
-		locked = spin_trylock(&up->port.lock);
+	if (up->port.sysrq || oops_in_progress)
+		locked = spin_trylock_irqsave(&up->port.lock, flags);
 	else
-		spin_lock(&up->port.lock);
+		spin_lock_irqsave(&up->port.lock, flags);
 
 	/*
 	 * First save the IER then disable the interrupts
@@ -1342,8 +1339,7 @@ serial_omap_console_write(struct console *co, const char *s,
 	pm_runtime_mark_last_busy(up->dev);
 	pm_runtime_put_autosuspend(up->dev);
 	if (locked)
-		spin_unlock(&up->port.lock);
-	local_irq_restore(flags);
+		spin_unlock_irqrestore(&up->port.lock, flags);
 }
 
 static int __init
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 59d9d512dcdac..1ee8637a232ab 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -1715,7 +1715,7 @@ static void ffs_data_put(struct ffs_data *ffs)
 		pr_info("%s(): freeing\n", __func__);
 		ffs_data_clear(ffs);
 		BUG_ON(waitqueue_active(&ffs->ev.waitq) ||
-		       waitqueue_active(&ffs->ep0req_completion.wait) ||
+		       swait_active(&ffs->ep0req_completion.wait) ||
 		       waitqueue_active(&ffs->wait));
 		destroy_workqueue(ffs->io_completion_wq);
 		kfree(ffs->dev_name);
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index b47938dff1a22..e5141c1136e47 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -344,7 +344,7 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len)
 	spin_unlock_irq (&epdata->dev->lock);
 
 	if (likely (value == 0)) {
-		value = wait_event_interruptible (done.wait, done.done);
+		value = swait_event_interruptible_exclusive(done.wait, done.done);
 		if (value != 0) {
 			spin_lock_irq (&epdata->dev->lock);
 			if (likely (epdata->ep != NULL)) {
@@ -353,7 +353,7 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len)
 				usb_ep_dequeue (epdata->ep, epdata->req);
 				spin_unlock_irq (&epdata->dev->lock);
 
-				wait_event (done.wait, done.done);
+				swait_event_exclusive(done.wait, done.done);
 				if (epdata->status == -ECONNRESET)
 					epdata->status = -EINTR;
 			} else {
diff --git a/drivers/video/backlight/Kconfig b/drivers/video/backlight/Kconfig
index 40676be2e46aa..d09396393724b 100644
--- a/drivers/video/backlight/Kconfig
+++ b/drivers/video/backlight/Kconfig
@@ -99,7 +99,7 @@ config LCD_TOSA
 
 config LCD_HP700
 	tristate "HP Jornada 700 series LCD Driver"
-	depends on SA1100_JORNADA720_SSP && !PREEMPT
+	depends on SA1100_JORNADA720_SSP && !PREEMPTION
 	default y
 	help
 	  If you have an HP Jornada 700 series handheld (710/720/728)
@@ -228,7 +228,7 @@ config BACKLIGHT_HP680
 
 config BACKLIGHT_HP700
 	tristate "HP Jornada 700 series Backlight Driver"
-	depends on SA1100_JORNADA720_SSP && !PREEMPT
+	depends on SA1100_JORNADA720_SSP && !PREEMPTION
 	default y
 	help
 	  If you have an HP Jornada 700 series,
diff --git a/drivers/watchdog/watchdog_dev.c b/drivers/watchdog/watchdog_dev.c
index dbd2ad4c92948..00896eec12de4 100644
--- a/drivers/watchdog/watchdog_dev.c
+++ b/drivers/watchdog/watchdog_dev.c
@@ -158,7 +158,7 @@ static inline void watchdog_update_worker(struct watchdog_device *wdd)
 		ktime_t t = watchdog_next_keepalive(wdd);
 
 		if (t > 0)
-			hrtimer_start(&wd_data->timer, t, HRTIMER_MODE_REL);
+			hrtimer_start(&wd_data->timer, t, HRTIMER_MODE_REL_HARD);
 	} else {
 		hrtimer_cancel(&wd_data->timer);
 	}
@@ -177,7 +177,7 @@ static int __watchdog_ping(struct watchdog_device *wdd)
 	if (ktime_after(earliest_keepalive, now)) {
 		hrtimer_start(&wd_data->timer,
 			      ktime_sub(earliest_keepalive, now),
-			      HRTIMER_MODE_REL);
+			      HRTIMER_MODE_REL_HARD);
 		return 0;
 	}
 
@@ -971,7 +971,7 @@ static int watchdog_cdev_register(struct watchdog_device *wdd, dev_t devno)
 		return -ENODEV;
 
 	kthread_init_work(&wd_data->work, watchdog_ping_work);
-	hrtimer_init(&wd_data->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer_init(&wd_data->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
 	wd_data->timer.function = watchdog_timer_expired;
 
 	if (wdd->id == 0) {
@@ -1019,7 +1019,7 @@ static int watchdog_cdev_register(struct watchdog_device *wdd, dev_t devno)
 		__module_get(wdd->ops->owner);
 		kref_get(&wd_data->kref);
 		if (handle_boot_enabled)
-			hrtimer_start(&wd_data->timer, 0, HRTIMER_MODE_REL);
+			hrtimer_start(&wd_data->timer, 0, HRTIMER_MODE_REL_HARD);
 		else
 			pr_info("watchdog%d running and kernel based pre-userspace handler disabled\n",
 				wdd->id);
diff --git a/drivers/xen/preempt.c b/drivers/xen/preempt.c
index 8b9919c26095d..70650b248de5d 100644
--- a/drivers/xen/preempt.c
+++ b/drivers/xen/preempt.c
@@ -8,7 +8,7 @@
 #include <linux/sched.h>
 #include <xen/xen-ops.h>
 
-#ifndef CONFIG_PREEMPT
+#ifndef CONFIG_PREEMPTION
 
 /*
  * Some hypercalls issued by the toolstack can take many 10s of
@@ -37,4 +37,4 @@ asmlinkage __visible void xen_maybe_preempt_hcall(void)
 		__this_cpu_write(xen_in_preemptible_hcall, true);
 	}
 }
-#endif /* CONFIG_PREEMPT */
+#endif /* CONFIG_PREEMPTION */
diff --git a/fs/afs/dir_silly.c b/fs/afs/dir_silly.c
index 361088a5edb98..c1b1a51eb7297 100644
--- a/fs/afs/dir_silly.c
+++ b/fs/afs/dir_silly.c
@@ -202,7 +202,7 @@ int afs_silly_iput(struct dentry *dentry, struct inode *inode)
 	struct dentry *alias;
 	int ret;
 
-	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+	DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
 
 	_enter("%p{%pd},%llx", dentry, dentry, vnode->fid.vnode);
 
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 5acf5c507ec2e..ad1ccf94e4b87 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -179,7 +179,7 @@ btrfs_device_set_##name(struct btrfs_device *dev, u64 size)		\
 	write_seqcount_end(&dev->data_seqcount);			\
 	preempt_enable();						\
 }
-#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
+#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
 #define BTRFS_DEVICE_GETSET_FUNCS(name)					\
 static inline u64							\
 btrfs_device_get_##name(const struct btrfs_device *dev)			\
diff --git a/fs/buffer.c b/fs/buffer.c
index 86a38b9793235..4baea587981e0 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -275,8 +275,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
 	 * decide that the page is now completely done.
 	 */
 	first = page_buffers(page);
-	local_irq_save(flags);
-	bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
+	spin_lock_irqsave(&first->b_uptodate_lock, flags);
 	clear_buffer_async_read(bh);
 	unlock_buffer(bh);
 	tmp = bh;
@@ -289,8 +288,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
 		}
 		tmp = tmp->b_this_page;
 	} while (tmp != bh);
-	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
 
 	/*
 	 * If none of the buffers had errors and they are all
@@ -302,8 +300,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
 	return;
 
 still_busy:
-	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
 	return;
 }
 
@@ -331,8 +328,7 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate)
 	}
 
 	first = page_buffers(page);
-	local_irq_save(flags);
-	bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
+	spin_lock_irqsave(&first->b_uptodate_lock, flags);
 
 	clear_buffer_async_write(bh);
 	unlock_buffer(bh);
@@ -344,14 +340,12 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate)
 		}
 		tmp = tmp->b_this_page;
 	}
-	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
 	end_page_writeback(page);
 	return;
 
 still_busy:
-	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
 	return;
 }
 EXPORT_SYMBOL(end_buffer_async_write);
@@ -3368,6 +3362,7 @@ struct buffer_head *alloc_buffer_head(gfp_t gfp_flags)
 	struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags);
 	if (ret) {
 		INIT_LIST_HEAD(&ret->b_assoc_buffers);
+		spin_lock_init(&ret->b_uptodate_lock);
 		preempt_disable();
 		__this_cpu_inc(bh_accounting.nr);
 		recalc_bh_state();
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index 3925a7bfc74d6..33f7723fb83e9 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -80,7 +80,7 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name,
 	struct inode *inode;
 	struct super_block *sb = parent->d_sb;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
-	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+	DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
 
 	cifs_dbg(FYI, "%s: for %s\n", __func__, name->name);
 
diff --git a/fs/dcache.c b/fs/dcache.c
index e88cf0554e659..5699176ed169c 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2482,9 +2482,10 @@ EXPORT_SYMBOL(d_rehash);
 static inline unsigned start_dir_add(struct inode *dir)
 {
 
+	preempt_disable_rt();
 	for (;;) {
-		unsigned n = dir->i_dir_seq;
-		if (!(n & 1) && cmpxchg(&dir->i_dir_seq, n, n + 1) == n)
+		unsigned n = dir->__i_dir_seq;
+		if (!(n & 1) && cmpxchg(&dir->__i_dir_seq, n, n + 1) == n)
 			return n;
 		cpu_relax();
 	}
@@ -2492,26 +2493,30 @@ static inline unsigned start_dir_add(struct inode *dir)
 
 static inline void end_dir_add(struct inode *dir, unsigned n)
 {
-	smp_store_release(&dir->i_dir_seq, n + 2);
+	smp_store_release(&dir->__i_dir_seq, n + 2);
+	preempt_enable_rt();
 }
 
 static void d_wait_lookup(struct dentry *dentry)
 {
-	if (d_in_lookup(dentry)) {
-		DECLARE_WAITQUEUE(wait, current);
-		add_wait_queue(dentry->d_wait, &wait);
-		do {
-			set_current_state(TASK_UNINTERRUPTIBLE);
-			spin_unlock(&dentry->d_lock);
-			schedule();
-			spin_lock(&dentry->d_lock);
-		} while (d_in_lookup(dentry));
-	}
+	struct swait_queue __wait;
+
+	if (!d_in_lookup(dentry))
+		return;
+
+	INIT_LIST_HEAD(&__wait.task_list);
+	do {
+		prepare_to_swait_exclusive(dentry->d_wait, &__wait, TASK_UNINTERRUPTIBLE);
+		spin_unlock(&dentry->d_lock);
+		schedule();
+		spin_lock(&dentry->d_lock);
+	} while (d_in_lookup(dentry));
+	finish_swait(dentry->d_wait, &__wait);
 }
 
 struct dentry *d_alloc_parallel(struct dentry *parent,
 				const struct qstr *name,
-				wait_queue_head_t *wq)
+				struct swait_queue_head *wq)
 {
 	unsigned int hash = name->hash;
 	struct hlist_bl_head *b = in_lookup_hash(parent, hash);
@@ -2525,7 +2530,7 @@ struct dentry *d_alloc_parallel(struct dentry *parent,
 
 retry:
 	rcu_read_lock();
-	seq = smp_load_acquire(&parent->d_inode->i_dir_seq);
+	seq = smp_load_acquire(&parent->d_inode->__i_dir_seq);
 	r_seq = read_seqbegin(&rename_lock);
 	dentry = __d_lookup_rcu(parent, name, &d_seq);
 	if (unlikely(dentry)) {
@@ -2553,7 +2558,7 @@ struct dentry *d_alloc_parallel(struct dentry *parent,
 	}
 
 	hlist_bl_lock(b);
-	if (unlikely(READ_ONCE(parent->d_inode->i_dir_seq) != seq)) {
+	if (unlikely(READ_ONCE(parent->d_inode->__i_dir_seq) != seq)) {
 		hlist_bl_unlock(b);
 		rcu_read_unlock();
 		goto retry;
@@ -2626,7 +2631,7 @@ void __d_lookup_done(struct dentry *dentry)
 	hlist_bl_lock(b);
 	dentry->d_flags &= ~DCACHE_PAR_LOOKUP;
 	__hlist_bl_del(&dentry->d_u.d_in_lookup_hash);
-	wake_up_all(dentry->d_wait);
+	swake_up_all(dentry->d_wait);
 	dentry->d_wait = NULL;
 	hlist_bl_unlock(b);
 	INIT_HLIST_NODE(&dentry->d_u.d_alias);
@@ -3139,6 +3144,8 @@ __setup("dhash_entries=", set_dhash_entries);
 
 static void __init dcache_init_early(void)
 {
+	unsigned int loop;
+
 	/* If hashes are distributed across NUMA nodes, defer
 	 * hash allocation until vmalloc space is available.
 	 */
@@ -3155,11 +3162,16 @@ static void __init dcache_init_early(void)
 					NULL,
 					0,
 					0);
+
+	for (loop = 0; loop < (1U << d_hash_shift); loop++)
+		INIT_HLIST_BL_HEAD(dentry_hashtable + loop);
+
 	d_hash_shift = 32 - d_hash_shift;
 }
 
 static void __init dcache_init(void)
 {
+	unsigned int loop;
 	/*
 	 * A constructor could be added for stable state like the lists,
 	 * but it is probably not worth it because of the cache nature
@@ -3183,6 +3195,10 @@ static void __init dcache_init(void)
 					NULL,
 					0,
 					0);
+
+	for (loop = 0; loop < (1U << d_hash_shift); loop++)
+		INIT_HLIST_BL_HEAD(dentry_hashtable + loop);
+
 	d_hash_shift = 32 - d_hash_shift;
 }
 
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index c4159bcc05d9a..9ba07cb3cb524 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -567,12 +567,12 @@ static int ep_poll_wakeup_proc(void *priv, void *cookie, int call_nests)
 
 static void ep_poll_safewake(wait_queue_head_t *wq)
 {
-	int this_cpu = get_cpu();
+	int this_cpu = get_cpu_light();
 
 	ep_call_nested(&poll_safewake_ncalls,
 		       ep_poll_wakeup_proc, NULL, wq, (void *) (long) this_cpu);
 
-	put_cpu();
+	put_cpu_light();
 }
 
 #else
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 12ceadef32c5a..64d4c06fbf836 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -87,11 +87,10 @@ static void ext4_finish_bio(struct bio *bio)
 		}
 		bh = head = page_buffers(page);
 		/*
-		 * We check all buffers in the page under BH_Uptodate_Lock
+		 * We check all buffers in the page under b_uptodate_lock
 		 * to avoid races with other end io clearing async_write flags
 		 */
-		local_irq_save(flags);
-		bit_spin_lock(BH_Uptodate_Lock, &head->b_state);
+		spin_lock_irqsave(&head->b_uptodate_lock, flags);
 		do {
 			if (bh_offset(bh) < bio_start ||
 			    bh_offset(bh) + bh->b_size > bio_end) {
@@ -103,8 +102,7 @@ static void ext4_finish_bio(struct bio *bio)
 			if (bio->bi_status)
 				buffer_io_error(bh);
 		} while ((bh = bh->b_this_page) != head);
-		bit_spin_unlock(BH_Uptodate_Lock, &head->b_state);
-		local_irq_restore(flags);
+		spin_unlock_irqrestore(&head->b_uptodate_lock, flags);
 		if (!under_io) {
 			fscrypt_free_bounce_page(bounce_page);
 			end_page_writeback(page);
diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c
index 0ce39658a6200..5508d92e3f8fc 100644
--- a/fs/fscache/cookie.c
+++ b/fs/fscache/cookie.c
@@ -958,3 +958,11 @@ int __fscache_check_consistency(struct fscache_cookie *cookie,
 	return -ESTALE;
 }
 EXPORT_SYMBOL(__fscache_check_consistency);
+
+void __init fscache_cookie_init(void)
+{
+	int i;
+
+	for (i = 0; i < (1 << fscache_cookie_hash_shift) - 1; i++)
+		INIT_HLIST_BL_HEAD(&fscache_cookie_hash[i]);
+}
diff --git a/fs/fscache/main.c b/fs/fscache/main.c
index 59c2494efda34..f9625eb898530 100644
--- a/fs/fscache/main.c
+++ b/fs/fscache/main.c
@@ -145,6 +145,7 @@ static int __init fscache_init(void)
 		ret = -ENOMEM;
 		goto error_cookie_jar;
 	}
+	fscache_cookie_init();
 
 	fscache_root = kobject_create_and_add("fscache", kernel_kobj);
 	if (!fscache_root)
diff --git a/fs/fuse/readdir.c b/fs/fuse/readdir.c
index 6a40f75a0d25e..6e813ecf8f512 100644
--- a/fs/fuse/readdir.c
+++ b/fs/fuse/readdir.c
@@ -158,7 +158,7 @@ static int fuse_direntplus_link(struct file *file,
 	struct inode *dir = d_inode(parent);
 	struct fuse_conn *fc;
 	struct inode *inode;
-	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+	DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
 
 	if (!o->nodeid) {
 		/*
diff --git a/fs/inode.c b/fs/inode.c
index fef457a42882b..6f1bab381e40e 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -156,7 +156,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	inode->i_bdev = NULL;
 	inode->i_cdev = NULL;
 	inode->i_link = NULL;
-	inode->i_dir_seq = 0;
+	inode->__i_dir_seq = 0;
 	inode->i_rdev = 0;
 	inode->dirtied_when = 0;
 
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 132fb92098c71..8e1ff875de438 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -482,10 +482,10 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 		if (jh->b_committed_data) {
 			struct buffer_head *bh = jh2bh(jh);
 
-			jbd_lock_bh_state(bh);
+			spin_lock(&jh->b_state_lock);
 			jbd2_free(jh->b_committed_data, bh->b_size);
 			jh->b_committed_data = NULL;
-			jbd_unlock_bh_state(bh);
+			spin_unlock(&jh->b_state_lock);
 		}
 		jbd2_journal_refile_buffer(journal, jh);
 	}
@@ -918,6 +918,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 		transaction_t *cp_transaction;
 		struct buffer_head *bh;
 		int try_to_free = 0;
+		bool drop_ref;
 
 		jh = commit_transaction->t_forget;
 		spin_unlock(&journal->j_list_lock);
@@ -927,7 +928,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 		 * done with it.
 		 */
 		get_bh(bh);
-		jbd_lock_bh_state(bh);
+		spin_lock(&jh->b_state_lock);
 		J_ASSERT_JH(jh,	jh->b_transaction == commit_transaction);
 
 		/*
@@ -1022,8 +1023,10 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 				try_to_free = 1;
 		}
 		JBUFFER_TRACE(jh, "refile or unfile buffer");
-		__jbd2_journal_refile_buffer(jh);
-		jbd_unlock_bh_state(bh);
+		drop_ref = __jbd2_journal_refile_buffer(jh);
+		spin_unlock(&jh->b_state_lock);
+		if (drop_ref)
+			jbd2_journal_put_journal_head(jh);
 		if (try_to_free)
 			release_buffer_page(bh);	/* Drops bh reference */
 		else
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 1c58859aa5924..f6034ce4a1073 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -363,7 +363,7 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
 	/* keep subsequent assertions sane */
 	atomic_set(&new_bh->b_count, 1);
 
-	jbd_lock_bh_state(bh_in);
+	spin_lock(&jh_in->b_state_lock);
 repeat:
 	/*
 	 * If a new transaction has already done a buffer copy-out, then
@@ -405,13 +405,13 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
 	if (need_copy_out && !done_copy_out) {
 		char *tmp;
 
-		jbd_unlock_bh_state(bh_in);
+		spin_unlock(&jh_in->b_state_lock);
 		tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS);
 		if (!tmp) {
 			brelse(new_bh);
 			return -ENOMEM;
 		}
-		jbd_lock_bh_state(bh_in);
+		spin_lock(&jh_in->b_state_lock);
 		if (jh_in->b_frozen_data) {
 			jbd2_free(tmp, bh_in->b_size);
 			goto repeat;
@@ -464,7 +464,7 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
 	__jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow);
 	spin_unlock(&journal->j_list_lock);
 	set_buffer_shadow(bh_in);
-	jbd_unlock_bh_state(bh_in);
+	spin_unlock(&jh_in->b_state_lock);
 
 	return do_escape | (done_copy_out << 1);
 }
@@ -2410,6 +2410,8 @@ static struct journal_head *journal_alloc_journal_head(void)
 		ret = kmem_cache_zalloc(jbd2_journal_head_cache,
 				GFP_NOFS | __GFP_NOFAIL);
 	}
+	if (ret)
+		spin_lock_init(&ret->b_state_lock);
 	return ret;
 }
 
@@ -2529,17 +2531,23 @@ static void __journal_remove_journal_head(struct buffer_head *bh)
 	J_ASSERT_BH(bh, buffer_jbd(bh));
 	J_ASSERT_BH(bh, jh2bh(jh) == bh);
 	BUFFER_TRACE(bh, "remove journal_head");
-	if (jh->b_frozen_data) {
-		printk(KERN_WARNING "%s: freeing b_frozen_data\n", __func__);
-		jbd2_free(jh->b_frozen_data, bh->b_size);
-	}
-	if (jh->b_committed_data) {
-		printk(KERN_WARNING "%s: freeing b_committed_data\n", __func__);
-		jbd2_free(jh->b_committed_data, bh->b_size);
-	}
+
+	/* Unlink before dropping the lock */
 	bh->b_private = NULL;
 	jh->b_bh = NULL;	/* debug, really */
 	clear_buffer_jbd(bh);
+}
+
+static void journal_release_journal_head(struct journal_head *jh, size_t b_size)
+{
+	if (jh->b_frozen_data) {
+		printk(KERN_WARNING "%s: freeing b_frozen_data\n", __func__);
+		jbd2_free(jh->b_frozen_data, b_size);
+	}
+	if (jh->b_committed_data) {
+		printk(KERN_WARNING "%s: freeing b_committed_data\n", __func__);
+		jbd2_free(jh->b_committed_data, b_size);
+	}
 	journal_free_journal_head(jh);
 }
 
@@ -2557,9 +2565,11 @@ void jbd2_journal_put_journal_head(struct journal_head *jh)
 	if (!jh->b_jcount) {
 		__journal_remove_journal_head(bh);
 		jbd_unlock_bh_journal_head(bh);
+		journal_release_journal_head(jh, bh->b_size);
 		__brelse(bh);
-	} else
+	} else {
 		jbd_unlock_bh_journal_head(bh);
+	}
 }
 
 /*
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index bee8498d77929..7c11afe605320 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -879,7 +879,7 @@ do_get_write_access(handle_t *handle, struct journal_head *jh,
 
  	start_lock = jiffies;
 	lock_buffer(bh);
-	jbd_lock_bh_state(bh);
+	spin_lock(&jh->b_state_lock);
 
 	/* If it takes too long to lock the buffer, trace it */
 	time_lock = jbd2_time_diff(start_lock, jiffies);
@@ -929,7 +929,7 @@ do_get_write_access(handle_t *handle, struct journal_head *jh,
 
 	error = -EROFS;
 	if (is_handle_aborted(handle)) {
-		jbd_unlock_bh_state(bh);
+		spin_unlock(&jh->b_state_lock);
 		goto out;
 	}
 	error = 0;
@@ -993,7 +993,7 @@ do_get_write_access(handle_t *handle, struct journal_head *jh,
 	 */
 	if (buffer_shadow(bh)) {
 		JBUFFER_TRACE(jh, "on shadow: sleep");
-		jbd_unlock_bh_state(bh);
+		spin_unlock(&jh->b_state_lock);
 		wait_on_bit_io(&bh->b_state, BH_Shadow, TASK_UNINTERRUPTIBLE);
 		goto repeat;
 	}
@@ -1014,7 +1014,7 @@ do_get_write_access(handle_t *handle, struct journal_head *jh,
 		JBUFFER_TRACE(jh, "generate frozen data");
 		if (!frozen_buffer) {
 			JBUFFER_TRACE(jh, "allocate memory for buffer");
-			jbd_unlock_bh_state(bh);
+			spin_unlock(&jh->b_state_lock);
 			frozen_buffer = jbd2_alloc(jh2bh(jh)->b_size,
 						   GFP_NOFS | __GFP_NOFAIL);
 			goto repeat;
@@ -1033,7 +1033,7 @@ do_get_write_access(handle_t *handle, struct journal_head *jh,
 	jh->b_next_transaction = transaction;
 
 done:
-	jbd_unlock_bh_state(bh);
+	spin_unlock(&jh->b_state_lock);
 
 	/*
 	 * If we are about to journal a buffer, then any revoke pending on it is
@@ -1172,7 +1172,7 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh)
 	 * that case: the transaction must have deleted the buffer for it to be
 	 * reused here.
 	 */
-	jbd_lock_bh_state(bh);
+	spin_lock(&jh->b_state_lock);
 	J_ASSERT_JH(jh, (jh->b_transaction == transaction ||
 		jh->b_transaction == NULL ||
 		(jh->b_transaction == journal->j_committing_transaction &&
@@ -1207,7 +1207,7 @@ int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh)
 		jh->b_next_transaction = transaction;
 		spin_unlock(&journal->j_list_lock);
 	}
-	jbd_unlock_bh_state(bh);
+	spin_unlock(&jh->b_state_lock);
 
 	/*
 	 * akpm: I added this.  ext3_alloc_branch can pick up new indirect
@@ -1275,13 +1275,13 @@ int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh)
 		committed_data = jbd2_alloc(jh2bh(jh)->b_size,
 					    GFP_NOFS|__GFP_NOFAIL);
 
-	jbd_lock_bh_state(bh);
+	spin_lock(&jh->b_state_lock);
 	if (!jh->b_committed_data) {
 		/* Copy out the current buffer contents into the
 		 * preserved, committed copy. */
 		JBUFFER_TRACE(jh, "generate b_committed data");
 		if (!committed_data) {
-			jbd_unlock_bh_state(bh);
+			spin_unlock(&jh->b_state_lock);
 			goto repeat;
 		}
 
@@ -1289,7 +1289,7 @@ int jbd2_journal_get_undo_access(handle_t *handle, struct buffer_head *bh)
 		committed_data = NULL;
 		memcpy(jh->b_committed_data, bh->b_data, bh->b_size);
 	}
-	jbd_unlock_bh_state(bh);
+	spin_unlock(&jh->b_state_lock);
 out:
 	jbd2_journal_put_journal_head(jh);
 	if (unlikely(committed_data))
@@ -1390,16 +1390,16 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 	 */
 	if (jh->b_transaction != transaction &&
 	    jh->b_next_transaction != transaction) {
-		jbd_lock_bh_state(bh);
+		spin_lock(&jh->b_state_lock);
 		J_ASSERT_JH(jh, jh->b_transaction == transaction ||
 				jh->b_next_transaction == transaction);
-		jbd_unlock_bh_state(bh);
+		spin_unlock(&jh->b_state_lock);
 	}
 	if (jh->b_modified == 1) {
 		/* If it's in our transaction it must be in BJ_Metadata list. */
 		if (jh->b_transaction == transaction &&
 		    jh->b_jlist != BJ_Metadata) {
-			jbd_lock_bh_state(bh);
+			spin_lock(&jh->b_state_lock);
 			if (jh->b_transaction == transaction &&
 			    jh->b_jlist != BJ_Metadata)
 				pr_err("JBD2: assertion failure: h_type=%u "
@@ -1409,13 +1409,13 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 				       jh->b_jlist);
 			J_ASSERT_JH(jh, jh->b_transaction != transaction ||
 					jh->b_jlist == BJ_Metadata);
-			jbd_unlock_bh_state(bh);
+			spin_unlock(&jh->b_state_lock);
 		}
 		goto out;
 	}
 
 	journal = transaction->t_journal;
-	jbd_lock_bh_state(bh);
+	spin_lock(&jh->b_state_lock);
 
 	if (jh->b_modified == 0) {
 		/*
@@ -1501,7 +1501,7 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh)
 	__jbd2_journal_file_buffer(jh, transaction, BJ_Metadata);
 	spin_unlock(&journal->j_list_lock);
 out_unlock_bh:
-	jbd_unlock_bh_state(bh);
+	spin_unlock(&jh->b_state_lock);
 out:
 	JBUFFER_TRACE(jh, "exit");
 	return ret;
@@ -1539,18 +1539,20 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
 
 	BUFFER_TRACE(bh, "entry");
 
-	jbd_lock_bh_state(bh);
+	jh = jbd2_journal_grab_journal_head(bh);
+	if (!jh) {
+		__bforget(bh);
+		return 0;
+	}
 
-	if (!buffer_jbd(bh))
-		goto not_jbd;
-	jh = bh2jh(bh);
+	spin_lock(&jh->b_state_lock);
 
 	/* Critical error: attempting to delete a bitmap buffer, maybe?
 	 * Don't do any jbd operations, and return an error. */
 	if (!J_EXPECT_JH(jh, !jh->b_committed_data,
 			 "inconsistent data on disk")) {
 		err = -EIO;
-		goto not_jbd;
+		goto drop;
 	}
 
 	/* keep track of whether or not this transaction modified us */
@@ -1598,10 +1600,7 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
 			__jbd2_journal_file_buffer(jh, transaction, BJ_Forget);
 		} else {
 			__jbd2_journal_unfile_buffer(jh);
-			if (!buffer_jbd(bh)) {
-				spin_unlock(&journal->j_list_lock);
-				goto not_jbd;
-			}
+			jbd2_journal_put_journal_head(jh);
 		}
 		spin_unlock(&journal->j_list_lock);
 	} else if (jh->b_transaction) {
@@ -1643,7 +1642,7 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
 		if (!jh->b_cp_transaction) {
 			JBUFFER_TRACE(jh, "belongs to none transaction");
 			spin_unlock(&journal->j_list_lock);
-			goto not_jbd;
+			goto drop;
 		}
 
 		/*
@@ -1653,7 +1652,7 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
 		if (!buffer_dirty(bh)) {
 			__jbd2_journal_remove_checkpoint(jh);
 			spin_unlock(&journal->j_list_lock);
-			goto not_jbd;
+			goto drop;
 		}
 
 		/*
@@ -1666,20 +1665,15 @@ int jbd2_journal_forget (handle_t *handle, struct buffer_head *bh)
 		__jbd2_journal_file_buffer(jh, transaction, BJ_Forget);
 		spin_unlock(&journal->j_list_lock);
 	}
-
-	jbd_unlock_bh_state(bh);
-	__brelse(bh);
 drop:
+	__brelse(bh);
+	spin_unlock(&jh->b_state_lock);
+	jbd2_journal_put_journal_head(jh);
 	if (drop_reserve) {
 		/* no need to reserve log space for this block -bzzz */
 		handle->h_buffer_credits++;
 	}
 	return err;
-
-not_jbd:
-	jbd_unlock_bh_state(bh);
-	__bforget(bh);
-	goto drop;
 }
 
 /**
@@ -1878,7 +1872,7 @@ int jbd2_journal_stop(handle_t *handle)
  *
  * j_list_lock is held.
  *
- * jbd_lock_bh_state(jh2bh(jh)) is held.
+ * jh->b_state_lock is held.
  */
 
 static inline void
@@ -1902,7 +1896,7 @@ __blist_add_buffer(struct journal_head **list, struct journal_head *jh)
  *
  * Called with j_list_lock held, and the journal may not be locked.
  *
- * jbd_lock_bh_state(jh2bh(jh)) is held.
+ * jh->b_state_lock is held.
  */
 
 static inline void
@@ -1934,7 +1928,7 @@ static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh)
 	transaction_t *transaction;
 	struct buffer_head *bh = jh2bh(jh);
 
-	J_ASSERT_JH(jh, jbd_is_locked_bh_state(bh));
+	lockdep_assert_held(&jh->b_state_lock);
 	transaction = jh->b_transaction;
 	if (transaction)
 		assert_spin_locked(&transaction->t_journal->j_list_lock);
@@ -1971,17 +1965,15 @@ static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh)
 }
 
 /*
- * Remove buffer from all transactions.
+ * Remove buffer from all transactions. The caller is responsible for dropping
+ * the jh reference that belonged to the transaction.
  *
  * Called with bh_state lock and j_list_lock
- *
- * jh and bh may be already freed when this function returns.
  */
 static void __jbd2_journal_unfile_buffer(struct journal_head *jh)
 {
 	__jbd2_journal_temp_unlink_buffer(jh);
 	jh->b_transaction = NULL;
-	jbd2_journal_put_journal_head(jh);
 }
 
 void jbd2_journal_unfile_buffer(journal_t *journal, struct journal_head *jh)
@@ -1990,18 +1982,19 @@ void jbd2_journal_unfile_buffer(journal_t *journal, struct journal_head *jh)
 
 	/* Get reference so that buffer cannot be freed before we unlock it */
 	get_bh(bh);
-	jbd_lock_bh_state(bh);
+	spin_lock(&jh->b_state_lock);
 	spin_lock(&journal->j_list_lock);
 	__jbd2_journal_unfile_buffer(jh);
 	spin_unlock(&journal->j_list_lock);
-	jbd_unlock_bh_state(bh);
+	spin_unlock(&jh->b_state_lock);
+	jbd2_journal_put_journal_head(jh);
 	__brelse(bh);
 }
 
 /*
  * Called from jbd2_journal_try_to_free_buffers().
  *
- * Called under jbd_lock_bh_state(bh)
+ * Called under jh->b_state_lock
  */
 static void
 __journal_try_to_free_buffer(journal_t *journal, struct buffer_head *bh)
@@ -2088,10 +2081,10 @@ int jbd2_journal_try_to_free_buffers(journal_t *journal,
 		if (!jh)
 			continue;
 
-		jbd_lock_bh_state(bh);
+		spin_lock(&jh->b_state_lock);
 		__journal_try_to_free_buffer(journal, bh);
+		spin_unlock(&jh->b_state_lock);
 		jbd2_journal_put_journal_head(jh);
-		jbd_unlock_bh_state(bh);
 		if (buffer_jbd(bh))
 			goto busy;
 	} while ((bh = bh->b_this_page) != head);
@@ -2112,7 +2105,7 @@ int jbd2_journal_try_to_free_buffers(journal_t *journal,
  *
  * Called under j_list_lock.
  *
- * Called under jbd_lock_bh_state(bh).
+ * Called under jh->b_state_lock.
  */
 static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction)
 {
@@ -2133,6 +2126,7 @@ static int __dispose_buffer(struct journal_head *jh, transaction_t *transaction)
 	} else {
 		JBUFFER_TRACE(jh, "on running transaction");
 		__jbd2_journal_unfile_buffer(jh);
+		jbd2_journal_put_journal_head(jh);
 	}
 	return may_free;
 }
@@ -2199,18 +2193,15 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh,
 	 * holding the page lock. --sct
 	 */
 
-	if (!buffer_jbd(bh))
+	jh = jbd2_journal_grab_journal_head(bh);
+	if (!jh)
 		goto zap_buffer_unlocked;
 
 	/* OK, we have data buffer in journaled mode */
 	write_lock(&journal->j_state_lock);
-	jbd_lock_bh_state(bh);
+	spin_lock(&jh->b_state_lock);
 	spin_lock(&journal->j_list_lock);
 
-	jh = jbd2_journal_grab_journal_head(bh);
-	if (!jh)
-		goto zap_buffer_no_jh;
-
 	/*
 	 * We cannot remove the buffer from checkpoint lists until the
 	 * transaction adding inode to orphan list (let's call it T)
@@ -2289,10 +2280,10 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh,
 		 * for commit and try again.
 		 */
 		if (partial_page) {
-			jbd2_journal_put_journal_head(jh);
 			spin_unlock(&journal->j_list_lock);
-			jbd_unlock_bh_state(bh);
+			spin_unlock(&jh->b_state_lock);
 			write_unlock(&journal->j_state_lock);
+			jbd2_journal_put_journal_head(jh);
 			return -EBUSY;
 		}
 		/*
@@ -2304,10 +2295,10 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh,
 		set_buffer_freed(bh);
 		if (journal->j_running_transaction && buffer_jbddirty(bh))
 			jh->b_next_transaction = journal->j_running_transaction;
-		jbd2_journal_put_journal_head(jh);
 		spin_unlock(&journal->j_list_lock);
-		jbd_unlock_bh_state(bh);
+		spin_unlock(&jh->b_state_lock);
 		write_unlock(&journal->j_state_lock);
+		jbd2_journal_put_journal_head(jh);
 		return 0;
 	} else {
 		/* Good, the buffer belongs to the running transaction.
@@ -2331,11 +2322,10 @@ static int journal_unmap_buffer(journal_t *journal, struct buffer_head *bh,
 	 * here.
 	 */
 	jh->b_modified = 0;
-	jbd2_journal_put_journal_head(jh);
-zap_buffer_no_jh:
 	spin_unlock(&journal->j_list_lock);
-	jbd_unlock_bh_state(bh);
+	spin_unlock(&jh->b_state_lock);
 	write_unlock(&journal->j_state_lock);
+	jbd2_journal_put_journal_head(jh);
 zap_buffer_unlocked:
 	clear_buffer_dirty(bh);
 	J_ASSERT_BH(bh, !buffer_jbddirty(bh));
@@ -2422,7 +2412,7 @@ void __jbd2_journal_file_buffer(struct journal_head *jh,
 	int was_dirty = 0;
 	struct buffer_head *bh = jh2bh(jh);
 
-	J_ASSERT_JH(jh, jbd_is_locked_bh_state(bh));
+	lockdep_assert_held(&jh->b_state_lock);
 	assert_spin_locked(&transaction->t_journal->j_list_lock);
 
 	J_ASSERT_JH(jh, jh->b_jlist < BJ_Types);
@@ -2484,11 +2474,11 @@ void __jbd2_journal_file_buffer(struct journal_head *jh,
 void jbd2_journal_file_buffer(struct journal_head *jh,
 				transaction_t *transaction, int jlist)
 {
-	jbd_lock_bh_state(jh2bh(jh));
+	spin_lock(&jh->b_state_lock);
 	spin_lock(&transaction->t_journal->j_list_lock);
 	__jbd2_journal_file_buffer(jh, transaction, jlist);
 	spin_unlock(&transaction->t_journal->j_list_lock);
-	jbd_unlock_bh_state(jh2bh(jh));
+	spin_unlock(&jh->b_state_lock);
 }
 
 /*
@@ -2498,23 +2488,25 @@ void jbd2_journal_file_buffer(struct journal_head *jh,
  * buffer on that transaction's metadata list.
  *
  * Called under j_list_lock
- * Called under jbd_lock_bh_state(jh2bh(jh))
+ * Called under jh->b_state_lock
  *
- * jh and bh may be already free when this function returns
+ * When this function returns true, there's no next transaction to refile to
+ * and the caller has to drop jh reference through
+ * jbd2_journal_put_journal_head().
  */
-void __jbd2_journal_refile_buffer(struct journal_head *jh)
+bool __jbd2_journal_refile_buffer(struct journal_head *jh)
 {
 	int was_dirty, jlist;
 	struct buffer_head *bh = jh2bh(jh);
 
-	J_ASSERT_JH(jh, jbd_is_locked_bh_state(bh));
+	lockdep_assert_held(&jh->b_state_lock);
 	if (jh->b_transaction)
 		assert_spin_locked(&jh->b_transaction->t_journal->j_list_lock);
 
 	/* If the buffer is now unused, just drop it. */
 	if (jh->b_next_transaction == NULL) {
 		__jbd2_journal_unfile_buffer(jh);
-		return;
+		return true;
 	}
 
 	/*
@@ -2542,6 +2534,7 @@ void __jbd2_journal_refile_buffer(struct journal_head *jh)
 
 	if (was_dirty)
 		set_buffer_jbddirty(bh);
+	return false;
 }
 
 /*
@@ -2552,16 +2545,15 @@ void __jbd2_journal_refile_buffer(struct journal_head *jh)
  */
 void jbd2_journal_refile_buffer(journal_t *journal, struct journal_head *jh)
 {
-	struct buffer_head *bh = jh2bh(jh);
+	bool drop;
 
-	/* Get reference so that buffer cannot be freed before we unlock it */
-	get_bh(bh);
-	jbd_lock_bh_state(bh);
+	spin_lock(&jh->b_state_lock);
 	spin_lock(&journal->j_list_lock);
-	__jbd2_journal_refile_buffer(jh);
-	jbd_unlock_bh_state(bh);
+	drop = __jbd2_journal_refile_buffer(jh);
+	spin_unlock(&jh->b_state_lock);
 	spin_unlock(&journal->j_list_lock);
-	__brelse(bh);
+	if (drop)
+		jbd2_journal_put_journal_head(jh);
 }
 
 /*
diff --git a/fs/namei.c b/fs/namei.c
index 671c3c1a3425b..d9926216e4f15 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1637,7 +1637,7 @@ static struct dentry *__lookup_slow(const struct qstr *name,
 {
 	struct dentry *dentry, *old;
 	struct inode *inode = dir->d_inode;
-	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+	DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
 
 	/* Don't go there if it's already dead */
 	if (unlikely(IS_DEADDIR(inode)))
@@ -3125,7 +3125,7 @@ static int lookup_open(struct nameidata *nd, struct path *path,
 	struct dentry *dentry;
 	int error, create_error = 0;
 	umode_t mode = op->mode;
-	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+	DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
 
 	if (unlikely(IS_DEADDIR(dir_inode)))
 		return -ENOENT;
diff --git a/fs/namespace.c b/fs/namespace.c
index 2adfe7b166a3e..e67f6e405f366 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -14,6 +14,7 @@
 #include <linux/mnt_namespace.h>
 #include <linux/user_namespace.h>
 #include <linux/namei.h>
+#include <linux/delay.h>
 #include <linux/security.h>
 #include <linux/cred.h>
 #include <linux/idr.h>
@@ -321,8 +322,11 @@ int __mnt_want_write(struct vfsmount *m)
 	 * incremented count after it has set MNT_WRITE_HOLD.
 	 */
 	smp_mb();
-	while (READ_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD)
-		cpu_relax();
+	while (READ_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) {
+		preempt_enable();
+		cpu_chill();
+		preempt_disable();
+	}
 	/*
 	 * After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will
 	 * be set to match its requirements. So we must not load that until
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index af549d70ec507..86a72d0d38177 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -162,11 +162,11 @@ static int nfs_delegation_claim_opens(struct inode *inode,
 		sp = state->owner;
 		/* Block nfs4_proc_unlck */
 		mutex_lock(&sp->so_delegreturn_mutex);
-		seq = raw_seqcount_begin(&sp->so_reclaim_seqcount);
+		seq = read_seqbegin(&sp->so_reclaim_seqlock);
 		err = nfs4_open_delegation_recall(ctx, state, stateid);
 		if (!err)
 			err = nfs_delegation_claim_locks(state, stateid);
-		if (!err && read_seqcount_retry(&sp->so_reclaim_seqcount, seq))
+		if (!err && read_seqretry(&sp->so_reclaim_seqlock, seq))
 			err = -EAGAIN;
 		mutex_unlock(&sp->so_delegreturn_mutex);
 		put_nfs_open_context(ctx);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index e180033e35cf1..d30412299573c 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -445,7 +445,7 @@ static
 void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry)
 {
 	struct qstr filename = QSTR_INIT(entry->name, entry->len);
-	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+	DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
 	struct dentry *dentry;
 	struct dentry *alias;
 	struct inode *dir = d_inode(parent);
@@ -1496,7 +1496,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
 		    struct file *file, unsigned open_flags,
 		    umode_t mode)
 {
-	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+	DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
 	struct nfs_open_context *ctx;
 	struct dentry *res;
 	struct iattr attr = { .ia_valid = ATTR_OPEN };
@@ -1825,7 +1825,11 @@ int nfs_rmdir(struct inode *dir, struct dentry *dentry)
 
 	trace_nfs_rmdir_enter(dir, dentry);
 	if (d_really_is_positive(dentry)) {
+#ifdef CONFIG_PREEMPT_RT
+		down(&NFS_I(d_inode(dentry))->rmdir_sem);
+#else
 		down_write(&NFS_I(d_inode(dentry))->rmdir_sem);
+#endif
 		error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name);
 		/* Ensure the VFS deletes this inode */
 		switch (error) {
@@ -1835,7 +1839,11 @@ int nfs_rmdir(struct inode *dir, struct dentry *dentry)
 		case -ENOENT:
 			nfs_dentry_handle_enoent(dentry);
 		}
+#ifdef CONFIG_PREEMPT_RT
+		up(&NFS_I(d_inode(dentry))->rmdir_sem);
+#else
 		up_write(&NFS_I(d_inode(dentry))->rmdir_sem);
+#endif
 	} else
 		error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name);
 	trace_nfs_rmdir_exit(dir, dentry, error);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 2a03bfeec10a4..785e4c4aa8fd6 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -2105,7 +2105,11 @@ static void init_once(void *foo)
 	atomic_long_set(&nfsi->nrequests, 0);
 	atomic_long_set(&nfsi->commit_info.ncommit, 0);
 	atomic_set(&nfsi->commit_info.rpcs_out, 0);
+#ifdef CONFIG_PREEMPT_RT
+	sema_init(&nfsi->rmdir_sem, 1);
+#else
 	init_rwsem(&nfsi->rmdir_sem);
+#endif
 	mutex_init(&nfsi->commit_mutex);
 	nfs4_init_once(nfsi);
 }
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 16b2e5cc3e94a..23b9cf27f4b95 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -115,7 +115,7 @@ struct nfs4_state_owner {
 	unsigned long	     so_flags;
 	struct list_head     so_states;
 	struct nfs_seqid_counter so_seqid;
-	seqcount_t	     so_reclaim_seqcount;
+	seqlock_t	     so_reclaim_seqlock;
 	struct mutex	     so_delegreturn_mutex;
 };
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index caacf5e7f5e15..1e8b05d7155e2 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2956,7 +2956,7 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 	unsigned int seq;
 	int ret;
 
-	seq = raw_seqcount_begin(&sp->so_reclaim_seqcount);
+	seq = raw_seqcount_begin(&sp->so_reclaim_seqlock.seqcount);
 
 	ret = _nfs4_proc_open(opendata, ctx);
 	if (ret != 0)
@@ -2998,7 +2998,7 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 
 	if (d_inode(dentry) == state->inode) {
 		nfs_inode_attach_open_context(ctx);
-		if (read_seqcount_retry(&sp->so_reclaim_seqcount, seq))
+		if (read_seqretry(&sp->so_reclaim_seqlock, seq))
 			nfs4_schedule_stateid_recovery(server, state);
 	}
 
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 0c6d53dc3672a..8ed95c22ead32 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -510,7 +510,7 @@ nfs4_alloc_state_owner(struct nfs_server *server,
 	nfs4_init_seqid_counter(&sp->so_seqid);
 	atomic_set(&sp->so_count, 1);
 	INIT_LIST_HEAD(&sp->so_lru);
-	seqcount_init(&sp->so_reclaim_seqcount);
+	seqlock_init(&sp->so_reclaim_seqlock);
 	mutex_init(&sp->so_delegreturn_mutex);
 	return sp;
 }
@@ -1618,8 +1618,12 @@ static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs
 	 * recovering after a network partition or a reboot from a
 	 * server that doesn't support a grace period.
 	 */
+#ifdef CONFIG_PREEMPT_RT
+	write_seqlock(&sp->so_reclaim_seqlock);
+#else
+	write_seqcount_begin(&sp->so_reclaim_seqlock.seqcount);
+#endif
 	spin_lock(&sp->so_lock);
-	raw_write_seqcount_begin(&sp->so_reclaim_seqcount);
 restart:
 	list_for_each_entry(state, &sp->so_states, open_states) {
 		if (!test_and_clear_bit(ops->state_flag_bit, &state->flags))
@@ -1680,14 +1684,20 @@ static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs
 		spin_lock(&sp->so_lock);
 		goto restart;
 	}
-	raw_write_seqcount_end(&sp->so_reclaim_seqcount);
 	spin_unlock(&sp->so_lock);
+#ifdef CONFIG_PREEMPT_RT
+	write_sequnlock(&sp->so_reclaim_seqlock);
+#else
+	write_seqcount_end(&sp->so_reclaim_seqlock.seqcount);
+#endif
 	return 0;
 out_err:
 	nfs4_put_open_state(state);
-	spin_lock(&sp->so_lock);
-	raw_write_seqcount_end(&sp->so_reclaim_seqcount);
-	spin_unlock(&sp->so_lock);
+#ifdef CONFIG_PREEMPT_RT
+	write_sequnlock(&sp->so_reclaim_seqlock);
+#else
+	write_seqcount_end(&sp->so_reclaim_seqlock.seqcount);
+#endif
 	return status;
 }
 
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 0effeee28352f..efa5adce9b309 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -13,7 +13,7 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/nfs_fs.h>
 #include <linux/sched.h>
-#include <linux/wait.h>
+#include <linux/swait.h>
 #include <linux/namei.h>
 #include <linux/fsnotify.h>
 
@@ -53,6 +53,29 @@ static void nfs_async_unlink_done(struct rpc_task *task, void *calldata)
 		rpc_restart_call_prepare(task);
 }
 
+#ifdef CONFIG_PREEMPT_RT
+static void nfs_down_anon(struct semaphore *sema)
+{
+	down(sema);
+}
+
+static void nfs_up_anon(struct semaphore *sema)
+{
+	up(sema);
+}
+
+#else
+static void nfs_down_anon(struct rw_semaphore *rwsem)
+{
+	down_read_non_owner(rwsem);
+}
+
+static void nfs_up_anon(struct rw_semaphore *rwsem)
+{
+	up_read_non_owner(rwsem);
+}
+#endif
+
 /**
  * nfs_async_unlink_release - Release the sillydelete data.
  * @calldata: struct nfs_unlinkdata to release
@@ -66,7 +89,7 @@ static void nfs_async_unlink_release(void *calldata)
 	struct dentry *dentry = data->dentry;
 	struct super_block *sb = dentry->d_sb;
 
-	up_read_non_owner(&NFS_I(d_inode(dentry->d_parent))->rmdir_sem);
+	nfs_up_anon(&NFS_I(d_inode(dentry->d_parent))->rmdir_sem);
 	d_lookup_done(dentry);
 	nfs_free_unlinkdata(data);
 	dput(dentry);
@@ -119,10 +142,10 @@ static int nfs_call_unlink(struct dentry *dentry, struct inode *inode, struct nf
 	struct inode *dir = d_inode(dentry->d_parent);
 	struct dentry *alias;
 
-	down_read_non_owner(&NFS_I(dir)->rmdir_sem);
+	nfs_down_anon(&NFS_I(dir)->rmdir_sem);
 	alias = d_alloc_parallel(dentry->d_parent, &data->args.name, &data->wq);
 	if (IS_ERR(alias)) {
-		up_read_non_owner(&NFS_I(dir)->rmdir_sem);
+		nfs_up_anon(&NFS_I(dir)->rmdir_sem);
 		return 0;
 	}
 	if (!d_in_lookup(alias)) {
@@ -144,7 +167,7 @@ static int nfs_call_unlink(struct dentry *dentry, struct inode *inode, struct nf
 			ret = 0;
 		spin_unlock(&alias->d_lock);
 		dput(alias);
-		up_read_non_owner(&NFS_I(dir)->rmdir_sem);
+		nfs_up_anon(&NFS_I(dir)->rmdir_sem);
 		/*
 		 * If we'd displaced old cached devname, free it.  At that
 		 * point dentry is definitely not a root, so we won't need
@@ -180,7 +203,7 @@ nfs_async_unlink(struct dentry *dentry, const struct qstr *name)
 
 	data->cred = get_current_cred();
 	data->res.dir_attr = &data->dir_attr;
-	init_waitqueue_head(&data->wq);
+	init_swait_queue_head(&data->wq);
 
 	status = -EBUSY;
 	spin_lock(&dentry->d_lock);
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index 7202a1e39d70c..554b744f41bf8 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -92,8 +92,7 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
 				"0x%llx.", (unsigned long long)bh->b_blocknr);
 	}
 	first = page_buffers(page);
-	local_irq_save(flags);
-	bit_spin_lock(BH_Uptodate_Lock, &first->b_state);
+	spin_lock_irqsave(&first->b_uptodate_lock, flags);
 	clear_buffer_async_read(bh);
 	unlock_buffer(bh);
 	tmp = bh;
@@ -108,8 +107,7 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
 		}
 		tmp = tmp->b_this_page;
 	} while (tmp != bh);
-	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&first->b_uptodate_lock, 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
@@ -142,8 +140,7 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
 	unlock_page(page);
 	return;
 still_busy:
-	bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
 	return;
 }
 
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index 69c21a3843af8..4180c3ef0a68c 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -1252,6 +1252,7 @@ static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh,
 					 int nr)
 {
 	struct ocfs2_group_desc *bg = (struct ocfs2_group_desc *) bg_bh->b_data;
+	struct journal_head *jh;
 	int ret;
 
 	if (ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap))
@@ -1260,13 +1261,14 @@ static int ocfs2_test_bg_bit_allocatable(struct buffer_head *bg_bh,
 	if (!buffer_jbd(bg_bh))
 		return 1;
 
-	jbd_lock_bh_state(bg_bh);
-	bg = (struct ocfs2_group_desc *) bh2jh(bg_bh)->b_committed_data;
+	jh = bh2jh(bg_bh);
+	spin_lock(&jh->b_state_lock);
+	bg = (struct ocfs2_group_desc *) jh->b_committed_data;
 	if (bg)
 		ret = !ocfs2_test_bit(nr, (unsigned long *)bg->bg_bitmap);
 	else
 		ret = 1;
-	jbd_unlock_bh_state(bg_bh);
+	spin_unlock(&jh->b_state_lock);
 
 	return ret;
 }
@@ -2387,6 +2389,7 @@ static int ocfs2_block_group_clear_bits(handle_t *handle,
 	int status;
 	unsigned int tmp;
 	struct ocfs2_group_desc *undo_bg = NULL;
+	struct journal_head *jh;
 
 	/* The caller got this descriptor from
 	 * ocfs2_read_group_descriptor().  Any corruption is a code bug. */
@@ -2405,10 +2408,10 @@ static int ocfs2_block_group_clear_bits(handle_t *handle,
 		goto bail;
 	}
 
+	jh = bh2jh(group_bh);
 	if (undo_fn) {
-		jbd_lock_bh_state(group_bh);
-		undo_bg = (struct ocfs2_group_desc *)
-					bh2jh(group_bh)->b_committed_data;
+		spin_lock(&jh->b_state_lock);
+		undo_bg = (struct ocfs2_group_desc *) jh->b_committed_data;
 		BUG_ON(!undo_bg);
 	}
 
@@ -2423,7 +2426,7 @@ static int ocfs2_block_group_clear_bits(handle_t *handle,
 	le16_add_cpu(&bg->bg_free_bits_count, num_bits);
 	if (le16_to_cpu(bg->bg_free_bits_count) > le16_to_cpu(bg->bg_bits)) {
 		if (undo_fn)
-			jbd_unlock_bh_state(group_bh);
+			spin_unlock(&jh->b_state_lock);
 		return ocfs2_error(alloc_inode->i_sb, "Group descriptor # %llu has bit count %u but claims %u are freed. num_bits %d\n",
 				   (unsigned long long)le64_to_cpu(bg->bg_blkno),
 				   le16_to_cpu(bg->bg_bits),
@@ -2432,7 +2435,7 @@ static int ocfs2_block_group_clear_bits(handle_t *handle,
 	}
 
 	if (undo_fn)
-		jbd_unlock_bh_state(group_bh);
+		spin_unlock(&jh->b_state_lock);
 
 	ocfs2_journal_dirty(handle, group_bh);
 bail:
diff --git a/fs/proc/base.c b/fs/proc/base.c
index ebea9501afb84..2dcd8fb3abb58 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1891,7 +1891,7 @@ bool proc_fill_cache(struct file *file, struct dir_context *ctx,
 
 	child = d_hash_and_lookup(dir, &qname);
 	if (!child) {
-		DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+		DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
 		child = d_alloc_parallel(dir, &qname, &wq);
 		if (IS_ERR(child))
 			goto end_instantiate;
diff --git a/fs/proc/kmsg.c b/fs/proc/kmsg.c
index 4f4a2abb225eb..4e62963a87ca8 100644
--- a/fs/proc/kmsg.c
+++ b/fs/proc/kmsg.c
@@ -18,8 +18,6 @@
 #include <linux/uaccess.h>
 #include <asm/io.h>
 
-extern wait_queue_head_t log_wait;
-
 static int kmsg_open(struct inode * inode, struct file * file)
 {
 	return do_syslog(SYSLOG_ACTION_OPEN, NULL, 0, SYSLOG_FROM_PROC);
@@ -42,7 +40,7 @@ static ssize_t kmsg_read(struct file *file, char __user *buf,
 
 static __poll_t kmsg_poll(struct file *file, poll_table *wait)
 {
-	poll_wait(file, &log_wait, wait);
+	poll_wait(file, printk_wait_queue(), wait);
 	if (do_syslog(SYSLOG_ACTION_SIZE_UNREAD, NULL, 0, SYSLOG_FROM_PROC))
 		return EPOLLIN | EPOLLRDNORM;
 	return 0;
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index d80989b6c3448..b5921f996e86d 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -702,7 +702,7 @@ static bool proc_sys_fill_cache(struct file *file,
 
 	child = d_lookup(dir, &qname);
 	if (!child) {
-		DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+		DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
 		child = d_alloc_parallel(dir, &qname, &wq);
 		if (IS_ERR(child))
 			return false;
diff --git a/fs/squashfs/decompressor_multi_percpu.c b/fs/squashfs/decompressor_multi_percpu.c
index 2a2a2d106440e..f8dd256763284 100644
--- a/fs/squashfs/decompressor_multi_percpu.c
+++ b/fs/squashfs/decompressor_multi_percpu.c
@@ -8,6 +8,7 @@
 #include <linux/slab.h>
 #include <linux/percpu.h>
 #include <linux/buffer_head.h>
+#include <linux/locallock.h>
 
 #include "squashfs_fs.h"
 #include "squashfs_fs_sb.h"
@@ -23,6 +24,8 @@ struct squashfs_stream {
 	void		*stream;
 };
 
+static DEFINE_LOCAL_IRQ_LOCK(stream_lock);
+
 void *squashfs_decompressor_create(struct squashfs_sb_info *msblk,
 						void *comp_opts)
 {
@@ -77,10 +80,15 @@ int squashfs_decompress(struct squashfs_sb_info *msblk, struct buffer_head **bh,
 {
 	struct squashfs_stream __percpu *percpu =
 			(struct squashfs_stream __percpu *) msblk->stream;
-	struct squashfs_stream *stream = get_cpu_ptr(percpu);
-	int res = msblk->decompressor->decompress(msblk, stream->stream, bh, b,
-		offset, length, output);
-	put_cpu_ptr(stream);
+	struct squashfs_stream *stream;
+	int res;
+
+	stream = get_locked_ptr(stream_lock, percpu);
+
+	res = msblk->decompressor->decompress(msblk, stream->stream, bh, b,
+			offset, length, output);
+
+	put_locked_ptr(stream_lock, stream);
 
 	if (res < 0)
 		ERROR("%s decompression failed, data probably corrupt\n",
diff --git a/fs/stack.c b/fs/stack.c
index 4ef2c056269d5..c9830924eb125 100644
--- a/fs/stack.c
+++ b/fs/stack.c
@@ -23,7 +23,7 @@ void fsstack_copy_inode_size(struct inode *dst, struct inode *src)
 
 	/*
 	 * But on 32-bit, we ought to make an effort to keep the two halves of
-	 * i_blocks in sync despite SMP or PREEMPT - though stat's
+	 * i_blocks in sync despite SMP or PREEMPTION - though stat's
 	 * generic_fillattr() doesn't bother, and we won't be applying quotas
 	 * (where i_blocks does become important) at the upper level.
 	 *
@@ -38,14 +38,14 @@ void fsstack_copy_inode_size(struct inode *dst, struct inode *src)
 		spin_unlock(&src->i_lock);
 
 	/*
-	 * If CONFIG_SMP or CONFIG_PREEMPT on 32-bit, it's vital for
+	 * If CONFIG_SMP or CONFIG_PREEMPTION on 32-bit, it's vital for
 	 * fsstack_copy_inode_size() to hold some lock around
 	 * i_size_write(), otherwise i_size_read() may spin forever (see
 	 * include/linux/fs.h).  We don't necessarily hold i_mutex when this
 	 * is called, so take i_lock for that case.
 	 *
 	 * And if on 32-bit, continue our effort to keep the two halves of
-	 * i_blocks in sync despite SMP or PREEMPT: use i_lock  for that case
+	 * i_blocks in sync despite SMP or PREEMPTION: use i_lock for that case
 	 * too, and do both at once by combining the tests.
 	 *
 	 * There is none of this locking overhead in the 64-bit case.
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index f9fd18670e22d..92871bee05b39 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -61,7 +61,7 @@ struct userfaultfd_ctx {
 	/* waitqueue head for events */
 	wait_queue_head_t event_wqh;
 	/* a refile sequence protected by fault_pending_wqh lock */
-	struct seqcount refile_seq;
+	seqlock_t refile_seq;
 	/* pseudo fd refcounting */
 	refcount_t refcount;
 	/* userfaultfd syscall flags */
@@ -1063,7 +1063,7 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
 			 * waitqueue could become empty if this is the
 			 * only userfault.
 			 */
-			write_seqcount_begin(&ctx->refile_seq);
+			write_seqlock(&ctx->refile_seq);
 
 			/*
 			 * The fault_pending_wqh.lock prevents the uwq
@@ -1089,7 +1089,7 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
 			list_del(&uwq->wq.entry);
 			add_wait_queue(&ctx->fault_wqh, &uwq->wq);
 
-			write_seqcount_end(&ctx->refile_seq);
+			write_sequnlock(&ctx->refile_seq);
 
 			/* careful to always initialize msg if ret == 0 */
 			*msg = uwq->msg;
@@ -1262,11 +1262,11 @@ static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx,
 	 * sure we've userfaults to wake.
 	 */
 	do {
-		seq = read_seqcount_begin(&ctx->refile_seq);
+		seq = read_seqbegin(&ctx->refile_seq);
 		need_wakeup = waitqueue_active(&ctx->fault_pending_wqh) ||
 			waitqueue_active(&ctx->fault_wqh);
 		cond_resched();
-	} while (read_seqcount_retry(&ctx->refile_seq, seq));
+	} while (read_seqretry(&ctx->refile_seq, seq));
 	if (need_wakeup)
 		__wake_userfault(ctx, range);
 }
@@ -1935,7 +1935,7 @@ static void init_once_userfaultfd_ctx(void *mem)
 	init_waitqueue_head(&ctx->fault_wqh);
 	init_waitqueue_head(&ctx->event_wqh);
 	init_waitqueue_head(&ctx->fd_wqh);
-	seqcount_init(&ctx->refile_seq);
+	seqlock_init(&ctx->refile_seq);
 }
 
 SYSCALL_DEFINE1(userfaultfd, int, flags)
diff --git a/include/Kbuild b/include/Kbuild
index ffba79483cc5e..95b4105a6186f 100644
--- a/include/Kbuild
+++ b/include/Kbuild
@@ -1158,8 +1158,15 @@ header-test-			+= xen/xenbus.h
 # Do not include directly
 header-test- += linux/compiler-clang.h
 header-test- += linux/compiler-gcc.h
+header-test- += linux/mutex_rt.h
 header-test- += linux/patchkey.h
 header-test- += linux/rwlock_api_smp.h
+header-test- += linux/rwlock_rt.h
+header-test- += linux/rwlock_types_rt.h
+header-test- += linux/rwsem-rt.h
+header-test- += linux/spinlock_rt.h
+header-test- += linux/spinlock_types_nort.h
+header-test- += linux/spinlock_types_rt.h
 header-test- += linux/spinlock_types_up.h
 header-test- += linux/spinlock_up.h
 header-test- += linux/wimax/debug.h
diff --git a/include/linux/bottom_half.h b/include/linux/bottom_half.h
index a19519f4241dc..ef2366a65ba2a 100644
--- a/include/linux/bottom_half.h
+++ b/include/linux/bottom_half.h
@@ -4,6 +4,10 @@
 
 #include <linux/preempt.h>
 
+#ifdef CONFIG_PREEMPT_RT
+extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt);
+#else
+
 #ifdef CONFIG_TRACE_IRQFLAGS
 extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt);
 #else
@@ -13,6 +17,7 @@ static __always_inline void __local_bh_disable_ip(unsigned long ip, unsigned int
 	barrier();
 }
 #endif
+#endif
 
 static inline void local_bh_disable(void)
 {
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 7b73ef7f902d4..e0b020eaf32e2 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -22,9 +22,6 @@ enum bh_state_bits {
 	BH_Dirty,	/* Is dirty */
 	BH_Lock,	/* Is locked */
 	BH_Req,		/* Has been submitted for I/O */
-	BH_Uptodate_Lock,/* Used by the first bh in a page, to serialise
-			  * IO completion of other buffers in the page
-			  */
 
 	BH_Mapped,	/* Has a disk mapping */
 	BH_New,		/* Disk mapping was newly created by get_block */
@@ -76,6 +73,9 @@ struct buffer_head {
 	struct address_space *b_assoc_map;	/* mapping this buffer is
 						   associated with */
 	atomic_t b_count;		/* users using this buffer_head */
+	spinlock_t b_uptodate_lock;	/* Used by the first bh in a page, to
+					 * serialise IO completion of other
+					 * buffers in the page */
 };
 
 /*
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 430e219e3abaf..5708205542bf8 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -144,9 +144,6 @@ struct cgroup_subsys_state {
 	struct list_head sibling;
 	struct list_head children;
 
-	/* flush target list anchored at cgrp->rstat_css_list */
-	struct list_head rstat_css_node;
-
 	/*
 	 * PI: Subsys-unique ID.  0 is unused and root is always 1.  The
 	 * matching css can be looked up using css_from_id().
@@ -455,7 +452,6 @@ struct cgroup {
 
 	/* per-cpu recursive resource statistics */
 	struct cgroup_rstat_cpu __percpu *rstat_cpu;
-	struct list_head rstat_css_list;
 
 	/* cgroup basic resource statistics */
 	struct cgroup_base_stat pending_bstat;	/* pending from children */
@@ -633,7 +629,6 @@ struct cgroup_subsys {
 	void (*css_released)(struct cgroup_subsys_state *css);
 	void (*css_free)(struct cgroup_subsys_state *css);
 	void (*css_reset)(struct cgroup_subsys_state *css);
-	void (*css_rstat_flush)(struct cgroup_subsys_state *css, int cpu);
 	int (*css_extra_stat_show)(struct seq_file *seq,
 				   struct cgroup_subsys_state *css);
 
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 3ba3e6da13a6f..affa3798c9f52 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -750,9 +750,6 @@ static inline void cgroup_path_from_kernfs_id(const union kernfs_node_id *id,
  */
 void cgroup_rstat_updated(struct cgroup *cgrp, int cpu);
 void cgroup_rstat_flush(struct cgroup *cgrp);
-void cgroup_rstat_flush_irqsafe(struct cgroup *cgrp);
-void cgroup_rstat_flush_hold(struct cgroup *cgrp);
-void cgroup_rstat_flush_release(void);
 
 /*
  * Basic resource stats.
diff --git a/include/linux/completion.h b/include/linux/completion.h
index 519e94915d185..bf8e77001f18f 100644
--- a/include/linux/completion.h
+++ b/include/linux/completion.h
@@ -9,7 +9,7 @@
  * See kernel/sched/completion.c for details.
  */
 
-#include <linux/wait.h>
+#include <linux/swait.h>
 
 /*
  * struct completion - structure used to maintain state for a "completion"
@@ -25,7 +25,7 @@
  */
 struct completion {
 	unsigned int done;
-	wait_queue_head_t wait;
+	struct swait_queue_head wait;
 };
 
 #define init_completion_map(x, m) __init_completion(x)
@@ -34,7 +34,7 @@ static inline void complete_acquire(struct completion *x) {}
 static inline void complete_release(struct completion *x) {}
 
 #define COMPLETION_INITIALIZER(work) \
-	{ 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) }
+	{ 0, __SWAIT_QUEUE_HEAD_INITIALIZER((work).wait) }
 
 #define COMPLETION_INITIALIZER_ONSTACK_MAP(work, map) \
 	(*({ init_completion_map(&(work), &(map)); &(work); }))
@@ -85,7 +85,7 @@ static inline void complete_release(struct completion *x) {}
 static inline void __init_completion(struct completion *x)
 {
 	x->done = 0;
-	init_waitqueue_head(&x->wait);
+	init_swait_queue_head(&x->wait);
 }
 
 /**
diff --git a/include/linux/console.h b/include/linux/console.h
index d09951d5a94e4..39d1bb43b4f25 100644
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -145,6 +145,7 @@ static inline int con_debug_leave(void)
 struct console {
 	char	name[16];
 	void	(*write)(struct console *, const char *, unsigned);
+	void	(*write_atomic)(struct console *, const char *, unsigned);
 	int	(*read)(struct console *, char *, unsigned);
 	struct tty_driver *(*device)(struct console *, int *);
 	void	(*unblank)(void);
@@ -153,6 +154,8 @@ struct console {
 	short	flags;
 	short	index;
 	int	cflag;
+	unsigned long printk_seq;
+	int	wrote_history;
 	void	*data;
 	struct	 console *next;
 };
@@ -234,4 +237,7 @@ extern void console_init(void);
 void dummycon_register_output_notifier(struct notifier_block *nb);
 void dummycon_unregister_output_notifier(struct notifier_block *nb);
 
+extern void console_atomic_lock(unsigned int *flags);
+extern void console_atomic_unlock(unsigned int flags);
+
 #endif /* _LINUX_CONSOLE_H */
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 10090f11ab954..ac021d808c71d 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -106,7 +106,7 @@ struct dentry {
 
 	union {
 		struct list_head d_lru;		/* LRU list */
-		wait_queue_head_t *d_wait;	/* in-lookup ones only */
+		struct swait_queue_head *d_wait;	/* in-lookup ones only */
 	};
 	struct list_head d_child;	/* child of parent list */
 	struct list_head d_subdirs;	/* our children */
@@ -236,7 +236,7 @@ extern void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op
 extern struct dentry * d_alloc(struct dentry *, const struct qstr *);
 extern struct dentry * d_alloc_anon(struct super_block *);
 extern struct dentry * d_alloc_parallel(struct dentry *, const struct qstr *,
-					wait_queue_head_t *);
+					struct swait_queue_head *);
 extern struct dentry * d_splice_alias(struct inode *, struct dentry *);
 extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *);
 extern struct dentry * d_exact_alias(struct dentry *, struct inode *);
diff --git a/include/linux/delay.h b/include/linux/delay.h
index 8e6828094c1ee..7f2df975a53e2 100644
--- a/include/linux/delay.h
+++ b/include/linux/delay.h
@@ -65,4 +65,10 @@ static inline void ssleep(unsigned int seconds)
 	msleep(seconds * 1000);
 }
 
+#ifdef CONFIG_PREEMPT_RT
+extern void cpu_chill(void);
+#else
+# define cpu_chill()	cpu_relax()
+#endif
+
 #endif /* defined(_LINUX_DELAY_H) */
diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h
index ee50d10f052b5..81272ca122ee5 100644
--- a/include/linux/dma-resv.h
+++ b/include/linux/dma-resv.h
@@ -65,13 +65,13 @@ struct dma_resv_list {
 /**
  * struct dma_resv - a reservation object manages fences for a buffer
  * @lock: update side lock
- * @seq: sequence count for managing RCU read-side synchronization
+ * @seq: sequence lock for managing RCU read-side synchronization
  * @fence_excl: the exclusive fence, if there is one currently
  * @fence: list of current shared fences
  */
 struct dma_resv {
 	struct ww_mutex lock;
-	seqcount_t seq;
+	seqlock_t seq;
 
 	struct dma_fence __rcu *fence_excl;
 	struct dma_resv_list __rcu *fence;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0b4d8fc79e0f3..ab03c913559c3 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -716,7 +716,7 @@ struct inode {
 		struct block_device	*i_bdev;
 		struct cdev		*i_cdev;
 		char			*i_link;
-		unsigned		i_dir_seq;
+		unsigned		__i_dir_seq;
 	};
 
 	__u32			i_generation;
@@ -855,7 +855,7 @@ static inline loff_t i_size_read(const struct inode *inode)
 		i_size = inode->i_size;
 	} while (read_seqcount_retry(&inode->i_size_seqcount, seq));
 	return i_size;
-#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
+#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
 	loff_t i_size;
 
 	preempt_disable();
@@ -880,7 +880,7 @@ static inline void i_size_write(struct inode *inode, loff_t i_size)
 	inode->i_size = i_size;
 	write_seqcount_end(&inode->i_size_seqcount);
 	preempt_enable();
-#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
+#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
 	preempt_disable();
 	inode->i_size = i_size;
 	preempt_enable();
diff --git a/include/linux/fscache.h b/include/linux/fscache.h
index ad044c0cb1f3b..164bfe4d207d0 100644
--- a/include/linux/fscache.h
+++ b/include/linux/fscache.h
@@ -226,6 +226,7 @@ extern void __fscache_readpages_cancel(struct fscache_cookie *cookie,
 extern void __fscache_disable_cookie(struct fscache_cookie *, const void *, bool);
 extern void __fscache_enable_cookie(struct fscache_cookie *, const void *, loff_t,
 				    bool (*)(void *), void *);
+extern void fscache_cookie_init(void);
 
 /**
  * fscache_register_netfs - Register a filesystem as desiring caching services
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 8b5330dd5ac09..c1583357e9cd4 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -717,7 +717,7 @@ static inline void hd_free_part(struct hd_struct *part)
  * accessor function.
  *
  * Code written along the lines of i_size_read() and i_size_write().
- * CONFIG_PREEMPT case optimizes the case of UP kernel with preemption
+ * CONFIG_PREEMPTION case optimizes the case of UP kernel with preemption
  * on.
  */
 static inline sector_t part_nr_sects_read(struct hd_struct *part)
@@ -730,7 +730,7 @@ static inline sector_t part_nr_sects_read(struct hd_struct *part)
 		nr_sects = part->nr_sects;
 	} while (read_seqcount_retry(&part->nr_sects_seq, seq));
 	return nr_sects;
-#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
+#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
 	sector_t nr_sects;
 
 	preempt_disable();
@@ -753,7 +753,7 @@ static inline void part_nr_sects_write(struct hd_struct *part, sector_t size)
 	write_seqcount_begin(&part->nr_sects_seq);
 	part->nr_sects = size;
 	write_seqcount_end(&part->nr_sects_seq);
-#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT)
+#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
 	preempt_disable();
 	part->nr_sects = size;
 	preempt_enable();
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 61f2f6ff94673..6ce61770ef343 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -580,6 +580,7 @@ extern void page_frag_free(void *addr);
 void page_alloc_init(void);
 void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp);
 void drain_all_pages(struct zone *zone);
+void drain_cpu_pages(unsigned int cpu, struct zone *zone);
 void drain_local_pages(struct zone *zone);
 
 void page_alloc_init_late(void);
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index da0af631ded5b..8d7bb3c0ff061 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -68,7 +68,6 @@ extern void irq_exit(void);
 #define nmi_enter()						\
 	do {							\
 		arch_nmi_enter();				\
-		printk_nmi_enter();				\
 		lockdep_off();					\
 		ftrace_nmi_enter();				\
 		BUG_ON(in_nmi());				\
@@ -85,7 +84,6 @@ extern void irq_exit(void);
 		preempt_count_sub(NMI_OFFSET + HARDIRQ_OFFSET);	\
 		ftrace_nmi_exit();				\
 		lockdep_on();					\
-		printk_nmi_exit();				\
 		arch_nmi_exit();				\
 	} while (0)
 
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index ea5cdbd8c2c32..4191b158c66a0 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -8,6 +8,7 @@
 #include <linux/mm.h>
 #include <linux/uaccess.h>
 #include <linux/hardirq.h>
+#include <linux/sched.h>
 
 #include <asm/cacheflush.h>
 
@@ -90,7 +91,7 @@ static inline void kunmap(struct page *page)
 
 static inline void *kmap_atomic(struct page *page)
 {
-	preempt_disable();
+	preempt_disable_nort();
 	pagefault_disable();
 	return page_address(page);
 }
@@ -99,7 +100,7 @@ static inline void *kmap_atomic(struct page *page)
 static inline void __kunmap_atomic(void *addr)
 {
 	pagefault_enable();
-	preempt_enable();
+	preempt_enable_nort();
 }
 
 #define kmap_atomic_pfn(pfn)	kmap_atomic(pfn_to_page(pfn))
@@ -111,32 +112,51 @@ static inline void __kunmap_atomic(void *addr)
 
 #if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32)
 
+#ifndef CONFIG_PREEMPT_RT
 DECLARE_PER_CPU(int, __kmap_atomic_idx);
+#endif
 
 static inline int kmap_atomic_idx_push(void)
 {
+#ifndef CONFIG_PREEMPT_RT
 	int idx = __this_cpu_inc_return(__kmap_atomic_idx) - 1;
 
-#ifdef CONFIG_DEBUG_HIGHMEM
+# ifdef CONFIG_DEBUG_HIGHMEM
 	WARN_ON_ONCE(in_irq() && !irqs_disabled());
 	BUG_ON(idx >= KM_TYPE_NR);
-#endif
+# endif
 	return idx;
+#else
+	current->kmap_idx++;
+	BUG_ON(current->kmap_idx > KM_TYPE_NR);
+	return current->kmap_idx - 1;
+#endif
 }
 
 static inline int kmap_atomic_idx(void)
 {
+#ifndef CONFIG_PREEMPT_RT
 	return __this_cpu_read(__kmap_atomic_idx) - 1;
+#else
+	return current->kmap_idx - 1;
+#endif
 }
 
 static inline void kmap_atomic_idx_pop(void)
 {
-#ifdef CONFIG_DEBUG_HIGHMEM
+#ifndef CONFIG_PREEMPT_RT
+# ifdef CONFIG_DEBUG_HIGHMEM
 	int idx = __this_cpu_dec_return(__kmap_atomic_idx);
 
 	BUG_ON(idx < 0);
-#else
+# else
 	__this_cpu_dec(__kmap_atomic_idx);
+# endif
+#else
+	current->kmap_idx--;
+# ifdef CONFIG_DEBUG_HIGHMEM
+	BUG_ON(current->kmap_idx < 0);
+# endif
 #endif
 }
 
diff --git a/include/linux/idr.h b/include/linux/idr.h
index ac6e946b6767b..839da8f2f6f13 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -169,10 +169,7 @@ static inline bool idr_is_empty(const struct idr *idr)
  * Each idr_preload() should be matched with an invocation of this
  * function.  See idr_preload() for details.
  */
-static inline void idr_preload_end(void)
-{
-	preempt_enable();
-}
+void idr_preload_end(void);
 
 /**
  * idr_for_each_entry() - Iterate over an IDR's elements of a given type.
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 89fc59dab57d2..029042f474c69 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -546,7 +546,7 @@ struct softirq_action
 asmlinkage void do_softirq(void);
 asmlinkage void __do_softirq(void);
 
-#ifdef __ARCH_HAS_DO_SOFTIRQ
+#if defined(__ARCH_HAS_DO_SOFTIRQ) && !defined(CONFIG_PREEMPT_RT)
 void do_softirq_own_stack(void);
 #else
 static inline void do_softirq_own_stack(void)
@@ -561,6 +561,7 @@ extern void __raise_softirq_irqoff(unsigned int nr);
 
 extern void raise_softirq_irqoff(unsigned int nr);
 extern void raise_softirq(unsigned int nr);
+extern void softirq_check_pending_idle(void);
 
 DECLARE_PER_CPU(struct task_struct *, ksoftirqd);
 
@@ -625,7 +626,10 @@ static inline void tasklet_unlock(struct tasklet_struct *t)
 
 static inline void tasklet_unlock_wait(struct tasklet_struct *t)
 {
-	while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { barrier(); }
+	while (test_bit(TASKLET_STATE_RUN, &(t)->state)) {
+		local_bh_disable();
+		local_bh_enable();
+	}
 }
 #else
 #define tasklet_trylock(t) 1
diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h
index b11fcdfd07707..2964f4526f79e 100644
--- a/include/linux/irq_work.h
+++ b/include/linux/irq_work.h
@@ -18,6 +18,8 @@
 
 /* Doesn't want IPI, wait for tick: */
 #define IRQ_WORK_LAZY		BIT(2)
+/* Run hard IRQ context, even on RT */
+#define IRQ_WORK_HARD_IRQ	BIT(3)
 
 #define IRQ_WORK_CLAIMED	(IRQ_WORK_PENDING | IRQ_WORK_BUSY)
 
@@ -52,4 +54,10 @@ static inline bool irq_work_needs_cpu(void) { return false; }
 static inline void irq_work_run(void) { }
 #endif
 
+#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT)
+void irq_work_tick_soft(void);
+#else
+static inline void irq_work_tick_soft(void) { }
+#endif
+
 #endif /* _LINUX_IRQ_WORK_H */
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index d6e2ab538ef27..1e7fc375c36da 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -72,6 +72,7 @@ struct irq_desc {
 	unsigned int		irqs_unhandled;
 	atomic_t		threads_handled;
 	int			threads_handled_last;
+	u64			random_ip;
 	raw_spinlock_t		lock;
 	struct cpumask		*percpu_enabled;
 	const struct cpumask	*percpu_affinity;
diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
index 21619c92c3770..5304de2f78386 100644
--- a/include/linux/irqflags.h
+++ b/include/linux/irqflags.h
@@ -43,14 +43,6 @@ do {						\
 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)
 #else
 # define trace_hardirqs_on()		do { } while (0)
 # define trace_hardirqs_off()		do { } while (0)
@@ -64,6 +56,21 @@ do {						\
 # define lockdep_softirq_exit()		do { } while (0)
 #endif
 
+#if defined(CONFIG_TRACE_IRQFLAGS) && !defined(CONFIG_PREEMPT_RT)
+# 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)
+#endif
+
 #if defined(CONFIG_IRQSOFF_TRACER) || \
 	defined(CONFIG_PREEMPT_TRACER)
  extern void stop_critical_timings(void);
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 10e6049c0ba91..b56dbe515ad73 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -313,7 +313,6 @@ enum jbd_state_bits {
 	BH_Revoked,		/* Has been revoked from the log */
 	BH_RevokeValid,		/* Revoked flag is valid */
 	BH_JBDDirty,		/* Is dirty but journaled */
-	BH_State,		/* Pins most journal_head state */
 	BH_JournalHead,		/* Pins bh->b_private and jh->b_bh */
 	BH_Shadow,		/* IO on shadow buffer is running */
 	BH_Verified,		/* Metadata block has been verified ok */
@@ -342,26 +341,6 @@ static inline struct journal_head *bh2jh(struct buffer_head *bh)
 	return bh->b_private;
 }
 
-static inline void jbd_lock_bh_state(struct buffer_head *bh)
-{
-	bit_spin_lock(BH_State, &bh->b_state);
-}
-
-static inline int jbd_trylock_bh_state(struct buffer_head *bh)
-{
-	return bit_spin_trylock(BH_State, &bh->b_state);
-}
-
-static inline int jbd_is_locked_bh_state(struct buffer_head *bh)
-{
-	return bit_spin_is_locked(BH_State, &bh->b_state);
-}
-
-static inline void jbd_unlock_bh_state(struct buffer_head *bh)
-{
-	bit_spin_unlock(BH_State, &bh->b_state);
-}
-
 static inline void jbd_lock_bh_journal_head(struct buffer_head *bh)
 {
 	bit_spin_lock(BH_JournalHead, &bh->b_state);
@@ -556,9 +535,9 @@ struct transaction_chp_stats_s {
  *      ->jbd_lock_bh_journal_head()	(This is "innermost")
  *
  *    j_state_lock
- *    ->jbd_lock_bh_state()
+ *    ->b_state_lock
  *
- *    jbd_lock_bh_state()
+ *    b_state_lock
  *    ->j_list_lock
  *
  *    j_state_lock
@@ -1257,7 +1236,7 @@ JBD2_FEATURE_INCOMPAT_FUNCS(csum3,		CSUM_V3)
 
 /* Filing buffers */
 extern void jbd2_journal_unfile_buffer(journal_t *, struct journal_head *);
-extern void __jbd2_journal_refile_buffer(struct journal_head *);
+extern bool __jbd2_journal_refile_buffer(struct journal_head *);
 extern void jbd2_journal_refile_buffer(journal_t *, struct journal_head *);
 extern void __jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int);
 extern void __journal_free_buffer(struct journal_head *bh);
diff --git a/include/linux/journal-head.h b/include/linux/journal-head.h
index 9fb8705243145..75bc56109031f 100644
--- a/include/linux/journal-head.h
+++ b/include/linux/journal-head.h
@@ -11,6 +11,8 @@
 #ifndef JOURNAL_HEAD_H_INCLUDED
 #define JOURNAL_HEAD_H_INCLUDED
 
+#include <linux/spinlock.h>
+
 typedef unsigned int		tid_t;		/* Unique transaction ID */
 typedef struct transaction_s	transaction_t;	/* Compound transaction type */
 
@@ -23,6 +25,11 @@ struct journal_head {
 	 */
 	struct buffer_head *b_bh;
 
+	/*
+	 * Protect the buffer head state
+	 */
+	spinlock_t b_state_lock;
+
 	/*
 	 * Reference count - see description in journal.c
 	 * [jbd_lock_bh_journal_head()]
@@ -30,7 +37,7 @@ struct journal_head {
 	int b_jcount;
 
 	/*
-	 * Journalling list for this buffer [jbd_lock_bh_state()]
+	 * Journalling list for this buffer [b_state_lock]
 	 * NOTE: We *cannot* combine this with b_modified into a bitfield
 	 * as gcc would then (which the C standard allows but which is
 	 * very unuseful) make 64-bit accesses to the bitfield and clobber
@@ -41,20 +48,20 @@ struct journal_head {
 	/*
 	 * This flag signals the buffer has been modified by
 	 * the currently running transaction
-	 * [jbd_lock_bh_state()]
+	 * [b_state_lock]
 	 */
 	unsigned b_modified;
 
 	/*
 	 * Copy of the buffer data frozen for writing to the log.
-	 * [jbd_lock_bh_state()]
+	 * [b_state_lock]
 	 */
 	char *b_frozen_data;
 
 	/*
 	 * Pointer to a saved copy of the buffer containing no uncommitted
 	 * deallocation references, so that allocations can avoid overwriting
-	 * uncommitted deletes. [jbd_lock_bh_state()]
+	 * uncommitted deletes. [b_state_lock]
 	 */
 	char *b_committed_data;
 
@@ -63,7 +70,7 @@ struct journal_head {
 	 * metadata: either the running transaction or the committing
 	 * transaction (if there is one).  Only applies to buffers on a
 	 * transaction's data or metadata journaling list.
-	 * [j_list_lock] [jbd_lock_bh_state()]
+	 * [j_list_lock] [b_state_lock]
 	 * Either of these locks is enough for reading, both are needed for
 	 * changes.
 	 */
@@ -73,13 +80,13 @@ struct journal_head {
 	 * Pointer to the running compound transaction which is currently
 	 * modifying the buffer's metadata, if there was already a transaction
 	 * committing it when the new transaction touched it.
-	 * [t_list_lock] [jbd_lock_bh_state()]
+	 * [t_list_lock] [b_state_lock]
 	 */
 	transaction_t *b_next_transaction;
 
 	/*
 	 * Doubly-linked list of buffers on a transaction's data, metadata or
-	 * forget queue. [t_list_lock] [jbd_lock_bh_state()]
+	 * forget queue. [t_list_lock] [b_state_lock]
 	 */
 	struct journal_head *b_tnext, *b_tprev;
 
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index d83d403dac2ea..2f9abc6aab0be 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -227,6 +227,10 @@ extern void __cant_sleep(const char *file, int line, int preempt_offset);
  */
 # define might_sleep() \
 	do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0)
+
+# define might_sleep_no_state_check() \
+	do { ___might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0)
+
 /**
  * cant_sleep - annotation for functions that cannot sleep
  *
@@ -258,6 +262,7 @@ extern void __cant_sleep(const char *file, int line, int preempt_offset);
   static inline void __might_sleep(const char *file, int line,
 				   int preempt_offset) { }
 # define might_sleep() do { might_resched(); } while (0)
+# define might_sleep_no_state_check() do { might_resched(); } while (0)
 # define cant_sleep() do { } while (0)
 # define sched_annotate_sleep() do { } while (0)
 # define non_block_start() do { } while (0)
diff --git a/include/linux/kmsg_dump.h b/include/linux/kmsg_dump.h
index 2e7a1e032c71a..ede5066663b92 100644
--- a/include/linux/kmsg_dump.h
+++ b/include/linux/kmsg_dump.h
@@ -46,10 +46,8 @@ struct kmsg_dumper {
 	bool registered;
 
 	/* private state of the kmsg iterator */
-	u32 cur_idx;
-	u32 next_idx;
-	u64 cur_seq;
-	u64 next_seq;
+	u64 line_seq;
+	u64 buffer_end_seq;
 };
 
 #ifdef CONFIG_PRINTK
diff --git a/include/linux/list_bl.h b/include/linux/list_bl.h
index ae1b541446c90..83e0ec90ed0d5 100644
--- a/include/linux/list_bl.h
+++ b/include/linux/list_bl.h
@@ -3,6 +3,7 @@
 #define _LINUX_LIST_BL_H
 
 #include <linux/list.h>
+#include <linux/spinlock.h>
 #include <linux/bit_spinlock.h>
 
 /*
@@ -33,13 +34,24 @@
 
 struct hlist_bl_head {
 	struct hlist_bl_node *first;
+#ifdef CONFIG_PREEMPT_RT
+	raw_spinlock_t lock;
+#endif
 };
 
 struct hlist_bl_node {
 	struct hlist_bl_node *next, **pprev;
 };
-#define INIT_HLIST_BL_HEAD(ptr) \
-	((ptr)->first = NULL)
+
+#ifdef CONFIG_PREEMPT_RT
+#define INIT_HLIST_BL_HEAD(h)		\
+do {					\
+	(h)->first = NULL;		\
+	raw_spin_lock_init(&(h)->lock);	\
+} while (0)
+#else
+#define INIT_HLIST_BL_HEAD(h) (h)->first = NULL
+#endif
 
 static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h)
 {
@@ -145,12 +157,26 @@ static inline void hlist_bl_del_init(struct hlist_bl_node *n)
 
 static inline void hlist_bl_lock(struct hlist_bl_head *b)
 {
+#ifndef CONFIG_PREEMPT_RT
 	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
 	__bit_spin_unlock(0, (unsigned long *)b);
+#else
+#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
+	__clear_bit(0, (unsigned long *)b);
+#endif
+	raw_spin_unlock(&b->lock);
+#endif
 }
 
 static inline bool hlist_bl_is_locked(struct hlist_bl_head *b)
diff --git a/include/linux/locallock.h b/include/linux/locallock.h
new file mode 100644
index 0000000000000..05a15110c8aa7
--- /dev/null
+++ b/include/linux/locallock.h
@@ -0,0 +1,281 @@
+#ifndef _LINUX_LOCALLOCK_H
+#define _LINUX_LOCALLOCK_H
+
+#include <linux/percpu.h>
+#include <linux/spinlock.h>
+
+#ifdef CONFIG_PREEMPT_RT
+
+#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)
+
+#define local_lock_on(lvar, cpu)				\
+	do { __local_lock(&per_cpu(lvar, cpu)); } while (0)
+
+static inline int __local_trylock(struct local_irq_lock *lv)
+{
+	if (lv->owner != current && spin_trylock(&lv->lock)) {
+		LL_WARN(lv->owner);
+		LL_WARN(lv->nestcnt);
+		lv->owner = current;
+		lv->nestcnt = 1;
+		return 1;
+	} else if (lv->owner == current) {
+		lv->nestcnt++;
+		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(this_cpu_ptr(&lvar));		\
+		put_local_var(lvar);				\
+	} while (0)
+
+#define local_unlock_on(lvar, cpu)                       \
+	do { __local_unlock(&per_cpu(lvar, cpu)); } while (0)
+
+static inline void __local_lock_irq(struct local_irq_lock *lv)
+{
+	spin_lock_irqsave(&lv->lock, lv->flags);
+	LL_WARN(lv->owner);
+	LL_WARN(lv->nestcnt);
+	lv->owner = current;
+	lv->nestcnt = 1;
+}
+
+#define local_lock_irq(lvar)						\
+	do { __local_lock_irq(&get_local_var(lvar)); } while (0)
+
+#define local_lock_irq_on(lvar, cpu)					\
+	do { __local_lock_irq(&per_cpu(lvar, cpu)); } while (0)
+
+static inline void __local_unlock_irq(struct local_irq_lock *lv)
+{
+	LL_WARN(!lv->nestcnt);
+	LL_WARN(lv->owner != current);
+	lv->owner = NULL;
+	lv->nestcnt = 0;
+	spin_unlock_irq(&lv->lock);
+}
+
+#define local_unlock_irq(lvar)						\
+	do {								\
+		__local_unlock_irq(this_cpu_ptr(&lvar));		\
+		put_local_var(lvar);					\
+	} while (0)
+
+#define local_unlock_irq_on(lvar, cpu)					\
+	do {								\
+		__local_unlock_irq(&per_cpu(lvar, cpu));		\
+	} while (0)
+
+static inline int __local_lock_irqsave(struct local_irq_lock *lv)
+{
+	if (lv->owner != current) {
+		__local_lock_irq(lv);
+		return 0;
+	} else {
+		lv->nestcnt++;
+		return 1;
+	}
+}
+
+#define local_lock_irqsave(lvar, _flags)				\
+	do {								\
+		if (__local_lock_irqsave(&get_local_var(lvar)))		\
+			put_local_var(lvar);				\
+		_flags = __this_cpu_read(lvar.flags);			\
+	} while (0)
+
+#define local_lock_irqsave_on(lvar, _flags, cpu)			\
+	do {								\
+		__local_lock_irqsave(&per_cpu(lvar, cpu));		\
+		_flags = per_cpu(lvar, cpu).flags;			\
+	} while (0)
+
+static inline int __local_unlock_irqrestore(struct local_irq_lock *lv,
+					    unsigned long flags)
+{
+	LL_WARN(!lv->nestcnt);
+	LL_WARN(lv->owner != current);
+	if (--lv->nestcnt)
+		return 0;
+
+	lv->owner = NULL;
+	spin_unlock_irqrestore(&lv->lock, lv->flags);
+	return 1;
+}
+
+#define local_unlock_irqrestore(lvar, flags)				\
+	do {								\
+		if (__local_unlock_irqrestore(this_cpu_ptr(&lvar), flags)) \
+			put_local_var(lvar);				\
+	} while (0)
+
+#define local_unlock_irqrestore_on(lvar, flags, cpu)			\
+	do {								\
+		__local_unlock_irqrestore(&per_cpu(lvar, cpu), flags);	\
+	} while (0)
+
+#define local_spin_trylock_irq(lvar, lock)				\
+	({								\
+		int __locked;						\
+		local_lock_irq(lvar);					\
+		__locked = spin_trylock(lock);				\
+		if (!__locked)						\
+			local_unlock_irq(lvar);				\
+		__locked;						\
+	})
+
+#define local_spin_lock_irq(lvar, lock)					\
+	do {								\
+		local_lock_irq(lvar);					\
+		spin_lock(lock);					\
+	} while (0)
+
+#define local_spin_unlock_irq(lvar, lock)				\
+	do {								\
+		spin_unlock(lock);					\
+		local_unlock_irq(lvar);					\
+	} while (0)
+
+#define local_spin_lock_irqsave(lvar, lock, flags)			\
+	do {								\
+		local_lock_irqsave(lvar, flags);			\
+		spin_lock(lock);					\
+	} while (0)
+
+#define local_spin_unlock_irqrestore(lvar, lock, flags)			\
+	do {								\
+		spin_unlock(lock);					\
+		local_unlock_irqrestore(lvar, flags);			\
+	} while (0)
+
+#define get_locked_var(lvar, var)					\
+	(*({								\
+		local_lock(lvar);					\
+		this_cpu_ptr(&var);					\
+	}))
+
+#define put_locked_var(lvar, var)	local_unlock(lvar);
+
+#define get_locked_ptr(lvar, var)					\
+	({								\
+		local_lock(lvar);					\
+		this_cpu_ptr(var);					\
+	})
+
+#define put_locked_ptr(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 */
+
+#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_trylock(lvar)					\
+	({							\
+		preempt_disable();				\
+		1;						\
+	})
+
+#define local_lock(lvar)			preempt_disable()
+#define local_unlock(lvar)			preempt_enable()
+#define local_lock_irq(lvar)			local_irq_disable()
+#define local_lock_irq_on(lvar, cpu)		local_irq_disable()
+#define local_unlock_irq(lvar)			local_irq_enable()
+#define local_unlock_irq_on(lvar, cpu)		local_irq_enable()
+#define local_lock_irqsave(lvar, flags)		local_irq_save(flags)
+#define local_unlock_irqrestore(lvar, flags)	local_irq_restore(flags)
+
+#define local_spin_trylock_irq(lvar, lock)	spin_trylock_irq(lock)
+#define local_spin_lock_irq(lvar, lock)		spin_lock_irq(lock)
+#define local_spin_unlock_irq(lvar, lock)	spin_unlock_irq(lock)
+#define local_spin_lock_irqsave(lvar, lock, flags)	\
+	spin_lock_irqsave(lock, flags)
+#define local_spin_unlock_irqrestore(lvar, lock, flags)	\
+	spin_unlock_irqrestore(lock, flags)
+
+#define get_locked_var(lvar, var)		get_cpu_var(var)
+#define put_locked_var(lvar, var)		put_cpu_var(var)
+#define get_locked_ptr(lvar, var)		get_cpu_ptr(var)
+#define put_locked_ptr(lvar, var)		put_cpu_ptr(var)
+
+#define local_lock_cpu(lvar)			get_cpu()
+#define local_unlock_cpu(lvar)			put_cpu()
+
+#endif
+
+#endif
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 270aa8fd2800b..497440fe047c0 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/uprobes.h>
+#include <linux/rcupdate.h>
 #include <linux/page-flags-layout.h>
 #include <linux/workqueue.h>
 
@@ -520,6 +521,9 @@ struct mm_struct {
 		bool tlb_flush_batched;
 #endif
 		struct uprobes_state uprobes_state;
+#ifdef CONFIG_PREEMPT_RT
+		struct rcu_head delayed_drop;
+#endif
 #ifdef CONFIG_HUGETLB_PAGE
 		atomic_long_t hugetlb_usage;
 #endif
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index aca8f36dfac9a..2b72473ded555 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -22,6 +22,17 @@
 
 struct ww_acquire_ctx;
 
+#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
+# include <linux/mutex_rt.h>
+#else
+
 /*
  * Simple, straightforward mutexes with strict semantics:
  *
@@ -108,13 +119,6 @@ do {									\
 	__mutex_init((mutex), #mutex, &__key);				\
 } while (0)
 
-#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) \
 		{ .owner = ATOMIC_LONG_INIT(0) \
 		, .wait_lock = __SPIN_LOCK_UNLOCKED(lockname.wait_lock) \
@@ -210,4 +214,6 @@ enum mutex_trylock_recursive_enum {
 extern /* __deprecated */ __must_check enum mutex_trylock_recursive_enum
 mutex_trylock_recursive(struct mutex *lock);
 
+#endif /* !PREEMPT_RT */
+
 #endif /* __LINUX_MUTEX_H */
diff --git a/include/linux/mutex_rt.h b/include/linux/mutex_rt.h
new file mode 100644
index 0000000000000..3fcb5edb1d2b4
--- /dev/null
+++ b/include/linux/mutex_rt.h
@@ -0,0 +1,130 @@
+#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 void __lockfunc _mutex_lock_io(struct mutex *lock);
+extern void __lockfunc _mutex_lock_io_nested(struct mutex *lock, int subclass);
+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_lock_io(l)		_mutex_lock_io(l);
+
+#define __mutex_owner(l)		((l)->lock.owner)
+
+#ifdef CONFIG_DEBUG_MUTEXES
+#define mutex_destroy(l)		rt_mutex_destroy(&(l)->lock)
+#else
+static inline void mutex_destroy(struct mutex *lock) {}
+#endif
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define mutex_lock_nested(l, s)	_mutex_lock_nested(l, s)
+# define mutex_lock_interruptible_nested(l, s) \
+					_mutex_lock_interruptible_nested(l, s)
+# define mutex_lock_killable_nested(l, s) \
+					_mutex_lock_killable_nested(l, s)
+# define mutex_lock_io_nested(l, s)	_mutex_lock_io_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)
+# define mutex_lock_io_nested(l, s)	_mutex_lock_io(l)
+#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)
+
+/**
+ * These values are chosen such that FAIL and SUCCESS match the
+ * values of the regular mutex_trylock().
+ */
+enum mutex_trylock_recursive_enum {
+	MUTEX_TRYLOCK_FAILED    = 0,
+	MUTEX_TRYLOCK_SUCCESS   = 1,
+	MUTEX_TRYLOCK_RECURSIVE,
+};
+/**
+ * mutex_trylock_recursive - trylock variant that allows recursive locking
+ * @lock: mutex to be locked
+ *
+ * This function should not be used, _ever_. It is purely for hysterical GEM
+ * raisins, and once those are gone this will be removed.
+ *
+ * Returns:
+ *  MUTEX_TRYLOCK_FAILED    - trylock failed,
+ *  MUTEX_TRYLOCK_SUCCESS   - lock acquired,
+ *  MUTEX_TRYLOCK_RECURSIVE - we already owned the lock.
+ */
+int __rt_mutex_owner_current(struct rt_mutex *lock);
+
+static inline /* __deprecated */ __must_check enum mutex_trylock_recursive_enum
+mutex_trylock_recursive(struct mutex *lock)
+{
+	if (unlikely(__rt_mutex_owner_current(&lock->lock)))
+		return MUTEX_TRYLOCK_RECURSIVE;
+
+	return mutex_trylock(lock);
+}
+
+extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
+
+#endif
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 76d952aeb0fcd..cee4e26d99d5b 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3016,6 +3016,7 @@ struct softnet_data {
 	unsigned int		dropped;
 	struct sk_buff_head	input_pkt_queue;
 	struct napi_struct	backlog;
+	struct sk_buff_head	tofree_queue;
 
 };
 
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 570a60c2f4f48..8e7f60827ecd9 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -165,7 +165,11 @@ struct nfs_inode {
 
 	/* Readers: in-flight sillydelete RPC calls */
 	/* Writers: rmdir */
+#ifdef CONFIG_PREEMPT_RT
+	struct semaphore        rmdir_sem;
+#else
 	struct rw_semaphore	rmdir_sem;
+#endif
 	struct mutex		commit_mutex;
 
 #if IS_ENABLED(CONFIG_NFS_V4)
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 9b8324ec08f31..c805cd551337a 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1594,7 +1594,7 @@ struct nfs_unlinkdata {
 	struct nfs_removeargs args;
 	struct nfs_removeres res;
 	struct dentry *dentry;
-	wait_queue_head_t wq;
+	struct swait_queue_head wq;
 	const struct cred *cred;
 	struct nfs_fattr dir_attr;
 	long timeout;
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 7aef0abc194a2..390031e816dcd 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -186,14 +186,14 @@ static inline void percpu_ref_get_many(struct percpu_ref *ref, unsigned long nr)
 {
 	unsigned long __percpu *percpu_count;
 
-	rcu_read_lock_sched();
+	rcu_read_lock();
 
 	if (__ref_is_percpu(ref, &percpu_count))
 		this_cpu_add(*percpu_count, nr);
 	else
 		atomic_long_add(nr, &ref->count);
 
-	rcu_read_unlock_sched();
+	rcu_read_unlock();
 }
 
 /**
@@ -223,7 +223,7 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref)
 	unsigned long __percpu *percpu_count;
 	bool ret;
 
-	rcu_read_lock_sched();
+	rcu_read_lock();
 
 	if (__ref_is_percpu(ref, &percpu_count)) {
 		this_cpu_inc(*percpu_count);
@@ -232,7 +232,7 @@ static inline bool percpu_ref_tryget(struct percpu_ref *ref)
 		ret = atomic_long_inc_not_zero(&ref->count);
 	}
 
-	rcu_read_unlock_sched();
+	rcu_read_unlock();
 
 	return ret;
 }
@@ -257,7 +257,7 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
 	unsigned long __percpu *percpu_count;
 	bool ret = false;
 
-	rcu_read_lock_sched();
+	rcu_read_lock();
 
 	if (__ref_is_percpu(ref, &percpu_count)) {
 		this_cpu_inc(*percpu_count);
@@ -266,7 +266,7 @@ static inline bool percpu_ref_tryget_live(struct percpu_ref *ref)
 		ret = atomic_long_inc_not_zero(&ref->count);
 	}
 
-	rcu_read_unlock_sched();
+	rcu_read_unlock();
 
 	return ret;
 }
@@ -285,14 +285,14 @@ static inline void percpu_ref_put_many(struct percpu_ref *ref, unsigned long nr)
 {
 	unsigned long __percpu *percpu_count;
 
-	rcu_read_lock_sched();
+	rcu_read_lock();
 
 	if (__ref_is_percpu(ref, &percpu_count))
 		this_cpu_sub(*percpu_count, nr);
 	else if (unlikely(atomic_long_sub_and_test(nr, &ref->count)))
 		ref->release(ref);
 
-	rcu_read_unlock_sched();
+	rcu_read_unlock();
 }
 
 /**
diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h
index 3998cdf9cd148..9fa9a1dd9a11a 100644
--- a/include/linux/percpu-rwsem.h
+++ b/include/linux/percpu-rwsem.h
@@ -119,7 +119,7 @@ static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem,
 					bool read, unsigned long ip)
 {
 	lock_release(&sem->rw_sem.dep_map, 1, ip);
-#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
+#if defined(CONFIG_RWSEM_SPIN_ON_OWNER) && !defined(CONFIG_PREEMPT_RT)
 	if (!read)
 		atomic_long_set(&sem->rw_sem.owner, RWSEM_OWNER_UNKNOWN);
 #endif
@@ -129,7 +129,7 @@ static inline void percpu_rwsem_acquire(struct percpu_rw_semaphore *sem,
 					bool read, unsigned long ip)
 {
 	lock_acquire(&sem->rw_sem.dep_map, 0, 1, read, 1, NULL, ip);
-#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
+#if defined(CONFIG_RWSEM_SPIN_ON_OWNER) && !defined(CONFIG_PREEMPT_RT)
 	if (!read)
 		atomic_long_set(&sem->rw_sem.owner, (long)current);
 #endif
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 5e76af742c807..3d0d9873de61e 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -19,6 +19,35 @@
 #define PERCPU_MODULE_RESERVE		0
 #endif
 
+#ifdef CONFIG_PREEMPT_RT
+
+#define get_local_var(var) (*({	\
+	migrate_disable();	\
+	this_cpu_ptr(&var);	}))
+
+#define put_local_var(var) do {	\
+	(void)&(var);		\
+	migrate_enable();	\
+} while (0)
+
+# define get_local_ptr(var) ({	\
+	migrate_disable();	\
+	this_cpu_ptr(var);	})
+
+# define put_local_ptr(var) do {	\
+	(void)(var);			\
+	migrate_enable();		\
+} while (0)
+
+#else
+
+#define get_local_var(var)	get_cpu_var(var)
+#define put_local_var(var)	put_cpu_var(var)
+#define get_local_ptr(var)	get_cpu_ptr(var)
+#define put_local_ptr(var)	put_cpu_ptr(var)
+
+#endif
+
 /* minimum unit size, also is the maximum supported allocation size */
 #define PCPU_MIN_UNIT_SIZE		PFN_ALIGN(32 << 10)
 
diff --git a/include/linux/pid.h b/include/linux/pid.h
index 9645b1194c981..916c1d0e42c22 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -3,6 +3,7 @@
 #define _LINUX_PID_H
 
 #include <linux/rculist.h>
+#include <linux/atomic.h>
 #include <linux/wait.h>
 #include <linux/refcount.h>
 
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index 3d10c84a97a94..bad09364b20a1 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -72,6 +72,7 @@ struct cpu_timer {
 	struct task_struct	*task;
 	struct list_head	elist;
 	int			firing;
+	int			firing_cpu;
 };
 
 static inline bool cpu_timer_enqueue(struct timerqueue_head *head,
@@ -123,6 +124,9 @@ struct posix_cputimers {
 	struct posix_cputimer_base	bases[CPUCLOCK_MAX];
 	unsigned int			timers_active;
 	unsigned int			expiry_active;
+#ifdef CONFIG_PREEMPT_RT
+	struct task_struct		*posix_timer_list;
+#endif
 };
 
 static inline void posix_cputimers_init(struct posix_cputimers *pct)
@@ -152,9 +156,16 @@ static inline void posix_cputimers_rt_watchdog(struct posix_cputimers *pct,
 	INIT_CPU_TIMERBASE(b[2]),					\
 }
 
+#ifdef CONFIG_PREEMPT_RT
+# define INIT_TIMER_LIST	.posix_timer_list = NULL,
+#else
+# define INIT_TIMER_LIST
+#endif
+
 #define INIT_CPU_TIMERS(s)						\
 	.posix_cputimers = {						\
 		.bases = INIT_CPU_TIMERBASES(s.posix_cputimers.bases),	\
+		INIT_TIMER_LIST						\
 	},
 #else
 struct posix_cputimers { };
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index bbb68dba37cc8..adb085fe31e43 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -78,10 +78,8 @@
 #include <asm/preempt.h>
 
 #define hardirq_count()	(preempt_count() & HARDIRQ_MASK)
-#define softirq_count()	(preempt_count() & SOFTIRQ_MASK)
 #define irq_count()	(preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \
 				 | NMI_MASK))
-
 /*
  * Are we doing bottom half or hardware interrupt processing?
  *
@@ -96,12 +94,23 @@
  *       should not be used in new code.
  */
 #define in_irq()		(hardirq_count())
-#define in_softirq()		(softirq_count())
 #define in_interrupt()		(irq_count())
-#define in_serving_softirq()	(softirq_count() & SOFTIRQ_OFFSET)
 #define in_nmi()		(preempt_count() & NMI_MASK)
 #define in_task()		(!(preempt_count() & \
 				   (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET)))
+#ifdef CONFIG_PREEMPT_RT
+
+#define softirq_count()		((long)current->softirq_count)
+#define in_softirq()		(softirq_count())
+#define in_serving_softirq()	(current->softirq_count & SOFTIRQ_OFFSET)
+
+#else
+
+#define softirq_count()		(preempt_count() & SOFTIRQ_MASK)
+#define in_softirq()		(softirq_count())
+#define in_serving_softirq()	(softirq_count() & SOFTIRQ_OFFSET)
+
+#endif
 
 /*
  * The preempt_count offset after preempt_disable();
@@ -115,7 +124,11 @@
 /*
  * The preempt_count offset after spin_lock()
  */
+#if !defined(CONFIG_PREEMPT_RT)
 #define PREEMPT_LOCK_OFFSET	PREEMPT_DISABLE_OFFSET
+#else
+#define PREEMPT_LOCK_OFFSET	0
+#endif
 
 /*
  * The preempt_count offset needed for things like:
@@ -164,6 +177,20 @@ extern void preempt_count_sub(int val);
 #define preempt_count_inc() preempt_count_add(1)
 #define preempt_count_dec() preempt_count_sub(1)
 
+#ifdef CONFIG_PREEMPT_LAZY
+#define add_preempt_lazy_count(val)	do { preempt_lazy_count() += (val); } while (0)
+#define sub_preempt_lazy_count(val)	do { preempt_lazy_count() -= (val); } while (0)
+#define inc_preempt_lazy_count()	add_preempt_lazy_count(1)
+#define dec_preempt_lazy_count()	sub_preempt_lazy_count(1)
+#define preempt_lazy_count()		(current_thread_info()->preempt_lazy_count)
+#else
+#define add_preempt_lazy_count(val)	do { } while (0)
+#define sub_preempt_lazy_count(val)	do { } while (0)
+#define inc_preempt_lazy_count()	do { } while (0)
+#define dec_preempt_lazy_count()	do { } while (0)
+#define preempt_lazy_count()		(0)
+#endif
+
 #ifdef CONFIG_PREEMPT_COUNT
 
 #define preempt_disable() \
@@ -172,16 +199,53 @@ do { \
 	barrier(); \
 } while (0)
 
+#define preempt_lazy_disable() \
+do { \
+	inc_preempt_lazy_count(); \
+	barrier(); \
+} while (0)
+
 #define sched_preempt_enable_no_resched() \
 do { \
 	barrier(); \
 	preempt_count_dec(); \
 } while (0)
 
-#define preempt_enable_no_resched() sched_preempt_enable_no_resched()
+#ifdef CONFIG_PREEMPT_RT
+# define preempt_enable_no_resched() sched_preempt_enable_no_resched()
+# define preempt_check_resched_rt() preempt_check_resched()
+#else
+# define preempt_enable_no_resched() preempt_enable()
+# define preempt_check_resched_rt() barrier();
+#endif
 
 #define preemptible()	(preempt_count() == 0 && !irqs_disabled())
 
+#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT)
+
+extern void migrate_disable(void);
+extern void migrate_enable(void);
+
+int __migrate_disabled(struct task_struct *p);
+
+#elif !defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT)
+
+extern void migrate_disable(void);
+extern void migrate_enable(void);
+static inline int __migrate_disabled(struct task_struct *p)
+{
+	return 0;
+}
+
+#else
+#define migrate_disable()		preempt_disable()
+#define migrate_enable()		preempt_enable()
+static inline int __migrate_disabled(struct task_struct *p)
+{
+	return 0;
+}
+#endif
+
 #ifdef CONFIG_PREEMPTION
 #define preempt_enable() \
 do { \
@@ -203,6 +267,13 @@ do { \
 		__preempt_schedule(); \
 } while (0)
 
+#define preempt_lazy_enable() \
+do { \
+	dec_preempt_lazy_count(); \
+	barrier(); \
+	preempt_check_resched(); \
+} while (0)
+
 #else /* !CONFIG_PREEMPTION */
 #define preempt_enable() \
 do { \
@@ -210,6 +281,12 @@ do { \
 	preempt_count_dec(); \
 } while (0)
 
+#define preempt_lazy_enable() \
+do { \
+	dec_preempt_lazy_count(); \
+	barrier(); \
+} while (0)
+
 #define preempt_enable_notrace() \
 do { \
 	barrier(); \
@@ -248,8 +325,16 @@ do { \
 #define preempt_disable_notrace()		barrier()
 #define preempt_enable_no_resched_notrace()	barrier()
 #define preempt_enable_notrace()		barrier()
+#define preempt_check_resched_rt()		barrier()
 #define preemptible()				0
 
+#define migrate_disable()			barrier()
+#define migrate_enable()			barrier()
+
+static inline int __migrate_disabled(struct task_struct *p)
+{
+	return 0;
+}
 #endif /* CONFIG_PREEMPT_COUNT */
 
 #ifdef MODULE
@@ -268,10 +353,22 @@ do { \
 } while (0)
 #define preempt_fold_need_resched() \
 do { \
-	if (tif_need_resched()) \
+	if (tif_need_resched_now()) \
 		set_preempt_need_resched(); \
 } while (0)
 
+#ifdef CONFIG_PREEMPT_RT
+# define preempt_disable_rt()		preempt_disable()
+# define preempt_enable_rt()		preempt_enable()
+# define preempt_disable_nort()		barrier()
+# define preempt_enable_nort()		barrier()
+#else
+# define preempt_disable_rt()		barrier()
+# define preempt_enable_rt()		barrier()
+# define preempt_disable_nort()		preempt_disable()
+# define preempt_enable_nort()		preempt_enable()
+#endif
+
 #ifdef CONFIG_PREEMPT_NOTIFIERS
 
 struct preempt_notifier;
diff --git a/include/linux/printk.h b/include/linux/printk.h
index c09d67edda3a1..1fe8068100c25 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -58,6 +58,7 @@ static inline const char *printk_skip_headers(const char *buffer)
  */
 #define CONSOLE_LOGLEVEL_DEFAULT CONFIG_CONSOLE_LOGLEVEL_DEFAULT
 #define CONSOLE_LOGLEVEL_QUIET	 CONFIG_CONSOLE_LOGLEVEL_QUIET
+#define CONSOLE_LOGLEVEL_EMERGENCY CONFIG_CONSOLE_LOGLEVEL_EMERGENCY
 
 extern int console_printk[];
 
@@ -65,6 +66,7 @@ extern int console_printk[];
 #define default_message_loglevel (console_printk[1])
 #define minimum_console_loglevel (console_printk[2])
 #define default_console_loglevel (console_printk[3])
+#define emergency_console_loglevel (console_printk[4])
 
 static inline void console_silent(void)
 {
@@ -146,18 +148,6 @@ static inline __printf(1, 2) __cold
 void early_printk(const char *s, ...) { }
 #endif
 
-#ifdef CONFIG_PRINTK_NMI
-extern void printk_nmi_enter(void);
-extern void printk_nmi_exit(void);
-extern void printk_nmi_direct_enter(void);
-extern void printk_nmi_direct_exit(void);
-#else
-static inline void printk_nmi_enter(void) { }
-static inline void printk_nmi_exit(void) { }
-static inline void printk_nmi_direct_enter(void) { }
-static inline void printk_nmi_direct_exit(void) { }
-#endif /* PRINTK_NMI */
-
 #ifdef CONFIG_PRINTK
 asmlinkage __printf(5, 0)
 int vprintk_emit(int facility, int level,
@@ -202,9 +192,7 @@ __printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...);
 void dump_stack_print_info(const char *log_lvl);
 void show_regs_print_info(const char *log_lvl);
 extern asmlinkage void dump_stack(void) __cold;
-extern void printk_safe_init(void);
-extern void printk_safe_flush(void);
-extern void printk_safe_flush_on_panic(void);
+struct wait_queue_head *printk_wait_queue(void);
 #else
 static inline __printf(1, 0)
 int vprintk(const char *s, va_list args)
@@ -268,18 +256,6 @@ static inline void show_regs_print_info(const char *log_lvl)
 static inline void dump_stack(void)
 {
 }
-
-static inline void printk_safe_init(void)
-{
-}
-
-static inline void printk_safe_flush(void)
-{
-}
-
-static inline void printk_safe_flush_on_panic(void)
-{
-}
 #endif
 
 extern int kptr_restrict;
diff --git a/include/linux/printk_ringbuffer.h b/include/linux/printk_ringbuffer.h
new file mode 100644
index 0000000000000..ec3d7ceec378e
--- /dev/null
+++ b/include/linux/printk_ringbuffer.h
@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_PRINTK_RINGBUFFER_H
+#define _LINUX_PRINTK_RINGBUFFER_H
+
+#include <linux/irq_work.h>
+#include <linux/atomic.h>
+#include <linux/percpu.h>
+#include <linux/wait.h>
+
+struct prb_cpulock {
+	atomic_t owner;
+	unsigned long __percpu *irqflags;
+};
+
+struct printk_ringbuffer {
+	void *buffer;
+	unsigned int size_bits;
+
+	u64 seq;
+	atomic_long_t lost;
+
+	atomic_long_t tail;
+	atomic_long_t head;
+	atomic_long_t reserve;
+
+	struct prb_cpulock *cpulock;
+	atomic_t ctx;
+
+	struct wait_queue_head *wq;
+	atomic_long_t wq_counter;
+	struct irq_work *wq_work;
+};
+
+struct prb_entry {
+	unsigned int size;
+	u64 seq;
+	char data[0];
+};
+
+struct prb_handle {
+	struct printk_ringbuffer *rb;
+	unsigned int cpu;
+	struct prb_entry *entry;
+};
+
+#define DECLARE_STATIC_PRINTKRB_CPULOCK(name)				\
+static DEFINE_PER_CPU(unsigned long, _##name##_percpu_irqflags);	\
+static struct prb_cpulock name = {					\
+	.owner = ATOMIC_INIT(-1),					\
+	.irqflags = &_##name##_percpu_irqflags,				\
+}
+
+#define PRB_INIT ((unsigned long)-1)
+
+#define DECLARE_STATIC_PRINTKRB_ITER(name, rbaddr)			\
+static struct prb_iterator name = {					\
+	.rb = rbaddr,							\
+	.lpos = PRB_INIT,						\
+}
+
+struct prb_iterator {
+	struct printk_ringbuffer *rb;
+	unsigned long lpos;
+};
+
+#define DECLARE_STATIC_PRINTKRB(name, szbits, cpulockptr)		\
+static char _##name##_buffer[1 << (szbits)]				\
+	__aligned(__alignof__(long));					\
+static DECLARE_WAIT_QUEUE_HEAD(_##name##_wait);				\
+static void _##name##_wake_work_func(struct irq_work *irq_work)		\
+{									\
+	wake_up_interruptible_all(&_##name##_wait);			\
+}									\
+static struct irq_work _##name##_wake_work = {				\
+	.func = _##name##_wake_work_func,				\
+	.flags = IRQ_WORK_LAZY,						\
+};									\
+static struct printk_ringbuffer name = {				\
+	.buffer = &_##name##_buffer[0],					\
+	.size_bits = szbits,						\
+	.seq = 0,							\
+	.lost = ATOMIC_LONG_INIT(0),					\
+	.tail = ATOMIC_LONG_INIT(-111 * sizeof(long)),			\
+	.head = ATOMIC_LONG_INIT(-111 * sizeof(long)),			\
+	.reserve = ATOMIC_LONG_INIT(-111 * sizeof(long)),		\
+	.cpulock = cpulockptr,						\
+	.ctx = ATOMIC_INIT(0),						\
+	.wq = &_##name##_wait,						\
+	.wq_counter = ATOMIC_LONG_INIT(0),				\
+	.wq_work = &_##name##_wake_work,				\
+}
+
+/* writer interface */
+char *prb_reserve(struct prb_handle *h, struct printk_ringbuffer *rb,
+		  unsigned int size);
+void prb_commit(struct prb_handle *h);
+
+/* reader interface */
+void prb_iter_init(struct prb_iterator *iter, struct printk_ringbuffer *rb,
+		   u64 *seq);
+void prb_iter_copy(struct prb_iterator *dest, struct prb_iterator *src);
+int prb_iter_next(struct prb_iterator *iter, char *buf, int size, u64 *seq);
+int prb_iter_wait_next(struct prb_iterator *iter, char *buf, int size,
+		       u64 *seq);
+int prb_iter_seek(struct prb_iterator *iter, u64 seq);
+int prb_iter_data(struct prb_iterator *iter, char *buf, int size, u64 *seq);
+
+/* utility functions */
+int prb_buffer_size(struct printk_ringbuffer *rb);
+void prb_inc_lost(struct printk_ringbuffer *rb);
+void prb_lock(struct prb_cpulock *cpu_lock, unsigned int *cpu_store);
+void prb_unlock(struct prb_cpulock *cpu_lock, unsigned int cpu_store);
+
+#endif /*_LINUX_PRINTK_RINGBUFFER_H */
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index 63e62372443a5..040b1fd0ab940 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -226,6 +226,7 @@ unsigned int radix_tree_gang_lookup(const struct radix_tree_root *,
 			unsigned int max_items);
 int radix_tree_preload(gfp_t gfp_mask);
 int radix_tree_maybe_preload(gfp_t gfp_mask);
+void radix_tree_preload_end(void);
 void radix_tree_init(void);
 void *radix_tree_tag_set(struct radix_tree_root *,
 			unsigned long index, unsigned int tag);
@@ -243,11 +244,6 @@ unsigned int radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *,
 		unsigned int max_items, unsigned int tag);
 int radix_tree_tagged(const struct radix_tree_root *, unsigned int tag);
 
-static inline void radix_tree_preload_end(void)
-{
-	preempt_enable();
-}
-
 void __rcu **idr_get_free(struct radix_tree_root *root,
 			      struct radix_tree_iter *iter, gfp_t gfp,
 			      unsigned long max);
diff --git a/include/linux/random.h b/include/linux/random.h
index f189c927fdea5..62d8caa3b0b12 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -33,7 +33,7 @@ static inline void add_latent_entropy(void) {}
 
 extern void add_input_randomness(unsigned int type, unsigned int code,
 				 unsigned int value) __latent_entropy;
-extern void add_interrupt_randomness(int irq, int irq_flags) __latent_entropy;
+extern void add_interrupt_randomness(int irq, int irq_flags, __u64 ip) __latent_entropy;
 
 extern void get_random_bytes(void *buf, int nbytes);
 extern int wait_for_random_bytes(void);
diff --git a/include/linux/ratelimit.h b/include/linux/ratelimit.h
index 8ddf79e9207a9..51e90cea9c455 100644
--- a/include/linux/ratelimit.h
+++ b/include/linux/ratelimit.h
@@ -59,7 +59,7 @@ static inline void ratelimit_state_exit(struct ratelimit_state *rs)
 		return;
 
 	if (rs->missed) {
-		pr_warn("%s: %d output lines suppressed due to ratelimiting\n",
+		pr_info("%s: %d output lines suppressed due to ratelimiting\n",
 			current->comm, rs->missed);
 		rs->missed = 0;
 	}
diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h
index 1fd61a9af45cd..c667ec871abb5 100644
--- a/include/linux/rbtree.h
+++ b/include/linux/rbtree.h
@@ -19,7 +19,7 @@
 
 #include <linux/kernel.h>
 #include <linux/stddef.h>
-#include <linux/rcupdate.h>
+#include <linux/rcu_assign_pointer.h>
 
 struct rb_node {
 	unsigned long  __rb_parent_color;
diff --git a/include/linux/rcu_assign_pointer.h b/include/linux/rcu_assign_pointer.h
new file mode 100644
index 0000000000000..78c05f606a73d
--- /dev/null
+++ b/include/linux/rcu_assign_pointer.h
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+#ifndef __LINUX_RCU_ASSIGN_POINTER_H__
+#define __LINUX_RCU_ASSIGN_POINTER_H__
+#include <linux/compiler.h>
+#include <asm/barrier.h>
+
+#ifdef __CHECKER__
+#define rcu_check_sparse(p, space) \
+	((void)(((typeof(*p) space *)p) == p))
+#else /* #ifdef __CHECKER__ */
+#define rcu_check_sparse(p, space)
+#endif /* #else #ifdef __CHECKER__ */
+
+/**
+ * RCU_INITIALIZER() - statically initialize an RCU-protected global variable
+ * @v: The value to statically initialize with.
+ */
+#define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v)
+
+/**
+ * rcu_assign_pointer() - assign to RCU-protected pointer
+ * @p: pointer to assign to
+ * @v: value to assign (publish)
+ *
+ * Assigns the specified value to the specified RCU-protected
+ * pointer, ensuring that any concurrent RCU readers will see
+ * any prior initialization.
+ *
+ * Inserts memory barriers on architectures that require them
+ * (which is most of them), and also prevents the compiler from
+ * reordering the code that initializes the structure after the pointer
+ * assignment.  More importantly, this call documents which pointers
+ * will be dereferenced by RCU read-side code.
+ *
+ * In some special cases, you may use RCU_INIT_POINTER() instead
+ * of rcu_assign_pointer().  RCU_INIT_POINTER() is a bit faster due
+ * to the fact that it does not constrain either the CPU or the compiler.
+ * That said, using RCU_INIT_POINTER() when you should have used
+ * rcu_assign_pointer() is a very bad thing that results in
+ * impossible-to-diagnose memory corruption.  So please be careful.
+ * See the RCU_INIT_POINTER() comment header for details.
+ *
+ * Note that rcu_assign_pointer() evaluates each of its arguments only
+ * once, appearances notwithstanding.  One of the "extra" evaluations
+ * is in typeof() and the other visible only to sparse (__CHECKER__),
+ * neither of which actually execute the argument.  As with most cpp
+ * macros, this execute-arguments-only-once property is important, so
+ * please be careful when making changes to rcu_assign_pointer() and the
+ * other macros that it invokes.
+ */
+#define rcu_assign_pointer(p, v)					\
+do {									\
+	uintptr_t _r_a_p__v = (uintptr_t)(v);				\
+	rcu_check_sparse(p, __rcu);					\
+									\
+	if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL)	\
+		WRITE_ONCE((p), (typeof(p))(_r_a_p__v));		\
+	else								\
+		smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v));	\
+} while (0)
+
+#endif
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 75a2eded7aa2c..4b7c52128409d 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -29,6 +29,7 @@
 #include <linux/lockdep.h>
 #include <asm/processor.h>
 #include <linux/cpumask.h>
+#include <linux/rcu_assign_pointer.h>
 
 #define ULONG_CMP_GE(a, b)	(ULONG_MAX / 2 >= (a) - (b))
 #define ULONG_CMP_LT(a, b)	(ULONG_MAX / 2 < (a) - (b))
@@ -51,6 +52,11 @@ void __rcu_read_unlock(void);
  * types of kernel builds, the rcu_read_lock() nesting depth is unknowable.
  */
 #define rcu_preempt_depth() (current->rcu_read_lock_nesting)
+#ifndef CONFIG_PREEMPT_RT
+#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 */
 
@@ -69,6 +75,8 @@ static inline int rcu_preempt_depth(void)
 	return 0;
 }
 
+#define sched_rcu_preempt_depth()	rcu_preempt_depth()
+
 #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
 
 /* Internal to kernel */
@@ -154,7 +162,7 @@ static inline void exit_tasks_rcu_finish(void) { }
  *
  * This macro resembles cond_resched(), except that it is defined to
  * report potential quiescent states to RCU-tasks even if the cond_resched()
- * machinery were to be shut off, as some advocate for PREEMPT kernels.
+ * machinery were to be shut off, as some advocate for PREEMPTION kernels.
  */
 #define cond_resched_tasks_rcu_qs() \
 do { \
@@ -279,7 +287,8 @@ static inline void rcu_preempt_sleep_check(void) { }
 #define rcu_sleep_check()						\
 	do {								\
 		rcu_preempt_sleep_check();				\
-		RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map),	\
+		if (!IS_ENABLED(CONFIG_PREEMPT_RT))		\
+		    RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map),	\
 				 "Illegal context switch in RCU-bh read-side critical section"); \
 		RCU_LOCKDEP_WARN(lock_is_held(&rcu_sched_lock_map),	\
 				 "Illegal context switch in RCU-sched read-side critical section"); \
@@ -300,13 +309,6 @@ static inline void rcu_preempt_sleep_check(void) { }
  * (e.g., __srcu), should this make sense in the future.
  */
 
-#ifdef __CHECKER__
-#define rcu_check_sparse(p, space) \
-	((void)(((typeof(*p) space *)p) == p))
-#else /* #ifdef __CHECKER__ */
-#define rcu_check_sparse(p, space)
-#endif /* #else #ifdef __CHECKER__ */
-
 #define __rcu_access_pointer(p, space) \
 ({ \
 	typeof(*p) *_________p1 = (typeof(*p) *__force)READ_ONCE(p); \
@@ -334,54 +336,6 @@ static inline void rcu_preempt_sleep_check(void) { }
 	((typeof(*p) __force __kernel *)(________p1)); \
 })
 
-/**
- * RCU_INITIALIZER() - statically initialize an RCU-protected global variable
- * @v: The value to statically initialize with.
- */
-#define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v)
-
-/**
- * rcu_assign_pointer() - assign to RCU-protected pointer
- * @p: pointer to assign to
- * @v: value to assign (publish)
- *
- * Assigns the specified value to the specified RCU-protected
- * pointer, ensuring that any concurrent RCU readers will see
- * any prior initialization.
- *
- * Inserts memory barriers on architectures that require them
- * (which is most of them), and also prevents the compiler from
- * reordering the code that initializes the structure after the pointer
- * assignment.  More importantly, this call documents which pointers
- * will be dereferenced by RCU read-side code.
- *
- * In some special cases, you may use RCU_INIT_POINTER() instead
- * of rcu_assign_pointer().  RCU_INIT_POINTER() is a bit faster due
- * to the fact that it does not constrain either the CPU or the compiler.
- * That said, using RCU_INIT_POINTER() when you should have used
- * rcu_assign_pointer() is a very bad thing that results in
- * impossible-to-diagnose memory corruption.  So please be careful.
- * See the RCU_INIT_POINTER() comment header for details.
- *
- * Note that rcu_assign_pointer() evaluates each of its arguments only
- * once, appearances notwithstanding.  One of the "extra" evaluations
- * is in typeof() and the other visible only to sparse (__CHECKER__),
- * neither of which actually execute the argument.  As with most cpp
- * macros, this execute-arguments-only-once property is important, so
- * please be careful when making changes to rcu_assign_pointer() and the
- * other macros that it invokes.
- */
-#define rcu_assign_pointer(p, v)					      \
-do {									      \
-	uintptr_t _r_a_p__v = (uintptr_t)(v);				      \
-	rcu_check_sparse(p, __rcu);					      \
-									      \
-	if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL)	      \
-		WRITE_ONCE((p), (typeof(p))(_r_a_p__v));		      \
-	else								      \
-		smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \
-} while (0)
-
 /**
  * rcu_swap_protected() - swap an RCU and a regular pointer
  * @rcu_ptr: RCU pointer
@@ -580,7 +534,7 @@ do {									      \
  *
  * You can avoid reading and understanding the next paragraph by
  * following this rule: don't put anything in an rcu_read_lock() RCU
- * read-side critical section that would block in a !PREEMPT kernel.
+ * read-side critical section that would block in a !PREEMPTION kernel.
  * But if you want the full story, read on!
  *
  * In non-preemptible RCU implementations (TREE_RCU and TINY_RCU),
diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h
index 6fd615a0eea94..138bd1e183e09 100644
--- a/include/linux/rtmutex.h
+++ b/include/linux/rtmutex.h
@@ -14,11 +14,15 @@
 #define __LINUX_RT_MUTEX_H
 
 #include <linux/linkage.h>
+#include <linux/spinlock_types_raw.h>
 #include <linux/rbtree.h>
-#include <linux/spinlock_types.h>
 
 extern int max_lock_depth; /* for sysctl */
 
+#ifdef CONFIG_DEBUG_MUTEXES
+#include <linux/debug_locks.h>
+#endif
+
 /**
  * The rt_mutex structure
  *
@@ -31,8 +35,8 @@ struct rt_mutex {
 	raw_spinlock_t		wait_lock;
 	struct rb_root_cached   waiters;
 	struct task_struct	*owner;
-#ifdef CONFIG_DEBUG_RT_MUTEXES
 	int			save_state;
+#ifdef CONFIG_DEBUG_RT_MUTEXES
 	const char		*name, *file;
 	int			line;
 	void			*magic;
@@ -82,16 +86,23 @@ do { \
 #define __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname)
 #endif
 
-#define __RT_MUTEX_INITIALIZER(mutexname) \
-	{ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \
+#define __RT_MUTEX_INITIALIZER_PLAIN(mutexname) \
+	.wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \
 	, .waiters = RB_ROOT_CACHED \
 	, .owner = NULL \
 	__DEBUG_RT_MUTEX_INITIALIZER(mutexname) \
-	__DEP_MAP_RT_MUTEX_INITIALIZER(mutexname)}
+	__DEP_MAP_RT_MUTEX_INITIALIZER(mutexname)
+
+#define __RT_MUTEX_INITIALIZER(mutexname) \
+	{ __RT_MUTEX_INITIALIZER_PLAIN(mutexname) }
 
 #define DEFINE_RT_MUTEX(mutexname) \
 	struct rt_mutex mutexname = __RT_MUTEX_INITIALIZER(mutexname)
 
+#define __RT_MUTEX_INITIALIZER_SAVE_STATE(mutexname) \
+	{ __RT_MUTEX_INITIALIZER_PLAIN(mutexname)    \
+		, .save_state = 1 }
+
 /**
  * rt_mutex_is_locked - is the mutex locked
  * @lock: the mutex to be queried
@@ -115,6 +126,7 @@ extern void rt_mutex_lock(struct rt_mutex *lock);
 #endif
 
 extern int rt_mutex_lock_interruptible(struct rt_mutex *lock);
+extern int rt_mutex_lock_killable(struct rt_mutex *lock);
 extern int rt_mutex_timed_lock(struct rt_mutex *lock,
 			       struct hrtimer_sleeper *timeout);
 
diff --git a/include/linux/rwlock_rt.h b/include/linux/rwlock_rt.h
new file mode 100644
index 0000000000000..a9c4c2ac4d1fa
--- /dev/null
+++ b/include/linux/rwlock_rt.h
@@ -0,0 +1,119 @@
+#ifndef __LINUX_RWLOCK_RT_H
+#define __LINUX_RWLOCK_RT_H
+
+#ifndef __LINUX_SPINLOCK_H
+#error Do not include directly. Use spinlock.h
+#endif
+
+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_read_trylock(rwlock_t *rwlock);
+extern void __lockfunc rt_write_unlock(rwlock_t *rwlock);
+extern void __lockfunc rt_read_unlock(rwlock_t *rwlock);
+extern int __lockfunc rt_read_can_lock(rwlock_t *rwlock);
+extern int __lockfunc rt_write_can_lock(rwlock_t *rwlock);
+extern void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key);
+
+#define read_can_lock(rwlock)		rt_read_can_lock(rwlock)
+#define write_can_lock(rwlock)		rt_write_can_lock(rwlock)
+
+#define read_trylock(lock)	__cond_lock(lock, rt_read_trylock(lock))
+#define write_trylock(lock)	__cond_lock(lock, rt_write_trylock(lock))
+
+static inline int __write_trylock_rt_irqsave(rwlock_t *lock, unsigned long *flags)
+{
+	/* XXX ARCH_IRQ_ENABLED */
+	*flags = 0;
+	return rt_write_trylock(lock);
+}
+
+#define write_trylock_irqsave(lock, flags)		\
+	__cond_lock(lock, __write_trylock_rt_irqsave(lock, &(flags)))
+
+#define read_lock_irqsave(lock, flags)			\
+	do {						\
+		typecheck(unsigned long, flags);	\
+		rt_read_lock(lock);			\
+		flags = 0;				\
+	} while (0)
+
+#define write_lock_irqsave(lock, flags)			\
+	do {						\
+		typecheck(unsigned long, flags);	\
+		rt_write_lock(lock);			\
+		flags = 0;				\
+	} while (0)
+
+#define read_lock(lock)		rt_read_lock(lock)
+
+#define read_lock_bh(lock)				\
+	do {						\
+		local_bh_disable();			\
+		rt_read_lock(lock);			\
+	} while (0)
+
+#define read_lock_irq(lock)	read_lock(lock)
+
+#define write_lock(lock)	rt_write_lock(lock)
+
+#define write_lock_bh(lock)				\
+	do {						\
+		local_bh_disable();			\
+		rt_write_lock(lock);			\
+	} while (0)
+
+#define write_lock_irq(lock)	write_lock(lock)
+
+#define read_unlock(lock)	rt_read_unlock(lock)
+
+#define read_unlock_bh(lock)				\
+	do {						\
+		rt_read_unlock(lock);			\
+		local_bh_enable();			\
+	} while (0)
+
+#define read_unlock_irq(lock)	read_unlock(lock)
+
+#define write_unlock(lock)	rt_write_unlock(lock)
+
+#define write_unlock_bh(lock)				\
+	do {						\
+		rt_write_unlock(lock);			\
+		local_bh_enable();			\
+	} while (0)
+
+#define write_unlock_irq(lock)	write_unlock(lock)
+
+#define read_unlock_irqrestore(lock, flags)		\
+	do {						\
+		typecheck(unsigned long, flags);	\
+		(void) flags;				\
+		rt_read_unlock(lock);			\
+	} while (0)
+
+#define write_unlock_irqrestore(lock, flags) \
+	do {						\
+		typecheck(unsigned long, flags);	\
+		(void) flags;				\
+		rt_write_unlock(lock);			\
+	} while (0)
+
+#define rwlock_init(rwl)				\
+do {							\
+	static struct lock_class_key __key;		\
+							\
+	__rt_rwlock_init(rwl, #rwl, &__key);		\
+} while (0)
+
+/*
+ * Internal functions made global for CPU pinning
+ */
+void __read_rt_lock(struct rt_rw_lock *lock);
+int __read_rt_trylock(struct rt_rw_lock *lock);
+void __write_rt_lock(struct rt_rw_lock *lock);
+int __write_rt_trylock(struct rt_rw_lock *lock);
+void __read_rt_unlock(struct rt_rw_lock *lock);
+void __write_rt_unlock(struct rt_rw_lock *lock);
+
+#endif
diff --git a/include/linux/rwlock_types.h b/include/linux/rwlock_types.h
index 857a72ceb7942..c21683f3e14af 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
diff --git a/include/linux/rwlock_types_rt.h b/include/linux/rwlock_types_rt.h
new file mode 100644
index 0000000000000..546a1f8f12748
--- /dev/null
+++ b/include/linux/rwlock_types_rt.h
@@ -0,0 +1,55 @@
+#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
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define RW_DEP_MAP_INIT(lockname)	.dep_map = { .name = #lockname }
+#else
+# define RW_DEP_MAP_INIT(lockname)
+#endif
+
+typedef struct rt_rw_lock rwlock_t;
+
+#define __RW_LOCK_UNLOCKED(name) __RWLOCK_RT_INITIALIZER(name)
+
+#define DEFINE_RWLOCK(name) \
+	rwlock_t name = __RW_LOCK_UNLOCKED(name)
+
+/*
+ * A reader biased implementation primarily for CPU pinning.
+ *
+ * Can be selected as general replacement for the single reader RT rwlock
+ * variant
+ */
+struct rt_rw_lock {
+	struct rt_mutex		rtmutex;
+	atomic_t		readers;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	dep_map;
+#endif
+};
+
+#define READER_BIAS	(1U << 31)
+#define WRITER_BIAS	(1U << 30)
+
+#define __RWLOCK_RT_INITIALIZER(name)					\
+{									\
+	.readers = ATOMIC_INIT(READER_BIAS),				\
+	.rtmutex = __RT_MUTEX_INITIALIZER_SAVE_STATE(name.rtmutex),	\
+	RW_DEP_MAP_INIT(name)						\
+}
+
+void __rwlock_biased_rt_init(struct rt_rw_lock *lock, const char *name,
+			     struct lock_class_key *key);
+
+#define rwlock_biased_rt_init(rwlock)					\
+	do {								\
+		static struct lock_class_key __key;			\
+									\
+		__rwlock_biased_rt_init((rwlock), #rwlock, &__key);	\
+	} while (0)
+
+#endif
diff --git a/include/linux/rwsem-rt.h b/include/linux/rwsem-rt.h
new file mode 100644
index 0000000000000..2018ff77904ad
--- /dev/null
+++ b/include/linux/rwsem-rt.h
@@ -0,0 +1,68 @@
+#ifndef _LINUX_RWSEM_RT_H
+#define _LINUX_RWSEM_RT_H
+
+#ifndef _LINUX_RWSEM_H
+#error "Include rwsem.h"
+#endif
+
+#include <linux/rtmutex.h>
+#include <linux/swait.h>
+
+#define READER_BIAS		(1U << 31)
+#define WRITER_BIAS		(1U << 30)
+
+struct rw_semaphore {
+	atomic_t		readers;
+	struct rt_mutex		rtmutex;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	dep_map;
+#endif
+};
+
+#define __RWSEM_INITIALIZER(name)				\
+{								\
+	.readers = ATOMIC_INIT(READER_BIAS),			\
+	.rtmutex = __RT_MUTEX_INITIALIZER(name.rtmutex),	\
+	RW_DEP_MAP_INIT(name)					\
+}
+
+#define DECLARE_RWSEM(lockname) \
+	struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname)
+
+extern void  __rwsem_init(struct rw_semaphore *rwsem, const char *name,
+			  struct lock_class_key *key);
+
+#define __init_rwsem(sem, name, key)			\
+do {							\
+		rt_mutex_init(&(sem)->rtmutex);		\
+		__rwsem_init((sem), (name), (key));	\
+} while (0)
+
+#define init_rwsem(sem)					\
+do {							\
+	static struct lock_class_key __key;		\
+							\
+	__init_rwsem((sem), #sem, &__key);		\
+} while (0)
+
+static inline int rwsem_is_locked(struct rw_semaphore *sem)
+{
+	return atomic_read(&sem->readers) != READER_BIAS;
+}
+
+static inline int rwsem_is_contended(struct rw_semaphore *sem)
+{
+	return atomic_read(&sem->readers) > 0;
+}
+
+extern void __down_read(struct rw_semaphore *sem);
+extern int __down_read_killable(struct rw_semaphore *sem);
+extern int __down_read_trylock(struct rw_semaphore *sem);
+extern void __down_write(struct rw_semaphore *sem);
+extern int __must_check __down_write_killable(struct rw_semaphore *sem);
+extern int __down_write_trylock(struct rw_semaphore *sem);
+extern void __up_read(struct rw_semaphore *sem);
+extern void __up_write(struct rw_semaphore *sem);
+extern void __downgrade_write(struct rw_semaphore *sem);
+
+#endif
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 00d6054687dd2..b240dd987834f 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -16,6 +16,11 @@
 #include <linux/spinlock.h>
 #include <linux/atomic.h>
 #include <linux/err.h>
+
+#ifdef CONFIG_PREEMPT_RT
+#include <linux/rwsem-rt.h>
+#else /* PREEMPT_RT */
+
 #ifdef CONFIG_RWSEM_SPIN_ON_OWNER
 #include <linux/osq_lock.h>
 #endif
@@ -121,6 +126,13 @@ static inline int rwsem_is_contended(struct rw_semaphore *sem)
 	return !list_empty(&sem->wait_list);
 }
 
+#endif /* !PREEMPT_RT */
+
+/*
+ * The functions below are the same for all rwsem implementations including
+ * the RT specific variant.
+ */
+
 /*
  * lock for reading
  */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 775503573ed70..c9e3aa38ce349 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -31,6 +31,7 @@
 #include <linux/task_io_accounting.h>
 #include <linux/posix-timers.h>
 #include <linux/rseq.h>
+#include <asm/kmap_types.h>
 
 /* task_struct member predeclarations (sorted alphabetically): */
 struct audit_context;
@@ -107,12 +108,8 @@ struct task_group;
 					 __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \
 					 TASK_PARKED)
 
-#define task_is_traced(task)		((task->state & __TASK_TRACED) != 0)
-
 #define task_is_stopped(task)		((task->state & __TASK_STOPPED) != 0)
 
-#define task_is_stopped_or_traced(task)	((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
-
 #define task_contributes_to_load(task)	((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
 					 (task->flags & PF_FROZEN) == 0 && \
 					 (task->state & TASK_NOLOAD) == 0)
@@ -140,6 +137,9 @@ struct task_group;
 		smp_store_mb(current->state, (state_value));	\
 	} while (0)
 
+#define __set_current_state_no_track(state_value)		\
+	current->state = (state_value);
+
 #define set_special_state(state_value)					\
 	do {								\
 		unsigned long flags; /* may shadow */			\
@@ -149,6 +149,7 @@ struct task_group;
 		current->state = (state_value);				\
 		raw_spin_unlock_irqrestore(&current->pi_lock, flags);	\
 	} while (0)
+
 #else
 /*
  * set_current_state() includes a barrier so that the write of current->state
@@ -193,6 +194,9 @@ struct task_group;
 #define set_current_state(state_value)					\
 	smp_store_mb(current->state, (state_value))
 
+#define __set_current_state_no_track(state_value)	\
+	__set_current_state(state_value)
+
 /*
  * set_special_state() should be used for those states when the blocking task
  * can not use the regular condition based wait-loop. In that case we must
@@ -230,6 +234,8 @@ extern void io_schedule_finish(int token);
 extern long io_schedule_timeout(long timeout);
 extern void io_schedule(void);
 
+int cpu_nr_pinned(int cpu);
+
 /**
  * struct prev_cputime - snapshot of system and user cputime
  * @utime: time spent in user mode
@@ -631,6 +637,8 @@ struct task_struct {
 #endif
 	/* -1 unrunnable, 0 runnable, >0 stopped: */
 	volatile long			state;
+	/* saved state for "spinlock sleepers" */
+	volatile long			saved_state;
 
 	/*
 	 * This begins the randomizable portion of task_struct. Only
@@ -700,6 +708,20 @@ struct task_struct {
 	int				nr_cpus_allowed;
 	const cpumask_t			*cpus_ptr;
 	cpumask_t			cpus_mask;
+#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT)
+	int				migrate_disable;
+	bool				migrate_disable_scheduled;
+# ifdef CONFIG_SCHED_DEBUG
+	int				pinned_on_cpu;
+# endif
+#elif !defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT)
+# ifdef CONFIG_SCHED_DEBUG
+	int				migrate_disable;
+# endif
+#endif
+#ifdef CONFIG_PREEMPT_RT
+	int				sleeping_lock;
+#endif
 
 #ifdef CONFIG_PREEMPT_RCU
 	int				rcu_read_lock_nesting;
@@ -913,11 +935,17 @@ struct task_struct {
 	/* Signal handlers: */
 	struct signal_struct		*signal;
 	struct sighand_struct		*sighand;
+	struct sigqueue			*sigqueue_cache;
+
 	sigset_t			blocked;
 	sigset_t			real_blocked;
 	/* Restored if set_restore_sigmask() was used: */
 	sigset_t			saved_sigmask;
 	struct sigpending		pending;
+#ifdef CONFIG_PREEMPT_RT
+	/* TODO: move me into ->restart_block ? */
+	struct				kernel_siginfo forced_info;
+#endif
 	unsigned long			sas_ss_sp;
 	size_t				sas_ss_size;
 	unsigned int			sas_ss_flags;
@@ -944,6 +972,7 @@ struct task_struct {
 	raw_spinlock_t			pi_lock;
 
 	struct wake_q_node		wake_q;
+	struct wake_q_node		wake_q_sleeper;
 
 #ifdef CONFIG_RT_MUTEXES
 	/* PI waiters blocked on a rt_mutex held by this task: */
@@ -978,6 +1007,9 @@ struct task_struct {
 	int				softirqs_enabled;
 	int				softirq_context;
 #endif
+#ifdef CONFIG_PREEMPT_RT
+	int				softirq_count;
+#endif
 
 #ifdef CONFIG_LOCKDEP
 # define MAX_LOCK_DEPTH			48UL
@@ -1241,6 +1273,12 @@ struct task_struct {
 	unsigned int			sequential_io;
 	unsigned int			sequential_io_avg;
 #endif
+#ifdef CONFIG_PREEMPT_RT
+# if defined CONFIG_HIGHMEM || defined CONFIG_X86_32
+	int				kmap_idx;
+	pte_t				kmap_pte[KM_TYPE_NR];
+# endif
+#endif
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 	unsigned long			task_state_change;
 #endif
@@ -1672,6 +1710,7 @@ extern struct task_struct *find_get_task_by_vpid(pid_t nr);
 
 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
@@ -1754,6 +1793,89 @@ static inline int test_tsk_need_resched(struct task_struct *tsk)
 	return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED));
 }
 
+#ifdef CONFIG_PREEMPT_LAZY
+static inline void set_tsk_need_resched_lazy(struct task_struct *tsk)
+{
+	set_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY);
+}
+
+static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk)
+{
+	clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY);
+}
+
+static inline int test_tsk_need_resched_lazy(struct task_struct *tsk)
+{
+	return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY));
+}
+
+static inline int need_resched_lazy(void)
+{
+	return test_thread_flag(TIF_NEED_RESCHED_LAZY);
+}
+
+static inline int need_resched_now(void)
+{
+	return test_thread_flag(TIF_NEED_RESCHED);
+}
+
+#else
+static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk) { }
+static inline int need_resched_lazy(void) { return 0; }
+
+static inline int need_resched_now(void)
+{
+	return test_thread_flag(TIF_NEED_RESCHED);
+}
+
+#endif
+
+
+static inline bool __task_is_stopped_or_traced(struct task_struct *task)
+{
+	if (task->state & (__TASK_STOPPED | __TASK_TRACED))
+		return true;
+#ifdef CONFIG_PREEMPT_RT
+	if (task->saved_state & (__TASK_STOPPED | __TASK_TRACED))
+		return true;
+#endif
+	return false;
+}
+
+static inline bool task_is_stopped_or_traced(struct task_struct *task)
+{
+	bool traced_stopped;
+
+#ifdef CONFIG_PREEMPT_RT
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&task->pi_lock, flags);
+	traced_stopped = __task_is_stopped_or_traced(task);
+	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
+#else
+	traced_stopped = __task_is_stopped_or_traced(task);
+#endif
+	return traced_stopped;
+}
+
+static inline bool task_is_traced(struct task_struct *task)
+{
+	bool traced = false;
+
+	if (task->state & __TASK_TRACED)
+		return true;
+#ifdef CONFIG_PREEMPT_RT
+	/* in case the task is sleeping on tasklist_lock */
+	raw_spin_lock_irq(&task->pi_lock);
+	if (task->state & __TASK_TRACED)
+		traced = true;
+	else if (task->saved_state & __TASK_TRACED)
+		traced = true;
+	raw_spin_unlock_irq(&task->pi_lock);
+#endif
+	return traced;
+}
+
 /*
  * cond_resched() and cond_resched_lock(): latency reduction via
  * explicit rescheduling in places that are safe. The return
@@ -1806,6 +1928,23 @@ static __always_inline bool need_resched(void)
 	return unlikely(tif_need_resched());
 }
 
+#ifdef CONFIG_PREEMPT_RT
+static inline void sleeping_lock_inc(void)
+{
+	current->sleeping_lock++;
+}
+
+static inline void sleeping_lock_dec(void)
+{
+	current->sleeping_lock--;
+}
+
+#else
+
+static inline void sleeping_lock_inc(void) { }
+static inline void sleeping_lock_dec(void) { }
+#endif
+
 /*
  * Wrappers for p->thread_info->cpu access. No-op on UP.
  */
@@ -1997,4 +2136,6 @@ int sched_trace_rq_cpu(struct rq *rq);
 
 const struct cpumask *sched_trace_rd_span(struct root_domain *rd);
 
+extern struct task_struct *takedown_cpu_task;
+
 #endif
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index c49257a3b5108..2a498fc3d949f 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -49,6 +49,17 @@ static inline void mmdrop(struct mm_struct *mm)
 		__mmdrop(mm);
 }
 
+#ifdef CONFIG_PREEMPT_RT
+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
+
 /*
  * This has to be called after a get_task_mm()/mmget_not_zero()
  * followed by taking the mmap_sem for writing before modifying the
diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h
index 26a2013ac39c4..6e2dff721547c 100644
--- a/include/linux/sched/wake_q.h
+++ b/include/linux/sched/wake_q.h
@@ -58,6 +58,17 @@ static inline bool wake_q_empty(struct wake_q_head *head)
 
 extern void wake_q_add(struct wake_q_head *head, struct task_struct *task);
 extern void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task);
-extern void wake_up_q(struct wake_q_head *head);
+extern void wake_q_add_sleeper(struct wake_q_head *head, struct task_struct *task);
+extern void __wake_up_q(struct wake_q_head *head, bool sleeper);
+
+static inline void wake_up_q(struct wake_q_head *head)
+{
+	__wake_up_q(head, false);
+}
+
+static inline void wake_up_q_sleeper(struct wake_q_head *head)
+{
+	__wake_up_q(head, true);
+}
 
 #endif /* _LINUX_SCHED_WAKE_Q_H */
diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h
index bcf4cf26b8c89..bc458c2658e4d 100644
--- a/include/linux/seqlock.h
+++ b/include/linux/seqlock.h
@@ -221,20 +221,30 @@ static inline int read_seqcount_retry(const seqcount_t *s, unsigned start)
 	return __read_seqcount_retry(s, start);
 }
 
-
-
-static inline void raw_write_seqcount_begin(seqcount_t *s)
+static inline void __raw_write_seqcount_begin(seqcount_t *s)
 {
 	s->sequence++;
 	smp_wmb();
 }
 
-static inline void raw_write_seqcount_end(seqcount_t *s)
+static inline void raw_write_seqcount_begin(seqcount_t *s)
+{
+	preempt_disable_rt();
+	__raw_write_seqcount_begin(s);
+}
+
+static inline void __raw_write_seqcount_end(seqcount_t *s)
 {
 	smp_wmb();
 	s->sequence++;
 }
 
+static inline void raw_write_seqcount_end(seqcount_t *s)
+{
+	__raw_write_seqcount_end(s);
+	preempt_enable_rt();
+}
+
 /**
  * raw_write_seqcount_barrier - do a seq write barrier
  * @s: pointer to seqcount_t
@@ -428,10 +438,33 @@ typedef struct {
 /*
  * Read side functions for starting and finalizing a read side section.
  */
+#ifndef CONFIG_PREEMPT_RT
 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 = READ_ONCE(sl->seqcount.sequence);
+	if (unlikely(ret & 1)) {
+		/*
+		 * Take the lock and let the writer proceed (i.e. evtl
+		 * boost it), otherwise we could loop here forever.
+		 */
+		spin_unlock_wait(&sl->lock);
+		goto repeat;
+	}
+	smp_rmb();
+	return ret;
+}
+#endif
 
 static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
 {
@@ -446,36 +479,45 @@ static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start)
 static inline void write_seqlock(seqlock_t *sl)
 {
 	spin_lock(&sl->lock);
-	write_seqcount_begin(&sl->seqcount);
+	__raw_write_seqcount_begin(&sl->seqcount);
+}
+
+static inline int try_write_seqlock(seqlock_t *sl)
+{
+	if (spin_trylock(&sl->lock)) {
+		__raw_write_seqcount_begin(&sl->seqcount);
+		return 1;
+	}
+	return 0;
 }
 
 static inline void write_sequnlock(seqlock_t *sl)
 {
-	write_seqcount_end(&sl->seqcount);
+	__raw_write_seqcount_end(&sl->seqcount);
 	spin_unlock(&sl->lock);
 }
 
 static inline void write_seqlock_bh(seqlock_t *sl)
 {
 	spin_lock_bh(&sl->lock);
-	write_seqcount_begin(&sl->seqcount);
+	__raw_write_seqcount_begin(&sl->seqcount);
 }
 
 static inline void write_sequnlock_bh(seqlock_t *sl)
 {
-	write_seqcount_end(&sl->seqcount);
+	__raw_write_seqcount_end(&sl->seqcount);
 	spin_unlock_bh(&sl->lock);
 }
 
 static inline void write_seqlock_irq(seqlock_t *sl)
 {
 	spin_lock_irq(&sl->lock);
-	write_seqcount_begin(&sl->seqcount);
+	__raw_write_seqcount_begin(&sl->seqcount);
 }
 
 static inline void write_sequnlock_irq(seqlock_t *sl)
 {
-	write_seqcount_end(&sl->seqcount);
+	__raw_write_seqcount_end(&sl->seqcount);
 	spin_unlock_irq(&sl->lock);
 }
 
@@ -484,7 +526,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl)
 	unsigned long flags;
 
 	spin_lock_irqsave(&sl->lock, flags);
-	write_seqcount_begin(&sl->seqcount);
+	__raw_write_seqcount_begin(&sl->seqcount);
 	return flags;
 }
 
@@ -494,7 +536,7 @@ static inline unsigned long __write_seqlock_irqsave(seqlock_t *sl)
 static inline void
 write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags)
 {
-	write_seqcount_end(&sl->seqcount);
+	__raw_write_seqcount_end(&sl->seqcount);
 	spin_unlock_irqrestore(&sl->lock, flags);
 }
 
diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h
index bb2bc99388cae..be74bb7cae64f 100644
--- a/include/linux/serial_8250.h
+++ b/include/linux/serial_8250.h
@@ -7,6 +7,7 @@
 #ifndef _LINUX_SERIAL_8250_H
 #define _LINUX_SERIAL_8250_H
 
+#include <linux/atomic.h>
 #include <linux/serial_core.h>
 #include <linux/serial_reg.h>
 #include <linux/platform_device.h>
@@ -123,6 +124,8 @@ struct uart_8250_port {
 #define MSR_SAVE_FLAGS UART_MSR_ANY_DELTA
 	unsigned char		msr_saved_flags;
 
+	atomic_t		console_printing;
+
 	struct uart_8250_dma	*dma;
 	const struct uart_8250_ops *ops;
 
@@ -174,6 +177,8 @@ void serial8250_init_port(struct uart_8250_port *up);
 void serial8250_set_defaults(struct uart_8250_port *up);
 void serial8250_console_write(struct uart_8250_port *up, const char *s,
 			      unsigned int count);
+void serial8250_console_write_atomic(struct uart_8250_port *up, const char *s,
+				     unsigned int count);
 int serial8250_console_setup(struct uart_port *port, char *options, bool probe);
 
 extern void serial8250_set_isa_configurator(void (*v)
diff --git a/include/linux/signal.h b/include/linux/signal.h
index 1a5f88316b081..1870c233799ee 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -255,6 +255,7 @@ static inline void init_sigpending(struct sigpending *sig)
 }
 
 extern void flush_sigqueue(struct sigpending *queue);
+extern void flush_task_sigqueue(struct task_struct *tsk);
 
 /* Test if 'sig' is valid signal. Use this instead of testing _NSIG directly */
 static inline int valid_signal(unsigned long sig)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 1ba6e2cc27250..2405012f471b6 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -293,6 +293,7 @@ struct sk_buff_head {
 
 	__u32		qlen;
 	spinlock_t	lock;
+	raw_spinlock_t	raw_lock;
 };
 
 struct sk_buff;
@@ -1844,6 +1845,12 @@ static inline void skb_queue_head_init(struct sk_buff_head *list)
 	__skb_queue_head_init(list);
 }
 
+static inline void skb_queue_head_init_raw(struct sk_buff_head *list)
+{
+	raw_spin_lock_init(&list->raw_lock);
+	__skb_queue_head_init(list);
+}
+
 static inline void skb_queue_head_init_class(struct sk_buff_head *list,
 		struct lock_class_key *class)
 {
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 6fc856c9eda58..3b9b782e59088 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -222,6 +222,9 @@ static inline int get_boot_cpu_id(void)
 #define get_cpu()		({ preempt_disable(); __smp_processor_id(); })
 #define put_cpu()		preempt_enable()
 
+#define get_cpu_light()		({ migrate_disable(); __smp_processor_id(); })
+#define put_cpu_light()		migrate_enable()
+
 /*
  * Callback to arch code if there's nosmp or maxcpus=0 on the
  * boot command line:
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index 031ce8617df8f..826ddd48e6059 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -307,7 +307,11 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
 })
 
 /* Include rwlock functions */
-#include <linux/rwlock.h>
+#ifdef CONFIG_PREEMPT_RT
+# include <linux/rwlock_rt.h>
+#else
+# include <linux/rwlock.h>
+#endif
 
 /*
  * Pull the _spin_*()/_read_*()/_write_*() functions/declarations:
@@ -318,6 +322,10 @@ static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock)
 # include <linux/spinlock_api_up.h>
 #endif
 
+#ifdef CONFIG_PREEMPT_RT
+# include <linux/spinlock_rt.h>
+#else /* PREEMPT_RT */
+
 /*
  * Map the spin_lock functions to the raw variants for PREEMPT_RT=n
  */
@@ -438,6 +446,8 @@ static __always_inline int spin_is_contended(spinlock_t *lock)
 
 #define assert_spin_locked(lock)	assert_raw_spin_locked(&(lock)->rlock)
 
+#endif /* !PREEMPT_RT */
+
 /*
  * Pull the atomic_t declaration:
  * (asm-mips/atomic.h needs above definitions)
diff --git a/include/linux/spinlock_api_smp.h b/include/linux/spinlock_api_smp.h
index b762eaba4cdf4..60f593969fe13 100644
--- a/include/linux/spinlock_api_smp.h
+++ b/include/linux/spinlock_api_smp.h
@@ -187,6 +187,8 @@ static inline int __raw_spin_trylock_bh(raw_spinlock_t *lock)
 	return 0;
 }
 
-#include <linux/rwlock_api_smp.h>
+#ifndef CONFIG_PREEMPT_RT
+# 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 0000000000000..3696a77fa77d6
--- /dev/null
+++ b/include/linux/spinlock_rt.h
@@ -0,0 +1,156 @@
+#ifndef __LINUX_SPINLOCK_RT_H
+#define __LINUX_SPINLOCK_RT_H
+
+#ifndef __LINUX_SPINLOCK_H
+#error Do not include directly. Use spinlock.h
+#endif
+
+#include <linux/bug.h>
+
+extern void
+__rt_spin_lock_init(spinlock_t *lock, const 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_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.
+ * Migrate disable handling must be done at the call site.
+ */
+extern void __lockfunc __rt_spin_lock(struct rt_mutex *lock);
+extern void __lockfunc __rt_spin_trylock(struct rt_mutex *lock);
+extern void __lockfunc __rt_spin_unlock(struct rt_mutex *lock);
+
+#define spin_lock(lock)			rt_spin_lock(lock)
+
+#define spin_lock_bh(lock)			\
+	do {					\
+		local_bh_disable();		\
+		rt_spin_lock(lock);		\
+	} while (0)
+
+#define spin_lock_irq(lock)		spin_lock(lock)
+
+#define spin_do_trylock(lock)		__cond_lock(lock, rt_spin_trylock(lock))
+
+#define spin_trylock(lock)			\
+({						\
+	int __locked;				\
+	__locked = spin_do_trylock(lock);	\
+	__locked;				\
+})
+
+#ifdef CONFIG_LOCKDEP
+# define spin_lock_nested(lock, subclass)		\
+	do {						\
+		rt_spin_lock_nested(lock, subclass);	\
+	} while (0)
+
+#define spin_lock_bh_nested(lock, subclass)		\
+	do {						\
+		local_bh_disable();			\
+		rt_spin_lock_nested(lock, subclass);	\
+	} while (0)
+
+# define spin_lock_irqsave_nested(lock, flags, subclass) \
+	do {						 \
+		typecheck(unsigned long, flags);	 \
+		flags = 0;				 \
+		rt_spin_lock_nested(lock, subclass);	 \
+	} while (0)
+#else
+# define spin_lock_nested(lock, subclass)	spin_lock(lock)
+# define spin_lock_bh_nested(lock, subclass)	spin_lock_bh(lock)
+
+# define spin_lock_irqsave_nested(lock, flags, subclass) \
+	do {						 \
+		typecheck(unsigned long, flags);	 \
+		flags = 0;				 \
+		spin_lock(lock);			 \
+	} while (0)
+#endif
+
+#define spin_lock_irqsave(lock, flags)			 \
+	do {						 \
+		typecheck(unsigned long, flags);	 \
+		flags = 0;				 \
+		spin_lock(lock);			 \
+	} while (0)
+
+static inline unsigned long spin_lock_trace_flags(spinlock_t *lock)
+{
+	unsigned long flags = 0;
+#ifdef CONFIG_TRACE_IRQFLAGS
+	flags = rt_spin_lock_trace_flags(lock);
+#else
+	spin_lock(lock); /* lock_local */
+#endif
+	return flags;
+}
+
+/* FIXME: we need rt_spin_lock_nest_lock */
+#define spin_lock_nest_lock(lock, nest_lock) spin_lock_nested(lock, 0)
+
+#define spin_unlock(lock)			rt_spin_unlock(lock)
+
+#define spin_unlock_bh(lock)				\
+	do {						\
+		rt_spin_unlock(lock);			\
+		local_bh_enable();			\
+	} while (0)
+
+#define spin_unlock_irq(lock)		spin_unlock(lock)
+
+#define spin_unlock_irqrestore(lock, flags)		\
+	do {						\
+		typecheck(unsigned long, flags);	\
+		(void) flags;				\
+		spin_unlock(lock);			\
+	} while (0)
+
+#define spin_trylock_bh(lock)	__cond_lock(lock, rt_spin_trylock_bh(lock))
+#define spin_trylock_irq(lock)	spin_trylock(lock)
+
+#define spin_trylock_irqsave(lock, flags)	\
+	rt_spin_trylock_irqsave(lock, &(flags))
+
+#define spin_unlock_wait(lock)		rt_spin_unlock_wait(lock)
+
+#ifdef CONFIG_GENERIC_LOCKBREAK
+# define spin_is_contended(lock)	((lock)->break_lock)
+#else
+# define spin_is_contended(lock)	(((void)(lock), 0))
+#endif
+
+static inline int spin_can_lock(spinlock_t *lock)
+{
+	return !rt_mutex_is_locked(&lock->lock);
+}
+
+static inline int spin_is_locked(spinlock_t *lock)
+{
+	return rt_mutex_is_locked(&lock->lock);
+}
+
+static inline void assert_spin_locked(spinlock_t *lock)
+{
+	BUG_ON(!spin_is_locked(lock));
+}
+
+#endif
diff --git a/include/linux/spinlock_types.h b/include/linux/spinlock_types.h
index 24b4e6f2c1a22..8d896d3e1a017 100644
--- a/include/linux/spinlock_types.h
+++ b/include/linux/spinlock_types.h
@@ -9,77 +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
+# 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_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 0000000000000..f1dac1fb1d6ac
--- /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 0000000000000..822bf64a61d3b
--- /dev/null
+++ b/include/linux/spinlock_types_raw.h
@@ -0,0 +1,55 @@
+#ifndef __LINUX_SPINLOCK_TYPES_RAW_H
+#define __LINUX_SPINLOCK_TYPES_RAW_H
+
+#include <linux/types.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_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 0000000000000..3e3d8c5f7a9ad
--- /dev/null
+++ b/include/linux/spinlock_types_rt.h
@@ -0,0 +1,48 @@
+#ifndef __LINUX_SPINLOCK_TYPES_RT_H
+#define __LINUX_SPINLOCK_TYPES_RT_H
+
+#ifndef __LINUX_SPINLOCK_TYPES_H
+#error "Do not include directly. Include spinlock_types.h instead"
+#endif
+
+#include <linux/cache.h>
+
+/*
+ * PREEMPT_RT: spinlocks - an RT mutex plus lock-break field:
+ */
+typedef struct spinlock {
+	struct rt_mutex		lock;
+	unsigned int		break_lock;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	dep_map;
+#endif
+} spinlock_t;
+
+#ifdef CONFIG_DEBUG_RT_MUTEXES
+# define __RT_SPIN_INITIALIZER(name) \
+	{ \
+	.wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \
+	.save_state = 1, \
+	.file = __FILE__, \
+	.line = __LINE__ , \
+	}
+#else
+# define __RT_SPIN_INITIALIZER(name) \
+	{								\
+	.wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock),		\
+	.save_state = 1, \
+	}
+#endif
+
+/*
+.wait_list = PLIST_HEAD_INIT_RAW((name).lock.wait_list, (name).lock.wait_lock)
+*/
+
+#define __SPIN_LOCK_UNLOCKED(name)			\
+	{ .lock = __RT_SPIN_INITIALIZER(name.lock),		\
+	  SPIN_DEP_MAP_INIT(name) }
+
+#define DEFINE_SPINLOCK(name) \
+	spinlock_t name = __SPIN_LOCK_UNLOCKED(name)
+
+#endif
diff --git a/include/linux/spinlock_types_up.h b/include/linux/spinlock_types_up.h
index c09b6407ae1b3..b0243ba07fb78 100644
--- a/include/linux/spinlock_types_up.h
+++ b/include/linux/spinlock_types_up.h
@@ -1,10 +1,6 @@
 #ifndef __LINUX_SPINLOCK_TYPES_UP_H
 #define __LINUX_SPINLOCK_TYPES_UP_H
 
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
 /*
  * include/linux/spinlock_types_up.h - spinlock type definitions for UP
  *
diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index f9a0c6189852e..27d32887103dd 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -26,6 +26,8 @@ struct cpu_stop_work {
 	cpu_stop_fn_t		fn;
 	void			*arg;
 	struct cpu_stop_done	*done;
+	/* Did not run due to disabled stopper; for nowait debug checks */
+	bool			disabled;
 };
 
 int stop_one_cpu(unsigned int cpu, cpu_stop_fn_t fn, void *arg);
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 6fc8843f1c9e9..dd0c894fb1090 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -197,6 +197,12 @@ struct platform_s2idle_ops {
 	void (*end)(void);
 };
 
+#if defined(CONFIG_SUSPEND) || defined(CONFIG_HIBERNATION)
+extern bool pm_in_action;
+#else
+# define pm_in_action false
+#endif
+
 #ifdef CONFIG_SUSPEND
 extern suspend_state_t mem_sleep_current;
 extern suspend_state_t mem_sleep_default;
diff --git a/include/linux/swait.h b/include/linux/swait.h
index 73e06e9986d4b..21ae66cd41d30 100644
--- a/include/linux/swait.h
+++ b/include/linux/swait.h
@@ -160,7 +160,9 @@ static inline bool swq_has_sleeper(struct swait_queue_head *wq)
 extern void swake_up_one(struct swait_queue_head *q);
 extern void swake_up_all(struct swait_queue_head *q);
 extern void swake_up_locked(struct swait_queue_head *q);
+extern void swake_up_all_locked(struct swait_queue_head *q);
 
+extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait);
 extern void prepare_to_swait_exclusive(struct swait_queue_head *q, struct swait_queue *wait, int state);
 extern long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state);
 
@@ -297,4 +299,18 @@ do {									\
 	__ret;								\
 })
 
+#define __swait_event_lock_irq(wq, condition, lock, cmd)		\
+	___swait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0,		\
+		       raw_spin_unlock_irq(&lock);			\
+		       cmd;						\
+		       schedule();					\
+		       raw_spin_lock_irq(&lock))
+
+#define swait_event_lock_irq(wq_head, condition, lock)			\
+	do {								\
+		if (condition)						\
+			break;						\
+		__swait_event_lock_irq(wq_head, condition, lock, );	\
+	} while (0)
+
 #endif /* _LINUX_SWAIT_H */
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index 659a4400517b2..6aed0d0b97ce0 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -97,7 +97,17 @@ static inline int test_ti_thread_flag(struct thread_info *ti, int flag)
 #define test_thread_flag(flag) \
 	test_ti_thread_flag(current_thread_info(), flag)
 
-#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED)
+#ifdef CONFIG_PREEMPT_LAZY
+#define tif_need_resched()	(test_thread_flag(TIF_NEED_RESCHED) || \
+				 test_thread_flag(TIF_NEED_RESCHED_LAZY))
+#define tif_need_resched_now()	(test_thread_flag(TIF_NEED_RESCHED))
+#define tif_need_resched_lazy()	test_thread_flag(TIF_NEED_RESCHED_LAZY))
+
+#else
+#define tif_need_resched()	test_thread_flag(TIF_NEED_RESCHED)
+#define tif_need_resched_now()	test_thread_flag(TIF_NEED_RESCHED)
+#define tif_need_resched_lazy()	0
+#endif
 
 #ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES
 static inline int arch_within_stack_frames(const void * const stack,
diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index 30a8cdcfd4a4f..f3b1ef07e4a5f 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -62,6 +62,9 @@ struct trace_entry {
 	unsigned char		flags;
 	unsigned char		preempt_count;
 	int			pid;
+	unsigned short		migrate_disable;
+	unsigned short		padding;
+	unsigned char		preempt_lazy_count;
 };
 
 #define TRACE_EVENT_TYPE_MAX						\
diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index d4ee6e9425625..2761659101c2e 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -182,6 +182,7 @@ static __always_inline void pagefault_disabled_dec(void)
  */
 static inline void pagefault_disable(void)
 {
+	migrate_disable();
 	pagefault_disabled_inc();
 	/*
 	 * make sure to have issued the store before a pagefault
@@ -198,6 +199,7 @@ static inline void pagefault_enable(void)
 	 */
 	barrier();
 	pagefault_disabled_dec();
+	migrate_enable();
 }
 
 /*
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index bdeda4b079fe8..dec95902b138c 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -54,7 +54,9 @@ DECLARE_PER_CPU(struct vm_event_state, vm_event_states);
  */
 static inline void __count_vm_event(enum vm_event_item item)
 {
+	preempt_disable_rt();
 	raw_cpu_inc(vm_event_states.event[item]);
+	preempt_enable_rt();
 }
 
 static inline void count_vm_event(enum vm_event_item item)
@@ -64,7 +66,9 @@ static inline void count_vm_event(enum vm_event_item item)
 
 static inline void __count_vm_events(enum vm_event_item item, long delta)
 {
+	preempt_disable_rt();
 	raw_cpu_add(vm_event_states.event[item], delta);
+	preempt_enable_rt();
 }
 
 static inline void count_vm_events(enum vm_event_item item, long delta)
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 3eb7cae8206c3..2090f205b5c68 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -10,6 +10,7 @@
 
 #include <asm/current.h>
 #include <uapi/linux/wait.h>
+#include <linux/atomic.h>
 
 typedef struct wait_queue_entry wait_queue_entry_t;
 
diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h
index ca23860adbb95..599572f9dcd1d 100644
--- a/include/net/gen_stats.h
+++ b/include/net/gen_stats.h
@@ -6,6 +6,7 @@
 #include <linux/socket.h>
 #include <linux/rtnetlink.h>
 #include <linux/pkt_sched.h>
+#include <net/net_seq_lock.h>
 
 struct gnet_stats_basic_cpu {
 	struct gnet_stats_basic_packed bstats;
@@ -36,15 +37,15 @@ int gnet_stats_start_copy_compat(struct sk_buff *skb, int type,
 				 spinlock_t *lock, struct gnet_dump *d,
 				 int padattr);
 
-int gnet_stats_copy_basic(const seqcount_t *running,
+int gnet_stats_copy_basic(net_seqlock_t *running,
 			  struct gnet_dump *d,
 			  struct gnet_stats_basic_cpu __percpu *cpu,
 			  struct gnet_stats_basic_packed *b);
-void __gnet_stats_copy_basic(const seqcount_t *running,
+void __gnet_stats_copy_basic(net_seqlock_t *running,
 			     struct gnet_stats_basic_packed *bstats,
 			     struct gnet_stats_basic_cpu __percpu *cpu,
 			     struct gnet_stats_basic_packed *b);
-int gnet_stats_copy_basic_hw(const seqcount_t *running,
+int gnet_stats_copy_basic_hw(net_seqlock_t *running,
 			     struct gnet_dump *d,
 			     struct gnet_stats_basic_cpu __percpu *cpu,
 			     struct gnet_stats_basic_packed *b);
@@ -64,13 +65,13 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
 		      struct gnet_stats_basic_cpu __percpu *cpu_bstats,
 		      struct net_rate_estimator __rcu **rate_est,
 		      spinlock_t *lock,
-		      seqcount_t *running, struct nlattr *opt);
+		      net_seqlock_t *running, struct nlattr *opt);
 void gen_kill_estimator(struct net_rate_estimator __rcu **ptr);
 int gen_replace_estimator(struct gnet_stats_basic_packed *bstats,
 			  struct gnet_stats_basic_cpu __percpu *cpu_bstats,
 			  struct net_rate_estimator __rcu **ptr,
 			  spinlock_t *lock,
-			  seqcount_t *running, struct nlattr *opt);
+			  net_seqlock_t *running, struct nlattr *opt);
 bool gen_estimator_active(struct net_rate_estimator __rcu **ptr);
 bool gen_estimator_read(struct net_rate_estimator __rcu **ptr,
 			struct gnet_stats_rate_est64 *sample);
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index b8452cc0e059f..224625e2354e8 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -460,7 +460,7 @@ static inline int neigh_hh_bridge(struct hh_cache *hh, struct sk_buff *skb)
 }
 #endif
 
-static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb)
+static inline int neigh_hh_output(struct hh_cache *hh, struct sk_buff *skb)
 {
 	unsigned int hh_alen = 0;
 	unsigned int seq;
@@ -503,7 +503,7 @@ static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb
 static inline int neigh_output(struct neighbour *n, struct sk_buff *skb,
 			       bool skip_cache)
 {
-	const struct hh_cache *hh = &n->hh;
+	struct hh_cache *hh = &n->hh;
 
 	if ((n->nud_state & NUD_CONNECTED) && hh->hh_len && !skip_cache)
 		return neigh_hh_output(hh, skb);
@@ -544,7 +544,7 @@ struct neighbour_cb {
 
 #define NEIGH_CB(skb)	((struct neighbour_cb *)(skb)->cb)
 
-static inline void neigh_ha_snapshot(char *dst, const struct neighbour *n,
+static inline void neigh_ha_snapshot(char *dst, struct neighbour *n,
 				     const struct net_device *dev)
 {
 	unsigned int seq;
diff --git a/include/net/net_seq_lock.h b/include/net/net_seq_lock.h
new file mode 100644
index 0000000000000..67710bace7418
--- /dev/null
+++ b/include/net/net_seq_lock.h
@@ -0,0 +1,15 @@
+#ifndef __NET_NET_SEQ_LOCK_H__
+#define __NET_NET_SEQ_LOCK_H__
+
+#ifdef CONFIG_PREEMPT_RT
+# define net_seqlock_t			seqlock_t
+# define net_seq_begin(__r)		read_seqbegin(__r)
+# define net_seq_retry(__r, __s)	read_seqretry(__r, __s)
+
+#else
+# define net_seqlock_t			seqcount_t
+# define net_seq_begin(__r)		read_seqcount_begin(__r)
+# define net_seq_retry(__r, __s)	read_seqcount_retry(__r, __s)
+#endif
+
+#endif
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index d80acda231ae2..58b830bd7a1e0 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -10,6 +10,7 @@
 #include <linux/percpu.h>
 #include <linux/dynamic_queue_limits.h>
 #include <linux/list.h>
+#include <net/net_seq_lock.h>
 #include <linux/refcount.h>
 #include <linux/workqueue.h>
 #include <linux/mutex.h>
@@ -100,7 +101,7 @@ struct Qdisc {
 	struct sk_buff_head	gso_skb ____cacheline_aligned_in_smp;
 	struct qdisc_skb_head	q;
 	struct gnet_stats_basic_packed bstats;
-	seqcount_t		running;
+	net_seqlock_t		running;
 	struct gnet_stats_queue	qstats;
 	unsigned long		state;
 	struct Qdisc            *next_sched;
@@ -138,7 +139,11 @@ static inline bool qdisc_is_running(struct Qdisc *qdisc)
 {
 	if (qdisc->flags & TCQ_F_NOLOCK)
 		return spin_is_locked(&qdisc->seqlock);
+#ifdef CONFIG_PREEMPT_RT
+	return spin_is_locked(&qdisc->running.lock) ? true : false;
+#else
 	return (raw_read_seqcount(&qdisc->running) & 1) ? true : false;
+#endif
 }
 
 static inline bool qdisc_is_percpu_stats(const struct Qdisc *q)
@@ -162,17 +167,27 @@ static inline bool qdisc_run_begin(struct Qdisc *qdisc)
 	} else if (qdisc_is_running(qdisc)) {
 		return false;
 	}
+#ifdef CONFIG_PREEMPT_RT
+	if (try_write_seqlock(&qdisc->running))
+		return true;
+	return false;
+#else
 	/* Variant of write_seqcount_begin() telling lockdep a trylock
 	 * was attempted.
 	 */
 	raw_write_seqcount_begin(&qdisc->running);
 	seqcount_acquire(&qdisc->running.dep_map, 0, 1, _RET_IP_);
 	return true;
+#endif
 }
 
 static inline void qdisc_run_end(struct Qdisc *qdisc)
 {
+#ifdef CONFIG_PREEMPT_RT
+	write_sequnlock(&qdisc->running);
+#else
 	write_seqcount_end(&qdisc->running);
+#endif
 	if (qdisc->flags & TCQ_F_NOLOCK)
 		spin_unlock(&qdisc->seqlock);
 }
@@ -535,7 +550,7 @@ static inline spinlock_t *qdisc_root_sleeping_lock(const struct Qdisc *qdisc)
 	return qdisc_lock(root);
 }
 
-static inline seqcount_t *qdisc_root_sleeping_running(const struct Qdisc *qdisc)
+static inline net_seqlock_t *qdisc_root_sleeping_running(const struct Qdisc *qdisc)
 {
 	struct Qdisc *root = qdisc_root_sleeping(qdisc);
 
diff --git a/include/xen/xen-ops.h b/include/xen/xen-ops.h
index d89969aa9942c..095be1d66f31c 100644
--- a/include/xen/xen-ops.h
+++ b/include/xen/xen-ops.h
@@ -215,7 +215,7 @@ bool xen_running_on_version_or_later(unsigned int major, unsigned int minor);
 void xen_efi_runtime_setup(void);
 
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 
 static inline void xen_preemptible_hcall_begin(void)
 {
@@ -239,6 +239,6 @@ static inline void xen_preemptible_hcall_end(void)
 	__this_cpu_write(xen_in_preemptible_hcall, false);
 }
 
-#endif /* CONFIG_PREEMPT */
+#endif /* CONFIG_PREEMPTION */
 
 #endif /* INCLUDE_XEN_OPS_H */
diff --git a/init/Kconfig b/init/Kconfig
index b4daad2bac233..a63af2602a48b 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -923,6 +923,7 @@ config CFS_BANDWIDTH
 config RT_GROUP_SCHED
 	bool "Group scheduling for SCHED_RR/FIFO"
 	depends on CGROUP_SCHED
+	depends on !PREEMPT_RT
 	default n
 	help
 	  This feature lets you explicitly allocate real CPU bandwidth
@@ -1629,6 +1630,7 @@ config KALLSYMS_BASE_RELATIVE
 # syscall, maps, verifier
 config BPF_SYSCALL
 	bool "Enable bpf() system call"
+	depends on !PREEMPT_RT
 	select BPF
 	select IRQ_WORK
 	default n
@@ -1804,6 +1806,7 @@ choice
 
 config SLAB
 	bool "SLAB"
+	depends on !PREEMPT_RT
 	select HAVE_HARDENED_USERCOPY_ALLOCATOR
 	help
 	  The regular slab allocator that is established and known to work
@@ -1824,6 +1827,7 @@ config SLUB
 config SLOB
 	depends on EXPERT
 	bool "SLOB (Simple Allocator)"
+	depends on !PREEMPT_RT
 	help
 	   SLOB replaces the stock allocator with a drastically simpler
 	   allocator. SLOB is generally more space efficient but
@@ -1889,7 +1893,7 @@ config SHUFFLE_PAGE_ALLOCATOR
 
 config SLUB_CPU_PARTIAL
 	default y
-	depends on SLUB && SMP
+	depends on SLUB && SMP && !PREEMPT_RT
 	bool "SLUB per cpu partial cache"
 	help
 	  Per cpu partial caches accelerate objects allocation and freeing
diff --git a/init/init_task.c b/init/init_task.c
index 9e5cbe5eab7b1..1539bfba1bef8 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -73,6 +73,10 @@ struct task_struct init_task
 	.cpus_ptr	= &init_task.cpus_mask,
 	.cpus_mask	= CPU_MASK_ALL,
 	.nr_cpus_allowed= NR_CPUS,
+#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT) && \
+    defined(CONFIG_SCHED_DEBUG)
+	.pinned_on_cpu	= -1,
+#endif
 	.mm		= NULL,
 	.active_mm	= &init_mm,
 	.restart_block	= {
diff --git a/init/main.c b/init/main.c
index 91f6ebb30ef04..a28d7b2fd5091 100644
--- a/init/main.c
+++ b/init/main.c
@@ -693,7 +693,6 @@ asmlinkage __visible void __init start_kernel(void)
 	boot_init_stack_canary();
 
 	time_init();
-	printk_safe_init();
 	perf_event_init();
 	profile_init();
 	call_function_init();
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
index e0852dc333acd..3de8fd11873b4 100644
--- a/kernel/Kconfig.locks
+++ b/kernel/Kconfig.locks
@@ -101,7 +101,7 @@ config UNINLINE_SPIN_UNLOCK
 # unlock and unlock_irq functions are inlined when:
 #   - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y
 #  or
-#   - DEBUG_SPINLOCK=n and PREEMPT=n
+#   - DEBUG_SPINLOCK=n and PREEMPTION=n
 #
 # unlock_bh and unlock_irqrestore functions are inlined when:
 #   - DEBUG_SPINLOCK=n and ARCH_INLINE_*LOCK=y
@@ -139,7 +139,7 @@ config INLINE_SPIN_UNLOCK_BH
 
 config INLINE_SPIN_UNLOCK_IRQ
 	def_bool y
-	depends on !PREEMPT || ARCH_INLINE_SPIN_UNLOCK_IRQ
+	depends on !PREEMPTION || ARCH_INLINE_SPIN_UNLOCK_IRQ
 
 config INLINE_SPIN_UNLOCK_IRQRESTORE
 	def_bool y
@@ -168,7 +168,7 @@ config INLINE_READ_LOCK_IRQSAVE
 
 config INLINE_READ_UNLOCK
 	def_bool y
-	depends on !PREEMPT || ARCH_INLINE_READ_UNLOCK
+	depends on !PREEMPTION || ARCH_INLINE_READ_UNLOCK
 
 config INLINE_READ_UNLOCK_BH
 	def_bool y
@@ -176,7 +176,7 @@ config INLINE_READ_UNLOCK_BH
 
 config INLINE_READ_UNLOCK_IRQ
 	def_bool y
-	depends on !PREEMPT || ARCH_INLINE_READ_UNLOCK_IRQ
+	depends on !PREEMPTION || ARCH_INLINE_READ_UNLOCK_IRQ
 
 config INLINE_READ_UNLOCK_IRQRESTORE
 	def_bool y
@@ -205,7 +205,7 @@ config INLINE_WRITE_LOCK_IRQSAVE
 
 config INLINE_WRITE_UNLOCK
 	def_bool y
-	depends on !PREEMPT || ARCH_INLINE_WRITE_UNLOCK
+	depends on !PREEMPTION || ARCH_INLINE_WRITE_UNLOCK
 
 config INLINE_WRITE_UNLOCK_BH
 	def_bool y
@@ -213,7 +213,7 @@ config INLINE_WRITE_UNLOCK_BH
 
 config INLINE_WRITE_UNLOCK_IRQ
 	def_bool y
-	depends on !PREEMPT || ARCH_INLINE_WRITE_UNLOCK_IRQ
+	depends on !PREEMPTION || ARCH_INLINE_WRITE_UNLOCK_IRQ
 
 config INLINE_WRITE_UNLOCK_IRQRESTORE
 	def_bool y
diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index deff972174967..7871ec3c9a02a 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -1,5 +1,11 @@
 # SPDX-License-Identifier: GPL-2.0-only
 
+config HAVE_PREEMPT_LAZY
+	bool
+
+config PREEMPT_LAZY
+	def_bool y if HAVE_PREEMPT_LAZY && PREEMPT_RT
+
 choice
 	prompt "Preemption Model"
 	default PREEMPT_NONE
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index ef4242e5d4bc6..82061b4f3ebcb 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -1957,7 +1957,6 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 	cgrp->dom_cgrp = cgrp;
 	cgrp->max_descendants = INT_MAX;
 	cgrp->max_depth = INT_MAX;
-	INIT_LIST_HEAD(&cgrp->rstat_css_list);
 	prev_cputime_init(&cgrp->prev_cputime);
 
 	for_each_subsys(ss, ssid)
@@ -5013,12 +5012,6 @@ static void css_release_work_fn(struct work_struct *work)
 	list_del_rcu(&css->sibling);
 
 	if (ss) {
-		/* css release path */
-		if (!list_empty(&css->rstat_css_node)) {
-			cgroup_rstat_flush(cgrp);
-			list_del_rcu(&css->rstat_css_node);
-		}
-
 		cgroup_idr_replace(&ss->css_idr, NULL, css->id);
 		if (ss->css_released)
 			ss->css_released(css);
@@ -5080,7 +5073,6 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
 	css->id = -1;
 	INIT_LIST_HEAD(&css->sibling);
 	INIT_LIST_HEAD(&css->children);
-	INIT_LIST_HEAD(&css->rstat_css_node);
 	css->serial_nr = css_serial_nr_next++;
 	atomic_set(&css->online_cnt, 0);
 
@@ -5089,9 +5081,6 @@ static void init_and_link_css(struct cgroup_subsys_state *css,
 		css_get(css->parent);
 	}
 
-	if (cgroup_on_dfl(cgrp) && ss->css_rstat_flush)
-		list_add_rcu(&css->rstat_css_node, &cgrp->rstat_css_list);
-
 	BUG_ON(cgroup_css(cgrp, ss));
 }
 
@@ -5193,7 +5182,6 @@ static struct cgroup_subsys_state *css_create(struct cgroup *cgrp,
 err_list_del:
 	list_del_rcu(&css->sibling);
 err_free_css:
-	list_del_rcu(&css->rstat_css_node);
 	INIT_RCU_WORK(&css->destroy_rwork, css_free_rwork_fn);
 	queue_rcu_work(cgroup_destroy_wq, &css->destroy_rwork);
 	return ERR_PTR(err);
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index c87ee6412b36a..680034721002b 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -345,7 +345,7 @@ void cpuset_read_unlock(void)
 	percpu_up_read(&cpuset_rwsem);
 }
 
-static DEFINE_SPINLOCK(callback_lock);
+static DEFINE_RAW_SPINLOCK(callback_lock);
 
 static struct workqueue_struct *cpuset_migrate_mm_wq;
 
@@ -1255,7 +1255,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
 	 * Newly added CPUs will be removed from effective_cpus and
 	 * newly deleted ones will be added back to effective_cpus.
 	 */
-	spin_lock_irq(&callback_lock);
+	raw_spin_lock_irq(&callback_lock);
 	if (adding) {
 		cpumask_or(parent->subparts_cpus,
 			   parent->subparts_cpus, tmp->addmask);
@@ -1274,7 +1274,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd,
 	}
 
 	parent->nr_subparts_cpus = cpumask_weight(parent->subparts_cpus);
-	spin_unlock_irq(&callback_lock);
+	raw_spin_unlock_irq(&callback_lock);
 
 	return cmd == partcmd_update;
 }
@@ -1379,7 +1379,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
 			continue;
 		rcu_read_unlock();
 
-		spin_lock_irq(&callback_lock);
+		raw_spin_lock_irq(&callback_lock);
 
 		cpumask_copy(cp->effective_cpus, tmp->new_cpus);
 		if (cp->nr_subparts_cpus &&
@@ -1410,7 +1410,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp)
 					= cpumask_weight(cp->subparts_cpus);
 			}
 		}
-		spin_unlock_irq(&callback_lock);
+		raw_spin_unlock_irq(&callback_lock);
 
 		WARN_ON(!is_in_v2_mode() &&
 			!cpumask_equal(cp->cpus_allowed, cp->effective_cpus));
@@ -1528,7 +1528,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 			return -EINVAL;
 	}
 
-	spin_lock_irq(&callback_lock);
+	raw_spin_lock_irq(&callback_lock);
 	cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed);
 
 	/*
@@ -1539,7 +1539,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
 			       cs->cpus_allowed);
 		cs->nr_subparts_cpus = cpumask_weight(cs->subparts_cpus);
 	}
-	spin_unlock_irq(&callback_lock);
+	raw_spin_unlock_irq(&callback_lock);
 
 	update_cpumasks_hier(cs, &tmp);
 
@@ -1733,9 +1733,9 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
 			continue;
 		rcu_read_unlock();
 
-		spin_lock_irq(&callback_lock);
+		raw_spin_lock_irq(&callback_lock);
 		cp->effective_mems = *new_mems;
-		spin_unlock_irq(&callback_lock);
+		raw_spin_unlock_irq(&callback_lock);
 
 		WARN_ON(!is_in_v2_mode() &&
 			!nodes_equal(cp->mems_allowed, cp->effective_mems));
@@ -1803,9 +1803,9 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
 	if (retval < 0)
 		goto done;
 
-	spin_lock_irq(&callback_lock);
+	raw_spin_lock_irq(&callback_lock);
 	cs->mems_allowed = trialcs->mems_allowed;
-	spin_unlock_irq(&callback_lock);
+	raw_spin_unlock_irq(&callback_lock);
 
 	/* use trialcs->mems_allowed as a temp variable */
 	update_nodemasks_hier(cs, &trialcs->mems_allowed);
@@ -1896,9 +1896,9 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
 	spread_flag_changed = ((is_spread_slab(cs) != is_spread_slab(trialcs))
 			|| (is_spread_page(cs) != is_spread_page(trialcs)));
 
-	spin_lock_irq(&callback_lock);
+	raw_spin_lock_irq(&callback_lock);
 	cs->flags = trialcs->flags;
-	spin_unlock_irq(&callback_lock);
+	raw_spin_unlock_irq(&callback_lock);
 
 	if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed)
 		rebuild_sched_domains_locked();
@@ -2407,7 +2407,7 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
 	cpuset_filetype_t type = seq_cft(sf)->private;
 	int ret = 0;
 
-	spin_lock_irq(&callback_lock);
+	raw_spin_lock_irq(&callback_lock);
 
 	switch (type) {
 	case FILE_CPULIST:
@@ -2429,7 +2429,7 @@ static int cpuset_common_seq_show(struct seq_file *sf, void *v)
 		ret = -EINVAL;
 	}
 
-	spin_unlock_irq(&callback_lock);
+	raw_spin_unlock_irq(&callback_lock);
 	return ret;
 }
 
@@ -2742,14 +2742,14 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
 
 	cpuset_inc();
 
-	spin_lock_irq(&callback_lock);
+	raw_spin_lock_irq(&callback_lock);
 	if (is_in_v2_mode()) {
 		cpumask_copy(cs->effective_cpus, parent->effective_cpus);
 		cs->effective_mems = parent->effective_mems;
 		cs->use_parent_ecpus = true;
 		parent->child_ecpus_count++;
 	}
-	spin_unlock_irq(&callback_lock);
+	raw_spin_unlock_irq(&callback_lock);
 
 	if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags))
 		goto out_unlock;
@@ -2776,12 +2776,12 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
 	}
 	rcu_read_unlock();
 
-	spin_lock_irq(&callback_lock);
+	raw_spin_lock_irq(&callback_lock);
 	cs->mems_allowed = parent->mems_allowed;
 	cs->effective_mems = parent->mems_allowed;
 	cpumask_copy(cs->cpus_allowed, parent->cpus_allowed);
 	cpumask_copy(cs->effective_cpus, parent->cpus_allowed);
-	spin_unlock_irq(&callback_lock);
+	raw_spin_unlock_irq(&callback_lock);
 out_unlock:
 	percpu_up_write(&cpuset_rwsem);
 	put_online_cpus();
@@ -2837,7 +2837,7 @@ static void cpuset_css_free(struct cgroup_subsys_state *css)
 static void cpuset_bind(struct cgroup_subsys_state *root_css)
 {
 	percpu_down_write(&cpuset_rwsem);
-	spin_lock_irq(&callback_lock);
+	raw_spin_lock_irq(&callback_lock);
 
 	if (is_in_v2_mode()) {
 		cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask);
@@ -2848,7 +2848,7 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css)
 		top_cpuset.mems_allowed = top_cpuset.effective_mems;
 	}
 
-	spin_unlock_irq(&callback_lock);
+	raw_spin_unlock_irq(&callback_lock);
 	percpu_up_write(&cpuset_rwsem);
 }
 
@@ -2945,12 +2945,12 @@ hotplug_update_tasks_legacy(struct cpuset *cs,
 {
 	bool is_empty;
 
-	spin_lock_irq(&callback_lock);
+	raw_spin_lock_irq(&callback_lock);
 	cpumask_copy(cs->cpus_allowed, new_cpus);
 	cpumask_copy(cs->effective_cpus, new_cpus);
 	cs->mems_allowed = *new_mems;
 	cs->effective_mems = *new_mems;
-	spin_unlock_irq(&callback_lock);
+	raw_spin_unlock_irq(&callback_lock);
 
 	/*
 	 * Don't call update_tasks_cpumask() if the cpuset becomes empty,
@@ -2987,10 +2987,10 @@ hotplug_update_tasks(struct cpuset *cs,
 	if (nodes_empty(*new_mems))
 		*new_mems = parent_cs(cs)->effective_mems;
 
-	spin_lock_irq(&callback_lock);
+	raw_spin_lock_irq(&callback_lock);
 	cpumask_copy(cs->effective_cpus, new_cpus);
 	cs->effective_mems = *new_mems;
-	spin_unlock_irq(&callback_lock);
+	raw_spin_unlock_irq(&callback_lock);
 
 	if (cpus_updated)
 		update_tasks_cpumask(cs);
@@ -3145,7 +3145,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
 
 	/* synchronize cpus_allowed to cpu_active_mask */
 	if (cpus_updated) {
-		spin_lock_irq(&callback_lock);
+		raw_spin_lock_irq(&callback_lock);
 		if (!on_dfl)
 			cpumask_copy(top_cpuset.cpus_allowed, &new_cpus);
 		/*
@@ -3165,17 +3165,17 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
 			}
 		}
 		cpumask_copy(top_cpuset.effective_cpus, &new_cpus);
-		spin_unlock_irq(&callback_lock);
+		raw_spin_unlock_irq(&callback_lock);
 		/* we don't mess with cpumasks of tasks in top_cpuset */
 	}
 
 	/* synchronize mems_allowed to N_MEMORY */
 	if (mems_updated) {
-		spin_lock_irq(&callback_lock);
+		raw_spin_lock_irq(&callback_lock);
 		if (!on_dfl)
 			top_cpuset.mems_allowed = new_mems;
 		top_cpuset.effective_mems = new_mems;
-		spin_unlock_irq(&callback_lock);
+		raw_spin_unlock_irq(&callback_lock);
 		update_tasks_nodemask(&top_cpuset);
 	}
 
@@ -3276,11 +3276,11 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&callback_lock, flags);
+	raw_spin_lock_irqsave(&callback_lock, flags);
 	rcu_read_lock();
 	guarantee_online_cpus(task_cs(tsk), pmask);
 	rcu_read_unlock();
-	spin_unlock_irqrestore(&callback_lock, flags);
+	raw_spin_unlock_irqrestore(&callback_lock, flags);
 }
 
 /**
@@ -3341,11 +3341,11 @@ nodemask_t cpuset_mems_allowed(struct task_struct *tsk)
 	nodemask_t mask;
 	unsigned long flags;
 
-	spin_lock_irqsave(&callback_lock, flags);
+	raw_spin_lock_irqsave(&callback_lock, flags);
 	rcu_read_lock();
 	guarantee_online_mems(task_cs(tsk), &mask);
 	rcu_read_unlock();
-	spin_unlock_irqrestore(&callback_lock, flags);
+	raw_spin_unlock_irqrestore(&callback_lock, flags);
 
 	return mask;
 }
@@ -3437,14 +3437,14 @@ bool __cpuset_node_allowed(int node, gfp_t gfp_mask)
 		return true;
 
 	/* Not hardwall and node outside mems_allowed: scan up cpusets */
-	spin_lock_irqsave(&callback_lock, flags);
+	raw_spin_lock_irqsave(&callback_lock, flags);
 
 	rcu_read_lock();
 	cs = nearest_hardwall_ancestor(task_cs(current));
 	allowed = node_isset(node, cs->mems_allowed);
 	rcu_read_unlock();
 
-	spin_unlock_irqrestore(&callback_lock, flags);
+	raw_spin_unlock_irqrestore(&callback_lock, flags);
 	return allowed;
 }
 
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index ca19b4c8acf53..a59962e66aea1 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -149,7 +149,7 @@ static struct cgroup *cgroup_rstat_cpu_pop_updated(struct cgroup *pos,
 }
 
 /* see cgroup_rstat_flush() */
-static void cgroup_rstat_flush_locked(struct cgroup *cgrp, bool may_sleep)
+static void cgroup_rstat_flush_locked(struct cgroup *cgrp)
 	__releases(&cgroup_rstat_lock) __acquires(&cgroup_rstat_lock)
 {
 	int cpu;
@@ -161,27 +161,17 @@ static void cgroup_rstat_flush_locked(struct cgroup *cgrp, bool may_sleep)
 						       cpu);
 		struct cgroup *pos = NULL;
 
-		raw_spin_lock(cpu_lock);
-		while ((pos = cgroup_rstat_cpu_pop_updated(pos, cgrp, cpu))) {
-			struct cgroup_subsys_state *css;
-
+		raw_spin_lock_irq(cpu_lock);
+		while ((pos = cgroup_rstat_cpu_pop_updated(pos, cgrp, cpu)))
 			cgroup_base_stat_flush(pos, cpu);
 
-			rcu_read_lock();
-			list_for_each_entry_rcu(css, &pos->rstat_css_list,
-						rstat_css_node)
-				css->ss->css_rstat_flush(css, cpu);
-			rcu_read_unlock();
-		}
-		raw_spin_unlock(cpu_lock);
+		raw_spin_unlock_irq(cpu_lock);
 
-		/* if @may_sleep, play nice and yield if necessary */
-		if (may_sleep && (need_resched() ||
-				  spin_needbreak(&cgroup_rstat_lock))) {
-			spin_unlock_irq(&cgroup_rstat_lock);
+		if (need_resched() || spin_needbreak(&cgroup_rstat_lock)) {
+			spin_unlock(&cgroup_rstat_lock);
 			if (!cond_resched())
 				cpu_relax();
-			spin_lock_irq(&cgroup_rstat_lock);
+			spin_lock(&cgroup_rstat_lock);
 		}
 	}
 }
@@ -203,24 +193,9 @@ void cgroup_rstat_flush(struct cgroup *cgrp)
 {
 	might_sleep();
 
-	spin_lock_irq(&cgroup_rstat_lock);
-	cgroup_rstat_flush_locked(cgrp, true);
-	spin_unlock_irq(&cgroup_rstat_lock);
-}
-
-/**
- * cgroup_rstat_flush_irqsafe - irqsafe version of cgroup_rstat_flush()
- * @cgrp: target cgroup
- *
- * This function can be called from any context.
- */
-void cgroup_rstat_flush_irqsafe(struct cgroup *cgrp)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&cgroup_rstat_lock, flags);
-	cgroup_rstat_flush_locked(cgrp, false);
-	spin_unlock_irqrestore(&cgroup_rstat_lock, flags);
+	spin_lock(&cgroup_rstat_lock);
+	cgroup_rstat_flush_locked(cgrp);
+	spin_unlock(&cgroup_rstat_lock);
 }
 
 /**
@@ -232,21 +207,21 @@ void cgroup_rstat_flush_irqsafe(struct cgroup *cgrp)
  *
  * This function may block.
  */
-void cgroup_rstat_flush_hold(struct cgroup *cgrp)
+static void cgroup_rstat_flush_hold(struct cgroup *cgrp)
 	__acquires(&cgroup_rstat_lock)
 {
 	might_sleep();
-	spin_lock_irq(&cgroup_rstat_lock);
-	cgroup_rstat_flush_locked(cgrp, true);
+	spin_lock(&cgroup_rstat_lock);
+	cgroup_rstat_flush_locked(cgrp);
 }
 
 /**
  * cgroup_rstat_flush_release - release cgroup_rstat_flush_hold()
  */
-void cgroup_rstat_flush_release(void)
+static void cgroup_rstat_flush_release(void)
 	__releases(&cgroup_rstat_lock)
 {
-	spin_unlock_irq(&cgroup_rstat_lock);
+	spin_unlock(&cgroup_rstat_lock);
 }
 
 int cgroup_rstat_init(struct cgroup *cgrp)
diff --git a/kernel/cpu.c b/kernel/cpu.c
index e2cad3ee2eadc..81a6e5068972c 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -849,6 +849,15 @@ static int take_cpu_down(void *_param)
 	int err, cpu = smp_processor_id();
 	int ret;
 
+#ifdef CONFIG_PREEMPT_RT
+	/*
+	 * If any tasks disabled migration before we got here,
+	 * go back and sleep again.
+	 */
+	if (cpu_nr_pinned(cpu))
+		return -EAGAIN;
+#endif
+
 	/* Ensure this CPU doesn't handle any more interrupts. */
 	err = __cpu_disable();
 	if (err < 0)
@@ -878,6 +887,10 @@ static int take_cpu_down(void *_param)
 	return 0;
 }
 
+#ifdef CONFIG_PREEMPT_RT
+struct task_struct *takedown_cpu_task;
+#endif
+
 static int takedown_cpu(unsigned int cpu)
 {
 	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
@@ -892,11 +905,39 @@ static int takedown_cpu(unsigned int cpu)
 	 */
 	irq_lock_sparse();
 
+#ifdef CONFIG_PREEMPT_RT
+	WARN_ON_ONCE(takedown_cpu_task);
+	takedown_cpu_task = current;
+
+again:
+	/*
+	 * If a task pins this CPU after we pass this check, take_cpu_down
+	 * will return -EAGAIN.
+	 */
+	for (;;) {
+		int nr_pinned;
+
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		nr_pinned = cpu_nr_pinned(cpu);
+		if (nr_pinned == 0)
+			break;
+		schedule();
+	}
+	set_current_state(TASK_RUNNING);
+#endif
+
 	/*
 	 * So now all preempt/rcu users must observe !cpu_active().
 	 */
 	err = stop_machine_cpuslocked(take_cpu_down, NULL, cpumask_of(cpu));
+#ifdef CONFIG_PREEMPT_RT
+	if (err == -EAGAIN)
+		goto again;
+#endif
 	if (err) {
+#ifdef CONFIG_PREEMPT_RT
+		takedown_cpu_task = NULL;
+#endif
 		/* CPU refused to die */
 		irq_unlock_sparse();
 		/* Unpark the hotplug thread so we can rollback there */
@@ -915,6 +956,9 @@ static int takedown_cpu(unsigned int cpu)
 	wait_for_ap_thread(st, false);
 	BUG_ON(st->state != CPUHP_AP_IDLE_DEAD);
 
+#ifdef CONFIG_PREEMPT_RT
+	takedown_cpu_task = NULL;
+#endif
 	/* Interrupts are moved away from the dying cpu, reenable alloc/free */
 	irq_unlock_sparse();
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 00a014670ed02..0824dbf49765f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -10258,7 +10258,7 @@ static struct pmu *perf_init_event(struct perf_event *event)
 		goto unlock;
 	}
 
-	list_for_each_entry_rcu(pmu, &pmus, entry) {
+	list_for_each_entry_rcu(pmu, &pmus, entry, lockdep_is_held(&pmus_srcu)) {
 		ret = perf_try_init_event(pmu, event);
 		if (!ret)
 			goto unlock;
diff --git a/kernel/exit.c b/kernel/exit.c
index d351fd09e7395..b5b5f46b73564 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -161,7 +161,7 @@ static void __exit_signal(struct task_struct *tsk)
 	 * 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 6cabc124378c2..e4d28dc8ac656 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -43,6 +43,7 @@
 #include <linux/hmm.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/kprobes.h>
 #include <linux/vmacache.h>
 #include <linux/nsproxy.h>
 #include <linux/capability.h>
@@ -289,7 +290,7 @@ static inline void free_thread_stack(struct task_struct *tsk)
 			return;
 		}
 
-		vfree_atomic(tsk->stack);
+		vfree(tsk->stack);
 		return;
 	}
 #endif
@@ -696,6 +697,19 @@ void __mmdrop(struct mm_struct *mm)
 }
 EXPORT_SYMBOL_GPL(__mmdrop);
 
+#ifdef CONFIG_PREEMPT_RT
+/*
+ * RCU callback for delayed mm drop. Not strictly rcu, but we don't
+ * want another facility to make this work.
+ */
+void __mmdrop_delayed(struct rcu_head *rhp)
+{
+	struct mm_struct *mm = container_of(rhp, struct mm_struct, delayed_drop);
+
+	__mmdrop(mm);
+}
+#endif
+
 static void mmdrop_async_fn(struct work_struct *work)
 {
 	struct mm_struct *mm;
@@ -737,6 +751,15 @@ void __put_task_struct(struct task_struct *tsk)
 	WARN_ON(refcount_read(&tsk->usage));
 	WARN_ON(tsk == current);
 
+	/*
+	 * Remove function-return probe instances associated with this
+	 * task and put them back on the free list.
+	 */
+	kprobe_flush_task(tsk);
+
+	/* Task is done with its stack. */
+	put_task_stack(tsk);
+
 	cgroup_free(tsk);
 	task_numa_free(tsk, true);
 	security_task_free(tsk);
@@ -927,6 +950,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	tsk->splice_pipe = NULL;
 	tsk->task_frag.page = NULL;
 	tsk->wake_q.next = NULL;
+	tsk->wake_q_sleeper.next = NULL;
 
 	account_kernel_stack(tsk, 1);
 
@@ -1900,6 +1924,7 @@ static __latent_entropy struct task_struct *copy_process(
 	spin_lock_init(&p->alloc_lock);
 
 	init_sigpending(&p->pending);
+	p->sigqueue_cache = NULL;
 
 	p->utime = p->stime = p->gtime = 0;
 #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
diff --git a/kernel/futex.c b/kernel/futex.c
index afbf928d6a6b0..58c0c77fda797 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -945,7 +945,9 @@ static void exit_pi_state_list(struct task_struct *curr)
 		if (head->next != next) {
 			/* retain curr->pi_lock for the loop invariant */
 			raw_spin_unlock(&pi_state->pi_mutex.wait_lock);
+			raw_spin_unlock_irq(&curr->pi_lock);
 			spin_unlock(&hb->lock);
+			raw_spin_lock_irq(&curr->pi_lock);
 			put_pi_state(pi_state);
 			continue;
 		}
@@ -1554,6 +1556,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_
 	struct task_struct *new_owner;
 	bool postunlock = false;
 	DEFINE_WAKE_Q(wake_q);
+	DEFINE_WAKE_Q(wake_sleeper_q);
 	int ret = 0;
 
 	new_owner = rt_mutex_next_owner(&pi_state->pi_mutex);
@@ -1613,13 +1616,13 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_pi_state *pi_
 	pi_state->owner = new_owner;
 	raw_spin_unlock(&new_owner->pi_lock);
 
-	postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q);
-
+	postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q,
+					     &wake_sleeper_q);
 out_unlock:
 	raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock);
 
 	if (postunlock)
-		rt_mutex_postunlock(&wake_q);
+		rt_mutex_postunlock(&wake_q, &wake_sleeper_q);
 
 	return ret;
 }
@@ -2243,6 +2246,16 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 				requeue_pi_wake_futex(this, &key2, hb2);
 				drop_count++;
 				continue;
+			} else if (ret == -EAGAIN) {
+				/*
+				 * Waiter was woken by timeout or
+				 * signal and has set pi_blocked_on to
+				 * PI_WAKEUP_INPROGRESS before we
+				 * tried to enqueue it on the rtmutex.
+				 */
+				this->pi_state = NULL;
+				put_pi_state(pi_state);
+				continue;
 			} else if (ret) {
 				/*
 				 * rt_mutex_start_proxy_lock() detected a
@@ -2951,7 +2964,7 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
 		goto no_block;
 	}
 
-	rt_mutex_init_waiter(&rt_waiter);
+	rt_mutex_init_waiter(&rt_waiter, false);
 
 	/*
 	 * On PREEMPT_RT_FULL, when hb->lock becomes an rt_mutex, we must not
@@ -2967,6 +2980,14 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
 	 * before __rt_mutex_start_proxy_lock() is done.
 	 */
 	raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock);
+	/*
+	 * the migrate_disable() here disables migration in the in_atomic() fast
+	 * path which is enabled again in the following spin_unlock(). We have
+	 * one migrate_disable() pending in the slow-path which is reversed
+	 * after the raw_spin_unlock_irq() where we leave the atomic context.
+	 */
+	migrate_disable();
+
 	spin_unlock(q.lock_ptr);
 	/*
 	 * __rt_mutex_start_proxy_lock() unconditionally enqueues the @rt_waiter
@@ -2975,6 +2996,7 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
 	 */
 	ret = __rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current);
 	raw_spin_unlock_irq(&q.pi_state->pi_mutex.wait_lock);
+	migrate_enable();
 
 	if (ret) {
 		if (ret == 1)
@@ -3123,10 +3145,19 @@ static int futex_unlock_pi(u32 __user *uaddr, unsigned int flags)
 		 * rt_waiter. Also see the WARN in wake_futex_pi().
 		 */
 		raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock);
+		/*
+		 * Magic trickery for now to make the RT migrate disable
+		 * logic happy. The following spin_unlock() happens with
+		 * interrupts disabled so the internal migrate_enable()
+		 * won't undo the migrate_disable() which was issued when
+		 * locking hb->lock.
+		 */
+		migrate_disable();
 		spin_unlock(&hb->lock);
 
 		/* drops pi_state->pi_mutex.wait_lock */
 		ret = wake_futex_pi(uaddr, uval, pi_state);
+		migrate_enable();
 
 		put_pi_state(pi_state);
 
@@ -3298,7 +3329,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	struct hrtimer_sleeper timeout, *to;
 	struct futex_pi_state *pi_state = NULL;
 	struct rt_mutex_waiter rt_waiter;
-	struct futex_hash_bucket *hb;
+	struct futex_hash_bucket *hb, *hb2;
 	union futex_key key2 = FUTEX_KEY_INIT;
 	struct futex_q q = futex_q_init;
 	int res, ret;
@@ -3319,7 +3350,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	 * The waiter is allocated on our stack, manipulated by the requeue
 	 * code while we sleep on uaddr.
 	 */
-	rt_mutex_init_waiter(&rt_waiter);
+	rt_mutex_init_waiter(&rt_waiter, false);
 
 	ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, FUTEX_WRITE);
 	if (unlikely(ret != 0))
@@ -3350,20 +3381,55 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	/* 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) {
@@ -3372,7 +3438,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		 * did a lock-steal - fix up the PI-state in that case.
 		 */
 		if (q.pi_state && (q.pi_state->owner != current)) {
-			spin_lock(q.lock_ptr);
+			spin_lock(&hb2->lock);
+			BUG_ON(&hb2->lock != q.lock_ptr);
 			ret = fixup_pi_state_owner(uaddr2, &q, current);
 			if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) {
 				pi_state = q.pi_state;
@@ -3383,7 +3450,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 			 * the requeue_pi() code acquired for us.
 			 */
 			put_pi_state(q.pi_state);
-			spin_unlock(q.lock_ptr);
+			spin_unlock(&hb2->lock);
 		}
 	} else {
 		struct rt_mutex *pi_mutex;
@@ -3397,7 +3464,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 		pi_mutex = &q.pi_state->pi_mutex;
 		ret = rt_mutex_wait_proxy_lock(pi_mutex, to, &rt_waiter);
 
-		spin_lock(q.lock_ptr);
+		spin_lock(&hb2->lock);
+		BUG_ON(&hb2->lock != q.lock_ptr);
 		if (ret && !rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter))
 			ret = 0;
 
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index a4ace611f47fe..3306fabed2217 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -185,10 +185,16 @@ irqreturn_t handle_irq_event_percpu(struct irq_desc *desc)
 {
 	irqreturn_t retval;
 	unsigned int flags = 0;
+	struct pt_regs *regs = get_irq_regs();
+	u64 ip = regs ? instruction_pointer(regs) : 0;
 
 	retval = __handle_irq_event_percpu(desc, &flags);
 
-	add_interrupt_randomness(desc->irq_data.irq, flags);
+#ifdef CONFIG_PREEMPT_RT
+	desc->random_ip = ip;
+#else
+	add_interrupt_randomness(desc->irq_data.irq, flags, ip);
+#endif
 
 	if (!noirqdebug)
 		note_interrupt(desc, retval);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 1753486b440cb..665a1dd59e5fc 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1099,6 +1099,12 @@ static int irq_thread(void *data)
 		if (action_ret == IRQ_WAKE_THREAD)
 			irq_wake_secondary(desc, action);
 
+#ifdef CONFIG_PREEMPT_RT
+		migrate_disable();
+		add_interrupt_randomness(action->irq, 0,
+				 desc->random_ip ^ (unsigned long) action);
+		migrate_enable();
+#endif
 		wake_threads_waitq(desc);
 	}
 
@@ -2681,7 +2687,7 @@ EXPORT_SYMBOL_GPL(irq_get_irqchip_state);
  *	This call sets the internal irqchip state of an interrupt,
  *	depending on the value of @which.
  *
- *	This function should be called with preemption disabled if the
+ *	This function should be called with migration disabled if the
  *	interrupt controller has per-cpu registers.
  */
 int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which,
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 2ed97a7c9b2a6..9e97124946a6a 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -442,6 +442,10 @@ MODULE_PARM_DESC(noirqdebug, "Disable irq lockup detection when true");
 
 static int __init irqfixup_setup(char *str)
 {
+#ifdef CONFIG_PREEMPT_RT
+	pr_warn("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");
@@ -454,6 +458,10 @@ module_param(irqfixup, int, 0644);
 
 static int __init irqpoll_setup(char *str)
 {
+#ifdef CONFIG_PREEMPT_RT
+	pr_warn("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 d42acaf818861..aab68fdbcb8d2 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -18,6 +18,7 @@
 #include <linux/cpu.h>
 #include <linux/notifier.h>
 #include <linux/smp.h>
+#include <linux/interrupt.h>
 #include <asm/processor.h>
 
 
@@ -60,13 +61,19 @@ void __weak arch_irq_work_raise(void)
 /* Enqueue on current CPU, work must already be claimed and preempt disabled */
 static void __irq_work_queue_local(struct irq_work *work)
 {
+	struct llist_head *list;
+	bool lazy_work, realtime = IS_ENABLED(CONFIG_PREEMPT_RT);
+
+	lazy_work = work->flags & IRQ_WORK_LAZY;
+
 	/* If the work is "lazy", handle it from next tick if any */
-	if (work->flags & IRQ_WORK_LAZY) {
-		if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) &&
-		    tick_nohz_tick_stopped())
-			arch_irq_work_raise();
-	} else {
-		if (llist_add(&work->llnode, this_cpu_ptr(&raised_list)))
+	if (lazy_work || (realtime && !(work->flags & IRQ_WORK_HARD_IRQ)))
+		list = this_cpu_ptr(&lazy_list);
+	else
+		list = this_cpu_ptr(&raised_list);
+
+	if (llist_add(&work->llnode, list)) {
+		if (!lazy_work || tick_nohz_tick_stopped())
 			arch_irq_work_raise();
 	}
 }
@@ -108,9 +115,16 @@ bool irq_work_queue_on(struct irq_work *work, int cpu)
 
 	preempt_disable();
 	if (cpu != smp_processor_id()) {
+		struct llist_head *list;
+
 		/* Arch remote IPI send/receive backend aren't NMI safe */
 		WARN_ON_ONCE(in_nmi());
-		if (llist_add(&work->llnode, &per_cpu(raised_list, cpu)))
+		if (IS_ENABLED(CONFIG_PREEMPT_RT) && !(work->flags & IRQ_WORK_HARD_IRQ))
+			list = &per_cpu(lazy_list, cpu);
+		else
+			list = &per_cpu(raised_list, cpu);
+
+		if (llist_add(&work->llnode, list))
 			arch_send_call_function_single_ipi(cpu);
 	} else {
 		__irq_work_queue_local(work);
@@ -129,9 +143,8 @@ bool irq_work_needs_cpu(void)
 	raised = this_cpu_ptr(&raised_list);
 	lazy = this_cpu_ptr(&lazy_list);
 
-	if (llist_empty(raised) || arch_irq_work_has_interrupt())
-		if (llist_empty(lazy))
-			return false;
+	if (llist_empty(raised) && llist_empty(lazy))
+		return false;
 
 	/* All work should have been flushed before going offline */
 	WARN_ON_ONCE(cpu_is_offline(smp_processor_id()));
@@ -145,8 +158,12 @@ static void irq_work_run_list(struct llist_head *list)
 	struct llist_node *llnode;
 	unsigned long flags;
 
+#ifndef CONFIG_PREEMPT_RT
+	/*
+	 * nort: On RT IRQ-work may run in SOFTIRQ context.
+	 */
 	BUG_ON(!irqs_disabled());
-
+#endif
 	if (llist_empty(list))
 		return;
 
@@ -178,7 +195,16 @@ static void irq_work_run_list(struct llist_head *list)
 void irq_work_run(void)
 {
 	irq_work_run_list(this_cpu_ptr(&raised_list));
-	irq_work_run_list(this_cpu_ptr(&lazy_list));
+	if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
+		/*
+		 * NOTE: we raise softirq via IPI for safety,
+		 * and execute in irq_work_tick() to move the
+		 * overhead from hard to soft irq context.
+		 */
+		if (!llist_empty(this_cpu_ptr(&lazy_list)))
+			raise_softirq(TIMER_SOFTIRQ);
+	} else
+		irq_work_run_list(this_cpu_ptr(&lazy_list));
 }
 EXPORT_SYMBOL_GPL(irq_work_run);
 
@@ -188,8 +214,17 @@ void irq_work_tick(void)
 
 	if (!llist_empty(raised) && !arch_irq_work_has_interrupt())
 		irq_work_run_list(raised);
+
+	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+		irq_work_run_list(this_cpu_ptr(&lazy_list));
+}
+
+#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT)
+void irq_work_tick_soft(void)
+{
 	irq_work_run_list(this_cpu_ptr(&lazy_list));
 }
+#endif
 
 /*
  * Synchronize against the irq_work @entry, ensures the entry is not
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 15d70a90b50dc..e7cef4e2e01f9 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -972,7 +972,6 @@ void crash_kexec(struct pt_regs *regs)
 	old_cpu = atomic_cmpxchg(&panic_cpu, PANIC_CPU_INVALID, this_cpu);
 	if (old_cpu == PANIC_CPU_INVALID) {
 		/* This is the 1st CPU which comes here, so go ahead. */
-		printk_safe_flush_on_panic();
 		__crash_kexec(regs);
 
 		/*
diff --git a/kernel/ksysfs.c b/kernel/ksysfs.c
index 35859da8bd4f7..dfff31ed644a6 100644
--- a/kernel/ksysfs.c
+++ b/kernel/ksysfs.c
@@ -138,6 +138,15 @@ KERNEL_ATTR_RO(vmcoreinfo);
 
 #endif /* CONFIG_CRASH_CORE */
 
+#if defined(CONFIG_PREEMPT_RT)
+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)
@@ -228,6 +237,9 @@ static struct attribute * kernel_attrs[] = {
 #ifndef CONFIG_TINY_RCU
 	&rcu_expedited_attr.attr,
 	&rcu_normal_attr.attr,
+#endif
+#ifdef CONFIG_PREEMPT_RT
+	&realtime_attr.attr,
 #endif
 	NULL
 };
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index 45452facff3b4..fa253e0db7515 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -3,7 +3,7 @@
 # and is generally not a function of system call inputs.
 KCOV_INSTRUMENT		:= n
 
-obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o
+obj-y += semaphore.o rwsem.o percpu-rwsem.o
 
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE)
@@ -12,19 +12,23 @@ CFLAGS_REMOVE_mutex-debug.o = $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_rtmutex-debug.o = $(CC_FLAGS_FTRACE)
 endif
 
-obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o
 obj-$(CONFIG_LOCKDEP) += lockdep.o
 ifeq ($(CONFIG_PROC_FS),y)
 obj-$(CONFIG_LOCKDEP) += lockdep_proc.o
 endif
 obj-$(CONFIG_SMP) += spinlock.o
-obj-$(CONFIG_LOCK_SPIN_ON_OWNER) += osq_lock.o
 obj-$(CONFIG_PROVE_LOCKING) += spinlock.o
 obj-$(CONFIG_QUEUED_SPINLOCKS) += qspinlock.o
 obj-$(CONFIG_RT_MUTEXES) += rtmutex.o
 obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
+ifneq ($(CONFIG_PREEMPT_RT),y)
+obj-y += mutex.o
+obj-$(CONFIG_LOCK_SPIN_ON_OWNER) += osq_lock.o
+obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o
+endif
+obj-$(CONFIG_PREEMPT_RT) += mutex-rt.o rwsem-rt.o rwlock-rt.o
 obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o
 obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o
 obj-$(CONFIG_WW_MUTEX_SELFTEST) += test-ww_mutex.o
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 233459c03b5ae..9090ea58fba53 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -4410,6 +4410,7 @@ static void check_flags(unsigned long flags)
 		}
 	}
 
+#ifndef CONFIG_PREEMPT_RT
 	/*
 	 * We dont accurately track softirq state in e.g.
 	 * hardirq contexts (such as on 4KSTACKS), so only
@@ -4424,6 +4425,7 @@ static void check_flags(unsigned long flags)
 			DEBUG_LOCKS_WARN_ON(!current->softirqs_enabled);
 		}
 	}
+#endif
 
 	if (!debug_locks)
 		print_irqtrace_events(current);
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index c513031cd7e33..9fb042d610d23 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -16,7 +16,6 @@
 #include <linux/kthread.h>
 #include <linux/sched/rt.h>
 #include <linux/spinlock.h>
-#include <linux/rwlock.h>
 #include <linux/mutex.h>
 #include <linux/rwsem.h>
 #include <linux/smp.h>
diff --git a/kernel/locking/mutex-rt.c b/kernel/locking/mutex-rt.c
new file mode 100644
index 0000000000000..4f81595c0f521
--- /dev/null
+++ b/kernel/locking/mutex-rt.c
@@ -0,0 +1,223 @@
+/*
+ * 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_state(&lock->lock, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(_mutex_lock);
+
+void __lockfunc _mutex_lock_io(struct mutex *lock)
+{
+	int token;
+
+	token = io_schedule_prepare();
+	_mutex_lock(lock);
+	io_schedule_finish(token);
+}
+EXPORT_SYMBOL_GPL(_mutex_lock_io);
+
+int __lockfunc _mutex_lock_interruptible(struct mutex *lock)
+{
+	int ret;
+
+	mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+	ret = __rt_mutex_lock_state(&lock->lock, TASK_INTERRUPTIBLE);
+	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_state(&lock->lock, TASK_KILLABLE);
+	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_state(&lock->lock, TASK_UNINTERRUPTIBLE);
+}
+EXPORT_SYMBOL(_mutex_lock_nested);
+
+void __lockfunc _mutex_lock_io_nested(struct mutex *lock, int subclass)
+{
+	int token;
+
+	token = io_schedule_prepare();
+
+	mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_);
+	__rt_mutex_lock_state(&lock->lock, TASK_UNINTERRUPTIBLE);
+
+	io_schedule_finish(token);
+}
+EXPORT_SYMBOL_GPL(_mutex_lock_io_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_state(&lock->lock, TASK_UNINTERRUPTIBLE);
+}
+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_state(&lock->lock, TASK_INTERRUPTIBLE);
+	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_state(&lock->lock, TASK_KILLABLE);
+	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);
+
+/**
+ * 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/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 2874bf5561620..602eb7821a1b1 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -8,6 +8,11 @@
  *  Copyright (C) 2005-2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com>
  *  Copyright (C) 2005 Kihon Technologies Inc., Steven Rostedt
  *  Copyright (C) 2006 Esben Nielsen
+ * Adaptive Spinlocks:
+ *  Copyright (C) 2008 Novell, Inc., Gregory Haskins, Sven Dietrich,
+ *				     and Peter Morreale,
+ * Adaptive Spinlocks simplification:
+ *  Copyright (C) 2008 Red Hat, Inc., Steven Rostedt <srostedt@redhat.com>
  *
  *  See Documentation/locking/rt-mutex-design.rst for details.
  */
@@ -19,6 +24,8 @@
 #include <linux/sched/wake_q.h>
 #include <linux/sched/debug.h>
 #include <linux/timer.h>
+#include <linux/ww_mutex.h>
+#include <linux/blkdev.h>
 
 #include "rtmutex_common.h"
 
@@ -136,6 +143,12 @@ static void fixup_rt_mutex_waiters(struct rt_mutex *lock)
 		WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS);
 }
 
+static int rt_mutex_real_waiter(struct rt_mutex_waiter *waiter)
+{
+	return waiter && waiter != PI_WAKEUP_INPROGRESS &&
+		waiter != PI_REQUEUE_INPROGRESS;
+}
+
 /*
  * We can speed up the acquire/release, if there's no debugging state to be
  * set up.
@@ -229,7 +242,7 @@ static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock,
  * Only use with rt_mutex_waiter_{less,equal}()
  */
 #define task_to_waiter(p)	\
-	&(struct rt_mutex_waiter){ .prio = (p)->prio, .deadline = (p)->dl.deadline }
+	&(struct rt_mutex_waiter){ .prio = (p)->prio, .deadline = (p)->dl.deadline, .task = (p) }
 
 static inline int
 rt_mutex_waiter_less(struct rt_mutex_waiter *left,
@@ -269,6 +282,27 @@ rt_mutex_waiter_equal(struct rt_mutex_waiter *left,
 	return 1;
 }
 
+#define STEAL_NORMAL  0
+#define STEAL_LATERAL 1
+
+static inline int
+rt_mutex_steal(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, int mode)
+{
+	struct rt_mutex_waiter *top_waiter = rt_mutex_top_waiter(lock);
+
+	if (waiter == top_waiter || rt_mutex_waiter_less(waiter, top_waiter))
+		return 1;
+
+	/*
+	 * Note that RT tasks are excluded from lateral-steals
+	 * to prevent the introduction of an unbounded latency.
+	 */
+	if (mode == STEAL_NORMAL || rt_task(waiter->task))
+		return 0;
+
+	return rt_mutex_waiter_equal(waiter, top_waiter);
+}
+
 static void
 rt_mutex_enqueue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter)
 {
@@ -373,6 +407,14 @@ static bool rt_mutex_cond_detect_deadlock(struct rt_mutex_waiter *waiter,
 	return debug_rt_mutex_detect_deadlock(waiter, chwalk);
 }
 
+static void rt_mutex_wake_waiter(struct rt_mutex_waiter *waiter)
+{
+	if (waiter->savestate)
+		wake_up_lock_sleeper(waiter->task);
+	else
+		wake_up_process(waiter->task);
+}
+
 /*
  * Max number of times we'll walk the boosting chain:
  */
@@ -380,7 +422,8 @@ int max_lock_depth = 1024;
 
 static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p)
 {
-	return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL;
+	return rt_mutex_real_waiter(p->pi_blocked_on) ?
+		p->pi_blocked_on->lock : NULL;
 }
 
 /*
@@ -516,7 +559,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	 * 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;
 
 	/*
@@ -696,13 +739,16 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
 	 * follow here. This is the end of the chain we are walking.
 	 */
 	if (!rt_mutex_owner(lock)) {
+		struct rt_mutex_waiter *lock_top_waiter;
+
 		/*
 		 * If the requeue [7] above changed the top waiter,
 		 * then we need to wake the new top waiter up to try
 		 * to get the lock.
 		 */
-		if (prerequeue_top_waiter != rt_mutex_top_waiter(lock))
-			wake_up_process(rt_mutex_top_waiter(lock)->task);
+		lock_top_waiter = rt_mutex_top_waiter(lock);
+		if (prerequeue_top_waiter != lock_top_waiter)
+			rt_mutex_wake_waiter(lock_top_waiter);
 		raw_spin_unlock_irq(&lock->wait_lock);
 		return 0;
 	}
@@ -803,9 +849,11 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
  * @task:   The task which wants to acquire the lock
  * @waiter: The waiter that is queued to the lock's wait tree if the
  *	    callsite called task_blocked_on_lock(), otherwise NULL
+ * @mode:   Lock steal mode (STEAL_NORMAL, STEAL_LATERAL)
  */
-static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
-				struct rt_mutex_waiter *waiter)
+static int __try_to_take_rt_mutex(struct rt_mutex *lock,
+				  struct task_struct *task,
+				  struct rt_mutex_waiter *waiter, int mode)
 {
 	lockdep_assert_held(&lock->wait_lock);
 
@@ -841,12 +889,11 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
 	 */
 	if (waiter) {
 		/*
-		 * If waiter is not the highest priority waiter of
-		 * @lock, give up.
+		 * If waiter is not the highest priority waiter of @lock,
+		 * or its peer when lateral steal is allowed, give up.
 		 */
-		if (waiter != rt_mutex_top_waiter(lock))
+		if (!rt_mutex_steal(lock, waiter, mode))
 			return 0;
-
 		/*
 		 * We can acquire the lock. Remove the waiter from the
 		 * lock waiters tree.
@@ -864,14 +911,12 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
 		 */
 		if (rt_mutex_has_waiters(lock)) {
 			/*
-			 * If @task->prio is greater than or equal to
-			 * the top waiter priority (kernel view),
-			 * @task lost.
+			 * If @task->prio is greater than the top waiter
+			 * priority (kernel view), or equal to it when a
+			 * lateral steal is forbidden, @task lost.
 			 */
-			if (!rt_mutex_waiter_less(task_to_waiter(task),
-						  rt_mutex_top_waiter(lock)))
+			if (!rt_mutex_steal(lock, task_to_waiter(task), mode))
 				return 0;
-
 			/*
 			 * The current top waiter stays enqueued. We
 			 * don't have to change anything in the lock
@@ -918,6 +963,344 @@ static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
 	return 1;
 }
 
+#ifdef CONFIG_PREEMPT_RT
+/*
+ * preemptible spin_lock functions:
+ */
+static inline void rt_spin_lock_fastlock(struct rt_mutex *lock,
+					 void  (*slowfn)(struct rt_mutex *lock))
+{
+	might_sleep_no_state_check();
+
+	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
+		return;
+	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_release(lock, current, NULL)))
+		return;
+	else
+		slowfn(lock);
+}
+#ifdef CONFIG_SMP
+/*
+ * Note that owner is a speculative pointer and dereferencing relies
+ * on rcu_read_lock() and the check against the lock owner.
+ */
+static int adaptive_wait(struct rt_mutex *lock,
+			 struct task_struct *owner)
+{
+	int res = 0;
+
+	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
+
+static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
+				   struct rt_mutex_waiter *waiter,
+				   struct task_struct *task,
+				   enum rtmutex_chainwalk chwalk);
+/*
+ * Slow path lock function spin_lock style: this variant is very
+ * careful not to miss any non-lock wakeups.
+ *
+ * We store the current state under p->pi_lock in p->saved_state and
+ * the try_to_wake_up() code handles this accordingly.
+ */
+void __sched rt_spin_lock_slowlock_locked(struct rt_mutex *lock,
+					  struct rt_mutex_waiter *waiter,
+					  unsigned long flags)
+{
+	struct task_struct *lock_owner, *self = current;
+	struct rt_mutex_waiter *top_waiter;
+	int ret;
+
+	if (__try_to_take_rt_mutex(lock, self, NULL, STEAL_LATERAL))
+		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().
+	 */
+	raw_spin_lock(&self->pi_lock);
+	self->saved_state = self->state;
+	__set_current_state_no_track(TASK_UNINTERRUPTIBLE);
+	raw_spin_unlock(&self->pi_lock);
+
+	ret = task_blocks_on_rt_mutex(lock, waiter, self, RT_MUTEX_MIN_CHAINWALK);
+	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_irqrestore(&lock->wait_lock, flags);
+
+		debug_rt_mutex_print_deadlock(waiter);
+
+		if (top_waiter != waiter || adaptive_wait(lock, lock_owner))
+			schedule();
+
+		raw_spin_lock_irqsave(&lock->wait_lock, flags);
+
+		raw_spin_lock(&self->pi_lock);
+		__set_current_state_no_track(TASK_UNINTERRUPTIBLE);
+		raw_spin_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.
+	 */
+	raw_spin_lock(&self->pi_lock);
+	__set_current_state_no_track(self->saved_state);
+	self->saved_state = TASK_RUNNING;
+	raw_spin_unlock(&self->pi_lock);
+
+	/*
+	 * 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(!RB_EMPTY_NODE(&waiter->tree_entry));
+}
+
+static void noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock)
+{
+	struct rt_mutex_waiter waiter;
+	unsigned long flags;
+
+	rt_mutex_init_waiter(&waiter, true);
+
+	raw_spin_lock_irqsave(&lock->wait_lock, flags);
+	rt_spin_lock_slowlock_locked(lock, &waiter, flags);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
+	debug_rt_mutex_free_waiter(&waiter);
+}
+
+static bool __sched __rt_mutex_unlock_common(struct rt_mutex *lock,
+					     struct wake_q_head *wake_q,
+					     struct wake_q_head *wq_sleeper);
+/*
+ * Slow path to release a rt_mutex spin_lock style
+ */
+void __sched rt_spin_lock_slowunlock(struct rt_mutex *lock)
+{
+	unsigned long flags;
+	DEFINE_WAKE_Q(wake_q);
+	DEFINE_WAKE_Q(wake_sleeper_q);
+	bool postunlock;
+
+	raw_spin_lock_irqsave(&lock->wait_lock, flags);
+	postunlock = __rt_mutex_unlock_common(lock, &wake_q, &wake_sleeper_q);
+	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
+
+	if (postunlock)
+		rt_mutex_postunlock(&wake_q, &wake_sleeper_q);
+}
+
+void __lockfunc rt_spin_lock(spinlock_t *lock)
+{
+	sleeping_lock_inc();
+	rcu_read_lock();
+	migrate_disable();
+	spin_acquire(&lock->dep_map, 0, 0, _RET_IP_);
+	rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock);
+}
+EXPORT_SYMBOL(rt_spin_lock);
+
+void __lockfunc __rt_spin_lock(struct rt_mutex *lock)
+{
+	rt_spin_lock_fastlock(lock, rt_spin_lock_slowlock);
+}
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass)
+{
+	sleeping_lock_inc();
+	rcu_read_lock();
+	migrate_disable();
+	spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
+	rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock);
+}
+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);
+	migrate_enable();
+	rcu_read_unlock();
+	sleeping_lock_dec();
+}
+EXPORT_SYMBOL(rt_spin_unlock);
+
+void __lockfunc __rt_spin_unlock(struct rt_mutex *lock)
+{
+	rt_spin_lock_fastunlock(lock, rt_spin_lock_slowunlock);
+}
+EXPORT_SYMBOL(__rt_spin_unlock);
+
+/*
+ * Wait for the lock to get unlocked: instead of polling for an unlock
+ * (like raw spinlocks do), we lock and unlock, to force the kernel to
+ * schedule if there's contention:
+ */
+void __lockfunc rt_spin_unlock_wait(spinlock_t *lock)
+{
+	spin_lock(lock);
+	spin_unlock(lock);
+}
+EXPORT_SYMBOL(rt_spin_unlock_wait);
+
+int __lockfunc rt_spin_trylock(spinlock_t *lock)
+{
+	int ret;
+
+	sleeping_lock_inc();
+	migrate_disable();
+	ret = __rt_mutex_trylock(&lock->lock);
+	if (ret) {
+		spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+		rcu_read_lock();
+	} else {
+		migrate_enable();
+		sleeping_lock_dec();
+	}
+	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) {
+		sleeping_lock_inc();
+		rcu_read_lock();
+		migrate_disable();
+		spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+	} else
+		local_bh_enable();
+	return ret;
+}
+EXPORT_SYMBOL(rt_spin_trylock_bh);
+
+int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags)
+{
+	int ret;
+
+	*flags = 0;
+	ret = __rt_mutex_trylock(&lock->lock);
+	if (ret) {
+		sleeping_lock_inc();
+		rcu_read_lock();
+		migrate_disable();
+		spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+	}
+	return ret;
+}
+EXPORT_SYMBOL(rt_spin_trylock_irqsave);
+
+void
+__rt_spin_lock_init(spinlock_t *lock, 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 *)lock, sizeof(*lock));
+	lockdep_init_map(&lock->dep_map, name, key, 0);
+#endif
+}
+EXPORT_SYMBOL(__rt_spin_lock_init);
+
+#endif /* PREEMPT_RT */
+
+#ifdef CONFIG_PREEMPT_RT
+	static inline int __sched
+__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx)
+{
+	struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock);
+	struct ww_acquire_ctx *hold_ctx = READ_ONCE(ww->ctx);
+
+	if (!hold_ctx)
+		return 0;
+
+	if (unlikely(ctx == hold_ctx))
+		return -EALREADY;
+
+	if (ctx->stamp - hold_ctx->stamp <= LONG_MAX &&
+	    (ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) {
+#ifdef CONFIG_DEBUG_MUTEXES
+		DEBUG_LOCKS_WARN_ON(ctx->contending_lock);
+		ctx->contending_lock = ww;
+#endif
+		return -EDEADLK;
+	}
+
+	return 0;
+}
+#else
+	static inline int __sched
+__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx)
+{
+	BUG();
+	return 0;
+}
+
+#endif
+
+static inline int
+try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task,
+		     struct rt_mutex_waiter *waiter)
+{
+	return __try_to_take_rt_mutex(lock, task, waiter, STEAL_NORMAL);
+}
+
 /*
  * Task blocks on lock.
  *
@@ -950,6 +1333,22 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 		return -EDEADLK;
 
 	raw_spin_lock(&task->pi_lock);
+	/*
+	 * In the case of futex requeue PI, this will be a proxy
+	 * lock. The task will wake unaware that it is enqueueed on
+	 * this lock. Avoid blocking on two locks and corrupting
+	 * pi_blocked_on via the PI_WAKEUP_INPROGRESS
+	 * flag. futex_wait_requeue_pi() sets this when it wakes up
+	 * before requeue (due to a signal or timeout). Do not enqueue
+	 * the task if PI_WAKEUP_INPROGRESS is set.
+	 */
+	if (task != current && task->pi_blocked_on == PI_WAKEUP_INPROGRESS) {
+		raw_spin_unlock(&task->pi_lock);
+		return -EAGAIN;
+	}
+
+       BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on));
+
 	waiter->task = task;
 	waiter->lock = lock;
 	waiter->prio = task->prio;
@@ -973,7 +1372,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
 		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 (rt_mutex_cond_detect_deadlock(waiter, chwalk)) {
 		chain_walk = 1;
@@ -1015,6 +1414,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
  * Called with lock->wait_lock held and interrupts disabled.
  */
 static void mark_wakeup_next_waiter(struct wake_q_head *wake_q,
+				    struct wake_q_head *wake_sleeper_q,
 				    struct rt_mutex *lock)
 {
 	struct rt_mutex_waiter *waiter;
@@ -1054,7 +1454,10 @@ static void mark_wakeup_next_waiter(struct wake_q_head *wake_q,
 	 * Pairs with preempt_enable() in rt_mutex_postunlock();
 	 */
 	preempt_disable();
-	wake_q_add(wake_q, waiter->task);
+	if (waiter->savestate)
+		wake_q_add_sleeper(wake_sleeper_q, waiter->task);
+	else
+		wake_q_add(wake_q, waiter->task);
 	raw_spin_unlock(&current->pi_lock);
 }
 
@@ -1069,7 +1472,7 @@ static void remove_waiter(struct rt_mutex *lock,
 {
 	bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock));
 	struct task_struct *owner = rt_mutex_owner(lock);
-	struct rt_mutex *next_lock;
+	struct rt_mutex *next_lock = NULL;
 
 	lockdep_assert_held(&lock->wait_lock);
 
@@ -1095,7 +1498,8 @@ static void remove_waiter(struct rt_mutex *lock,
 	rt_mutex_adjust_prio(owner);
 
 	/* Store the lock on which owner is blocked or NULL */
-	next_lock = task_blocked_on_lock(owner);
+	if (rt_mutex_real_waiter(owner->pi_blocked_on))
+		next_lock = task_blocked_on_lock(owner);
 
 	raw_spin_unlock(&owner->pi_lock);
 
@@ -1131,26 +1535,28 @@ void rt_mutex_adjust_pi(struct task_struct *task)
 	raw_spin_lock_irqsave(&task->pi_lock, flags);
 
 	waiter = task->pi_blocked_on;
-	if (!waiter || rt_mutex_waiter_equal(waiter, task_to_waiter(task))) {
+	if (!rt_mutex_real_waiter(waiter) ||
+	    rt_mutex_waiter_equal(waiter, task_to_waiter(task))) {
 		raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 		return;
 	}
 	next_lock = waiter->lock;
-	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 
 	/* gets dropped in rt_mutex_adjust_prio_chain()! */
 	get_task_struct(task);
 
+	raw_spin_unlock_irqrestore(&task->pi_lock, flags);
 	rt_mutex_adjust_prio_chain(task, RT_MUTEX_MIN_CHAINWALK, NULL,
 				   next_lock, NULL, task);
 }
 
-void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter)
+void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter, bool savestate)
 {
 	debug_rt_mutex_init_waiter(waiter);
 	RB_CLEAR_NODE(&waiter->pi_tree_entry);
 	RB_CLEAR_NODE(&waiter->tree_entry);
 	waiter->task = NULL;
+	waiter->savestate = savestate;
 }
 
 /**
@@ -1166,7 +1572,8 @@ void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter)
 static int __sched
 __rt_mutex_slowlock(struct rt_mutex *lock, int state,
 		    struct hrtimer_sleeper *timeout,
-		    struct rt_mutex_waiter *waiter)
+		    struct rt_mutex_waiter *waiter,
+		    struct ww_acquire_ctx *ww_ctx)
 {
 	int ret = 0;
 
@@ -1175,16 +1582,17 @@ __rt_mutex_slowlock(struct rt_mutex *lock, int state,
 		if (try_to_take_rt_mutex(lock, current, waiter))
 			break;
 
-		/*
-		 * TASK_INTERRUPTIBLE checks for signals and
-		 * timeout. Ignored otherwise.
-		 */
-		if (likely(state == TASK_INTERRUPTIBLE)) {
-			/* Signal pending? */
-			if (signal_pending(current))
-				ret = -EINTR;
-			if (timeout && !timeout->task)
-				ret = -ETIMEDOUT;
+		if (timeout && !timeout->task) {
+			ret = -ETIMEDOUT;
+			break;
+		}
+		if (signal_pending_state(state, current)) {
+			ret = -EINTR;
+			break;
+		}
+
+		if (ww_ctx && ww_ctx->acquired > 0) {
+			ret = __mutex_lock_check_stamp(lock, ww_ctx);
 			if (ret)
 				break;
 		}
@@ -1223,19 +1631,157 @@ static void rt_mutex_handle_deadlock(int res, int detect_deadlock,
 	}
 }
 
+static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww,
+						   struct ww_acquire_ctx *ww_ctx)
+{
+#ifdef CONFIG_DEBUG_MUTEXES
+	/*
+	 * If this WARN_ON triggers, you used ww_mutex_lock to acquire,
+	 * but released with a normal mutex_unlock in this call.
+	 *
+	 * This should never happen, always use ww_mutex_unlock.
+	 */
+	DEBUG_LOCKS_WARN_ON(ww->ctx);
+
+	/*
+	 * Not quite done after calling ww_acquire_done() ?
+	 */
+	DEBUG_LOCKS_WARN_ON(ww_ctx->done_acquire);
+
+	if (ww_ctx->contending_lock) {
+		/*
+		 * After -EDEADLK you tried to
+		 * acquire a different ww_mutex? Bad!
+		 */
+		DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock != ww);
+
+		/*
+		 * You called ww_mutex_lock after receiving -EDEADLK,
+		 * but 'forgot' to unlock everything else first?
+		 */
+		DEBUG_LOCKS_WARN_ON(ww_ctx->acquired > 0);
+		ww_ctx->contending_lock = NULL;
+	}
+
+	/*
+	 * Naughty, using a different class will lead to undefined behavior!
+	 */
+	DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class);
+#endif
+	ww_ctx->acquired++;
+}
+
+#ifdef CONFIG_PREEMPT_RT
+static void ww_mutex_account_lock(struct rt_mutex *lock,
+				  struct ww_acquire_ctx *ww_ctx)
+{
+	struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock);
+	struct rt_mutex_waiter *waiter, *n;
+
+	/*
+	 * This branch gets optimized out for the common case,
+	 * and is only important for ww_mutex_lock.
+	 */
+	ww_mutex_lock_acquired(ww, ww_ctx);
+	ww->ctx = ww_ctx;
+
+	/*
+	 * Give any possible sleeping processes the chance to wake up,
+	 * so they can recheck if they have to back off.
+	 */
+	rbtree_postorder_for_each_entry_safe(waiter, n, &lock->waiters.rb_root,
+					     tree_entry) {
+		/* XXX debug rt mutex waiter wakeup */
+
+		BUG_ON(waiter->lock != lock);
+		rt_mutex_wake_waiter(waiter);
+	}
+}
+
+#else
+
+static void ww_mutex_account_lock(struct rt_mutex *lock,
+				  struct ww_acquire_ctx *ww_ctx)
+{
+	BUG();
+}
+#endif
+
+int __sched rt_mutex_slowlock_locked(struct rt_mutex *lock, int state,
+				     struct hrtimer_sleeper *timeout,
+				     enum rtmutex_chainwalk chwalk,
+				     struct ww_acquire_ctx *ww_ctx,
+				     struct rt_mutex_waiter *waiter)
+{
+	int ret;
+
+#ifdef CONFIG_PREEMPT_RT
+	if (ww_ctx) {
+		struct ww_mutex *ww;
+
+		ww = container_of(lock, struct ww_mutex, base.lock);
+		if (unlikely(ww_ctx == READ_ONCE(ww->ctx)))
+			return -EALREADY;
+	}
+#endif
+
+	/* Try to acquire the lock again: */
+	if (try_to_take_rt_mutex(lock, current, NULL)) {
+		if (ww_ctx)
+			ww_mutex_account_lock(lock, ww_ctx);
+		return 0;
+	}
+
+	set_current_state(state);
+
+	/* Setup the timer, when timeout != NULL */
+	if (unlikely(timeout))
+		hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);
+
+	ret = task_blocks_on_rt_mutex(lock, waiter, current, chwalk);
+
+	if (likely(!ret)) {
+		/* sleep on the mutex */
+		ret = __rt_mutex_slowlock(lock, state, timeout, waiter,
+					  ww_ctx);
+	} else if (ww_ctx) {
+		/* ww_mutex received EDEADLK, let it become EALREADY */
+		ret = __mutex_lock_check_stamp(lock, ww_ctx);
+		BUG_ON(!ret);
+	}
+
+	if (unlikely(ret)) {
+		__set_current_state(TASK_RUNNING);
+		remove_waiter(lock, waiter);
+		/* ww_mutex wants to report EDEADLK/EALREADY, let it */
+		if (!ww_ctx)
+			rt_mutex_handle_deadlock(ret, chwalk, waiter);
+	} else if (ww_ctx) {
+		ww_mutex_account_lock(lock, ww_ctx);
+	}
+
+	/*
+	 * try_to_take_rt_mutex() sets the waiter bit
+	 * unconditionally. We might have to fix that up.
+	 */
+	fixup_rt_mutex_waiters(lock);
+	return ret;
+}
+
 /*
  * Slow path lock function:
  */
 static int __sched
 rt_mutex_slowlock(struct rt_mutex *lock, int state,
 		  struct hrtimer_sleeper *timeout,
-		  enum rtmutex_chainwalk chwalk)
+		  enum rtmutex_chainwalk chwalk,
+		  struct ww_acquire_ctx *ww_ctx)
 {
 	struct rt_mutex_waiter waiter;
 	unsigned long flags;
 	int ret = 0;
 
-	rt_mutex_init_waiter(&waiter);
+	rt_mutex_init_waiter(&waiter, false);
 
 	/*
 	 * Technically we could use raw_spin_[un]lock_irq() here, but this can
@@ -1247,35 +1793,8 @@ rt_mutex_slowlock(struct rt_mutex *lock, int state,
 	 */
 	raw_spin_lock_irqsave(&lock->wait_lock, flags);
 
-	/* Try to acquire the lock again: */
-	if (try_to_take_rt_mutex(lock, current, NULL)) {
-		raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
-		return 0;
-	}
-
-	set_current_state(state);
-
-	/* Setup the timer, when timeout != NULL */
-	if (unlikely(timeout))
-		hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS);
-
-	ret = task_blocks_on_rt_mutex(lock, &waiter, current, chwalk);
-
-	if (likely(!ret))
-		/* sleep on the mutex */
-		ret = __rt_mutex_slowlock(lock, state, timeout, &waiter);
-
-	if (unlikely(ret)) {
-		__set_current_state(TASK_RUNNING);
-		remove_waiter(lock, &waiter);
-		rt_mutex_handle_deadlock(ret, chwalk, &waiter);
-	}
-
-	/*
-	 * try_to_take_rt_mutex() sets the waiter bit
-	 * unconditionally. We might have to fix that up.
-	 */
-	fixup_rt_mutex_waiters(lock);
+	ret = rt_mutex_slowlock_locked(lock, state, timeout, chwalk, ww_ctx,
+				       &waiter);
 
 	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
@@ -1336,7 +1855,8 @@ static inline int rt_mutex_slowtrylock(struct rt_mutex *lock)
  * Return whether the current task needs to call rt_mutex_postunlock().
  */
 static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
-					struct wake_q_head *wake_q)
+					struct wake_q_head *wake_q,
+					struct wake_q_head *wake_sleeper_q)
 {
 	unsigned long flags;
 
@@ -1390,7 +1910,7 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
 	 *
 	 * Queue the next waiter for wakeup once we release the wait_lock.
 	 */
-	mark_wakeup_next_waiter(wake_q, lock);
+	mark_wakeup_next_waiter(wake_q, wake_sleeper_q, lock);
 	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
 	return true; /* call rt_mutex_postunlock() */
@@ -1404,29 +1924,45 @@ static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock,
  */
 static inline int
 rt_mutex_fastlock(struct rt_mutex *lock, int state,
+		  struct ww_acquire_ctx *ww_ctx,
 		  int (*slowfn)(struct rt_mutex *lock, int state,
 				struct hrtimer_sleeper *timeout,
-				enum rtmutex_chainwalk chwalk))
+				enum rtmutex_chainwalk chwalk,
+				struct ww_acquire_ctx *ww_ctx))
 {
 	if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
 		return 0;
 
-	return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK);
+	/*
+	 * If rt_mutex blocks, the function sched_submit_work will not call
+	 * blk_schedule_flush_plug (because tsk_is_pi_blocked would be true).
+	 * We must call blk_schedule_flush_plug here, if we don't call it,
+	 * a deadlock in I/O may happen.
+	 */
+	if (unlikely(blk_needs_flush_plug(current)))
+		blk_schedule_flush_plug(current);
+
+	return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK, ww_ctx);
 }
 
 static inline int
 rt_mutex_timed_fastlock(struct rt_mutex *lock, int state,
 			struct hrtimer_sleeper *timeout,
 			enum rtmutex_chainwalk chwalk,
+			struct ww_acquire_ctx *ww_ctx,
 			int (*slowfn)(struct rt_mutex *lock, int state,
 				      struct hrtimer_sleeper *timeout,
-				      enum rtmutex_chainwalk chwalk))
+				      enum rtmutex_chainwalk chwalk,
+				      struct ww_acquire_ctx *ww_ctx))
 {
 	if (chwalk == RT_MUTEX_MIN_CHAINWALK &&
 	    likely(rt_mutex_cmpxchg_acquire(lock, NULL, current)))
 		return 0;
 
-	return slowfn(lock, state, timeout, chwalk);
+	if (unlikely(blk_needs_flush_plug(current)))
+		blk_schedule_flush_plug(current);
+
+	return slowfn(lock, state, timeout, chwalk, ww_ctx);
 }
 
 static inline int
@@ -1442,9 +1978,11 @@ rt_mutex_fasttrylock(struct rt_mutex *lock,
 /*
  * Performs the wakeup of the the top-waiter and re-enables preemption.
  */
-void rt_mutex_postunlock(struct wake_q_head *wake_q)
+void rt_mutex_postunlock(struct wake_q_head *wake_q,
+			 struct wake_q_head *wake_sleeper_q)
 {
 	wake_up_q(wake_q);
+	wake_up_q_sleeper(wake_sleeper_q);
 
 	/* Pairs with preempt_disable() in rt_mutex_slowunlock() */
 	preempt_enable();
@@ -1453,23 +1991,46 @@ void rt_mutex_postunlock(struct wake_q_head *wake_q)
 static inline void
 rt_mutex_fastunlock(struct rt_mutex *lock,
 		    bool (*slowfn)(struct rt_mutex *lock,
-				   struct wake_q_head *wqh))
+				   struct wake_q_head *wqh,
+				   struct wake_q_head *wq_sleeper))
 {
 	DEFINE_WAKE_Q(wake_q);
+	DEFINE_WAKE_Q(wake_sleeper_q);
 
 	if (likely(rt_mutex_cmpxchg_release(lock, current, NULL)))
 		return;
 
-	if (slowfn(lock, &wake_q))
-		rt_mutex_postunlock(&wake_q);
+	if (slowfn(lock, &wake_q, &wake_sleeper_q))
+		rt_mutex_postunlock(&wake_q, &wake_sleeper_q);
+}
+
+int __sched __rt_mutex_lock_state(struct rt_mutex *lock, int state)
+{
+	might_sleep();
+	return rt_mutex_fastlock(lock, state, NULL, rt_mutex_slowlock);
+}
+
+/**
+ * rt_mutex_lock_state - lock a rt_mutex with a given state
+ *
+ * @lock:      The rt_mutex to be locked
+ * @state:     The state to set when blocking on the rt_mutex
+ */
+static inline int __sched rt_mutex_lock_state(struct rt_mutex *lock,
+					      unsigned int subclass, int state)
+{
+	int ret;
+
+	mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
+	ret = __rt_mutex_lock_state(lock, state);
+	if (ret)
+		mutex_release(&lock->dep_map, 1, _RET_IP_);
+	return ret;
 }
 
 static inline void __rt_mutex_lock(struct rt_mutex *lock, unsigned int subclass)
 {
-	might_sleep();
-
-	mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
-	rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock);
+	rt_mutex_lock_state(lock, subclass, TASK_UNINTERRUPTIBLE);
 }
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -1510,16 +2071,7 @@ EXPORT_SYMBOL_GPL(rt_mutex_lock);
  */
 int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock)
 {
-	int ret;
-
-	might_sleep();
-
-	mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	ret = rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, rt_mutex_slowlock);
-	if (ret)
-		mutex_release(&lock->dep_map, 1, _RET_IP_);
-
-	return ret;
+	return rt_mutex_lock_state(lock, 0, TASK_INTERRUPTIBLE);
 }
 EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible);
 
@@ -1536,6 +2088,22 @@ int __sched __rt_mutex_futex_trylock(struct rt_mutex *lock)
 	return __rt_mutex_slowtrylock(lock);
 }
 
+/**
+ * rt_mutex_lock_killable - lock a rt_mutex killable
+ *
+ * @lock:              the rt_mutex to be locked
+ * @detect_deadlock:   deadlock detection on/off
+ *
+ * Returns:
+ *  0          on success
+ * -EINTR      when interrupted by a signal
+ */
+int __sched rt_mutex_lock_killable(struct rt_mutex *lock)
+{
+	return rt_mutex_lock_state(lock, 0, TASK_KILLABLE);
+}
+EXPORT_SYMBOL_GPL(rt_mutex_lock_killable);
+
 /**
  * rt_mutex_timed_lock - lock a rt_mutex interruptible
  *			the timeout structure is provided
@@ -1559,6 +2127,7 @@ rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout)
 	mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
 	ret = rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout,
 				       RT_MUTEX_MIN_CHAINWALK,
+				       NULL,
 				       rt_mutex_slowlock);
 	if (ret)
 		mutex_release(&lock->dep_map, 1, _RET_IP_);
@@ -1567,6 +2136,18 @@ rt_mutex_timed_lock(struct rt_mutex *lock, struct hrtimer_sleeper *timeout)
 }
 EXPORT_SYMBOL_GPL(rt_mutex_timed_lock);
 
+int __sched __rt_mutex_trylock(struct rt_mutex *lock)
+{
+#ifdef CONFIG_PREEMPT_RT
+	if (WARN_ON_ONCE(in_irq() || in_nmi()))
+#else
+	if (WARN_ON_ONCE(in_irq() || in_nmi() || in_serving_softirq()))
+#endif
+		return 0;
+
+	return rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock);
+}
+
 /**
  * rt_mutex_trylock - try to lock a rt_mutex
  *
@@ -1582,10 +2163,7 @@ int __sched rt_mutex_trylock(struct rt_mutex *lock)
 {
 	int ret;
 
-	if (WARN_ON_ONCE(in_irq() || in_nmi() || in_serving_softirq()))
-		return 0;
-
-	ret = rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock);
+	ret = __rt_mutex_trylock(lock);
 	if (ret)
 		mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);
 
@@ -1593,6 +2171,11 @@ int __sched rt_mutex_trylock(struct rt_mutex *lock)
 }
 EXPORT_SYMBOL_GPL(rt_mutex_trylock);
 
+void __sched __rt_mutex_unlock(struct rt_mutex *lock)
+{
+	rt_mutex_fastunlock(lock, rt_mutex_slowunlock);
+}
+
 /**
  * rt_mutex_unlock - unlock a rt_mutex
  *
@@ -1601,16 +2184,13 @@ EXPORT_SYMBOL_GPL(rt_mutex_trylock);
 void __sched rt_mutex_unlock(struct rt_mutex *lock)
 {
 	mutex_release(&lock->dep_map, 1, _RET_IP_);
-	rt_mutex_fastunlock(lock, rt_mutex_slowunlock);
+	__rt_mutex_unlock(lock);
 }
 EXPORT_SYMBOL_GPL(rt_mutex_unlock);
 
-/**
- * Futex variant, that since futex variants do not use the fast-path, can be
- * simple and will not need to retry.
- */
-bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock,
-				    struct wake_q_head *wake_q)
+static bool __sched __rt_mutex_unlock_common(struct rt_mutex *lock,
+					     struct wake_q_head *wake_q,
+					     struct wake_q_head *wq_sleeper)
 {
 	lockdep_assert_held(&lock->wait_lock);
 
@@ -1627,23 +2207,35 @@ bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock,
 	 * avoid inversion prior to the wakeup.  preempt_disable()
 	 * therein pairs with rt_mutex_postunlock().
 	 */
-	mark_wakeup_next_waiter(wake_q, lock);
+	mark_wakeup_next_waiter(wake_q, wq_sleeper, lock);
 
 	return true; /* call postunlock() */
 }
 
+/**
+ * Futex variant, that since futex variants do not use the fast-path, can be
+ * simple and will not need to retry.
+ */
+bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock,
+				     struct wake_q_head *wake_q,
+				     struct wake_q_head *wq_sleeper)
+{
+	return __rt_mutex_unlock_common(lock, wake_q, wq_sleeper);
+}
+
 void __sched rt_mutex_futex_unlock(struct rt_mutex *lock)
 {
 	DEFINE_WAKE_Q(wake_q);
+	DEFINE_WAKE_Q(wake_sleeper_q);
 	unsigned long flags;
 	bool postunlock;
 
 	raw_spin_lock_irqsave(&lock->wait_lock, flags);
-	postunlock = __rt_mutex_futex_unlock(lock, &wake_q);
+	postunlock = __rt_mutex_futex_unlock(lock, &wake_q, &wake_sleeper_q);
 	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
 	if (postunlock)
-		rt_mutex_postunlock(&wake_q);
+		rt_mutex_postunlock(&wake_q, &wake_sleeper_q);
 }
 
 /**
@@ -1682,7 +2274,7 @@ void __rt_mutex_init(struct rt_mutex *lock, const char *name,
 	if (name && key)
 		debug_rt_mutex_init(lock, name, key);
 }
-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
@@ -1702,6 +2294,14 @@ void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
 				struct task_struct *proxy_owner)
 {
 	__rt_mutex_init(lock, NULL, NULL);
+#ifdef CONFIG_DEBUG_SPINLOCK
+	/*
+	 * get another key class for the wait_lock. LOCK_PI and UNLOCK_PI is
+	 * holding the ->wait_lock of the proxy_lock while unlocking a sleeping
+	 * lock.
+	 */
+	raw_spin_lock_init(&lock->wait_lock);
+#endif
 	debug_rt_mutex_proxy_lock(lock, proxy_owner);
 	rt_mutex_set_owner(lock, proxy_owner);
 }
@@ -1725,6 +2325,26 @@ void rt_mutex_proxy_unlock(struct rt_mutex *lock,
 	rt_mutex_set_owner(lock, NULL);
 }
 
+static void fixup_rt_mutex_blocked(struct rt_mutex *lock)
+{
+	struct task_struct *tsk = current;
+	/*
+	 * RT has a problem here when the wait got interrupted by a timeout
+	 * or a signal. task->pi_blocked_on is still set. The task must
+	 * acquire the hash bucket lock when returning from this function.
+	 *
+	 * If the hash bucket lock is contended then the
+	 * BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on)) in
+	 * task_blocks_on_rt_mutex() will trigger. This can be avoided by
+	 * clearing task->pi_blocked_on which removes the task from the
+	 * boosting chain of the rtmutex. That's correct because the task
+	 * is not longer blocked on it.
+	 */
+	raw_spin_lock(&tsk->pi_lock);
+	tsk->pi_blocked_on = NULL;
+	raw_spin_unlock(&tsk->pi_lock);
+}
+
 /**
  * __rt_mutex_start_proxy_lock() - Start lock acquisition for another task
  * @lock:		the rt_mutex to take
@@ -1755,6 +2375,34 @@ int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 	if (try_to_take_rt_mutex(lock, task, NULL))
 		return 1;
 
+#ifdef CONFIG_PREEMPT_RT
+	/*
+	 * In PREEMPT_RT there's an added race.
+	 * If the task, that we are about to requeue, times out,
+	 * it can set the PI_WAKEUP_INPROGRESS. This tells the requeue
+	 * to skip this task. But right after the task sets
+	 * its pi_blocked_on to PI_WAKEUP_INPROGRESS it can then
+	 * block on the spin_lock(&hb->lock), which in RT is an rtmutex.
+	 * This will replace the PI_WAKEUP_INPROGRESS with the actual
+	 * lock that it blocks on. We *must not* place this task
+	 * on this proxy lock in that case.
+	 *
+	 * To prevent this race, we first take the task's pi_lock
+	 * and check if it has updated its pi_blocked_on. If it has,
+	 * we assume that it woke up and we return -EAGAIN.
+	 * Otherwise, we set the task's pi_blocked_on to
+	 * PI_REQUEUE_INPROGRESS, so that if the task is waking up
+	 * it will know that we are in the process of requeuing it.
+	 */
+	raw_spin_lock(&task->pi_lock);
+	if (task->pi_blocked_on) {
+		raw_spin_unlock(&task->pi_lock);
+		return -EAGAIN;
+	}
+	task->pi_blocked_on = PI_REQUEUE_INPROGRESS;
+	raw_spin_unlock(&task->pi_lock);
+#endif
+
 	/* We enforce deadlock detection for futexes */
 	ret = task_blocks_on_rt_mutex(lock, waiter, task,
 				      RT_MUTEX_FULL_CHAINWALK);
@@ -1769,6 +2417,9 @@ int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 		ret = 0;
 	}
 
+	if (ret)
+		fixup_rt_mutex_blocked(lock);
+
 	debug_rt_mutex_print_deadlock(waiter);
 
 	return ret;
@@ -1854,12 +2505,15 @@ int rt_mutex_wait_proxy_lock(struct rt_mutex *lock,
 	raw_spin_lock_irq(&lock->wait_lock);
 	/* sleep on the mutex */
 	set_current_state(TASK_INTERRUPTIBLE);
-	ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter);
+	ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter, NULL);
 	/*
 	 * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might
 	 * have to fix that up.
 	 */
 	fixup_rt_mutex_waiters(lock);
+	if (ret)
+		fixup_rt_mutex_blocked(lock);
+
 	raw_spin_unlock_irq(&lock->wait_lock);
 
 	return ret;
@@ -1921,3 +2575,99 @@ bool rt_mutex_cleanup_proxy_lock(struct rt_mutex *lock,
 
 	return cleanup;
 }
+
+static inline int
+ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
+{
+#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH
+	unsigned tmp;
+
+	if (ctx->deadlock_inject_countdown-- == 0) {
+		tmp = ctx->deadlock_inject_interval;
+		if (tmp > UINT_MAX/4)
+			tmp = UINT_MAX;
+		else
+			tmp = tmp*2 + tmp + tmp/2;
+
+		ctx->deadlock_inject_interval = tmp;
+		ctx->deadlock_inject_countdown = tmp;
+		ctx->contending_lock = lock;
+
+		ww_mutex_unlock(lock);
+
+		return -EDEADLK;
+	}
+#endif
+
+	return 0;
+}
+
+#ifdef CONFIG_PREEMPT_RT
+int __sched
+ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
+{
+	int ret;
+
+	might_sleep();
+
+	mutex_acquire_nest(&lock->base.dep_map, 0, 0,
+			   ctx ? &ctx->dep_map : NULL, _RET_IP_);
+	ret = rt_mutex_slowlock(&lock->base.lock, TASK_INTERRUPTIBLE, NULL, 0,
+				ctx);
+	if (ret)
+		mutex_release(&lock->base.dep_map, 1, _RET_IP_);
+	else if (!ret && ctx && ctx->acquired > 1)
+		return ww_mutex_deadlock_injection(lock, ctx);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ww_mutex_lock_interruptible);
+
+int __sched
+ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
+{
+	int ret;
+
+	might_sleep();
+
+	mutex_acquire_nest(&lock->base.dep_map, 0, 0,
+			   ctx ? &ctx->dep_map : NULL, _RET_IP_);
+	ret = rt_mutex_slowlock(&lock->base.lock, TASK_UNINTERRUPTIBLE, NULL, 0,
+				ctx);
+	if (ret)
+		mutex_release(&lock->base.dep_map, 1, _RET_IP_);
+	else if (!ret && ctx && ctx->acquired > 1)
+		return ww_mutex_deadlock_injection(lock, ctx);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(ww_mutex_lock);
+
+void __sched ww_mutex_unlock(struct ww_mutex *lock)
+{
+	int nest = !!lock->ctx;
+
+	/*
+	 * The unlocking fastpath is the 0->1 transition from 'locked'
+	 * into 'unlocked' state:
+	 */
+	if (nest) {
+#ifdef CONFIG_DEBUG_MUTEXES
+		DEBUG_LOCKS_WARN_ON(!lock->ctx->acquired);
+#endif
+		if (lock->ctx->acquired > 0)
+			lock->ctx->acquired--;
+		lock->ctx = NULL;
+	}
+
+	mutex_release(&lock->base.dep_map, nest, _RET_IP_);
+	__rt_mutex_unlock(&lock->base.lock);
+}
+EXPORT_SYMBOL(ww_mutex_unlock);
+
+int __rt_mutex_owner_current(struct rt_mutex *lock)
+{
+	return rt_mutex_owner(lock) == current;
+}
+EXPORT_SYMBOL(__rt_mutex_owner_current);
+#endif
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index d1d62f942be22..546aaf058b9ec 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -15,6 +15,7 @@
 
 #include <linux/rtmutex.h>
 #include <linux/sched/wake_q.h>
+#include <linux/sched/debug.h>
 
 /*
  * This is the control structure for tasks blocked on a rt_mutex,
@@ -29,6 +30,7 @@ struct rt_mutex_waiter {
 	struct rb_node          pi_tree_entry;
 	struct task_struct	*task;
 	struct rt_mutex		*lock;
+	bool			savestate;
 #ifdef CONFIG_DEBUG_RT_MUTEXES
 	unsigned long		ip;
 	struct pid		*deadlock_task_pid;
@@ -130,12 +132,15 @@ enum rtmutex_chainwalk {
 /*
  * PI-futex support (proxy locking functions, etc.):
  */
+#define PI_WAKEUP_INPROGRESS	((struct rt_mutex_waiter *) 1)
+#define PI_REQUEUE_INPROGRESS	((struct rt_mutex_waiter *) 2)
+
 extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock);
 extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
 				       struct task_struct *proxy_owner);
 extern void rt_mutex_proxy_unlock(struct rt_mutex *lock,
 				  struct task_struct *proxy_owner);
-extern void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter);
+extern void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter, bool savetate);
 extern int __rt_mutex_start_proxy_lock(struct rt_mutex *lock,
 				     struct rt_mutex_waiter *waiter,
 				     struct task_struct *task);
@@ -153,9 +158,27 @@ extern int __rt_mutex_futex_trylock(struct rt_mutex *l);
 
 extern void rt_mutex_futex_unlock(struct rt_mutex *lock);
 extern bool __rt_mutex_futex_unlock(struct rt_mutex *lock,
-				 struct wake_q_head *wqh);
+				 struct wake_q_head *wqh,
+				 struct wake_q_head *wq_sleeper);
 
-extern void rt_mutex_postunlock(struct wake_q_head *wake_q);
+extern void rt_mutex_postunlock(struct wake_q_head *wake_q,
+				struct wake_q_head *wake_sleeper_q);
+
+/* RW semaphore special interface */
+struct ww_acquire_ctx;
+
+extern int __rt_mutex_lock_state(struct rt_mutex *lock, int state);
+extern int __rt_mutex_trylock(struct rt_mutex *lock);
+extern void __rt_mutex_unlock(struct rt_mutex *lock);
+int __sched rt_mutex_slowlock_locked(struct rt_mutex *lock, int state,
+				     struct hrtimer_sleeper *timeout,
+				     enum rtmutex_chainwalk chwalk,
+				     struct ww_acquire_ctx *ww_ctx,
+				     struct rt_mutex_waiter *waiter);
+void __sched rt_spin_lock_slowlock_locked(struct rt_mutex *lock,
+					  struct rt_mutex_waiter *waiter,
+					  unsigned long flags);
+void __sched rt_spin_lock_slowunlock(struct rt_mutex *lock);
 
 #ifdef CONFIG_DEBUG_RT_MUTEXES
 # include "rtmutex-debug.h"
diff --git a/kernel/locking/rwlock-rt.c b/kernel/locking/rwlock-rt.c
new file mode 100644
index 0000000000000..0ae8c62ea8320
--- /dev/null
+++ b/kernel/locking/rwlock-rt.c
@@ -0,0 +1,384 @@
+/*
+ */
+#include <linux/sched/debug.h>
+#include <linux/export.h>
+
+#include "rtmutex_common.h"
+#include <linux/rwlock_types_rt.h>
+
+/*
+ * RT-specific reader/writer locks
+ *
+ * write_lock()
+ *  1) Lock lock->rtmutex
+ *  2) Remove the reader BIAS to force readers into the slow path
+ *  3) Wait until all readers have left the critical region
+ *  4) Mark it write locked
+ *
+ * write_unlock()
+ *  1) Remove the write locked marker
+ *  2) Set the reader BIAS so readers can use the fast path again
+ *  3) Unlock lock->rtmutex to release blocked readers
+ *
+ * read_lock()
+ *  1) Try fast path acquisition (reader BIAS is set)
+ *  2) Take lock->rtmutex.wait_lock which protects the writelocked flag
+ *  3) If !writelocked, acquire it for read
+ *  4) If writelocked, block on lock->rtmutex
+ *  5) unlock lock->rtmutex, goto 1)
+ *
+ * read_unlock()
+ *  1) Try fast path release (reader count != 1)
+ *  2) Wake the writer waiting in write_lock()#3
+ *
+ * read_lock()#3 has the consequence, that rw locks on RT are not writer
+ * fair, but writers, which should be avoided in RT tasks (think tasklist
+ * lock), are subject to the rtmutex priority/DL inheritance mechanism.
+ *
+ * It's possible to make the rw locks writer fair by keeping a list of
+ * active readers. A blocked writer would force all newly incoming readers
+ * to block on the rtmutex, but the rtmutex would have to be proxy locked
+ * for one reader after the other. We can't use multi-reader inheritance
+ * because there is no way to support that with
+ * SCHED_DEADLINE. Implementing the one by one reader boosting/handover
+ * mechanism is a major surgery for a very dubious value.
+ *
+ * The risk of writer starvation is there, but the pathological use cases
+ * which trigger it are not necessarily the typical RT workloads.
+ */
+
+void __rwlock_biased_rt_init(struct rt_rw_lock *lock, const char *name,
+			     struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/*
+	 * Make sure we are not reinitializing a held semaphore:
+	 */
+	debug_check_no_locks_freed((void *)lock, sizeof(*lock));
+	lockdep_init_map(&lock->dep_map, name, key, 0);
+#endif
+	atomic_set(&lock->readers, READER_BIAS);
+	rt_mutex_init(&lock->rtmutex);
+	lock->rtmutex.save_state = 1;
+}
+
+int __read_rt_trylock(struct rt_rw_lock *lock)
+{
+	int r, old;
+
+	/*
+	 * Increment reader count, if lock->readers < 0, i.e. READER_BIAS is
+	 * set.
+	 */
+	for (r = atomic_read(&lock->readers); r < 0;) {
+		old = atomic_cmpxchg(&lock->readers, r, r + 1);
+		if (likely(old == r))
+			return 1;
+		r = old;
+	}
+	return 0;
+}
+
+void __sched __read_rt_lock(struct rt_rw_lock *lock)
+{
+	struct rt_mutex *m = &lock->rtmutex;
+	struct rt_mutex_waiter waiter;
+	unsigned long flags;
+
+	if (__read_rt_trylock(lock))
+		return;
+
+	raw_spin_lock_irqsave(&m->wait_lock, flags);
+	/*
+	 * Allow readers as long as the writer has not completely
+	 * acquired the semaphore for write.
+	 */
+	if (atomic_read(&lock->readers) != WRITER_BIAS) {
+		atomic_inc(&lock->readers);
+		raw_spin_unlock_irqrestore(&m->wait_lock, flags);
+		return;
+	}
+
+	/*
+	 * Call into the slow lock path with the rtmutex->wait_lock
+	 * held, so this can't result in the following race:
+	 *
+	 * Reader1		Reader2		Writer
+	 *			read_lock()
+	 *					write_lock()
+	 *					rtmutex_lock(m)
+	 *					swait()
+	 * read_lock()
+	 * unlock(m->wait_lock)
+	 *			read_unlock()
+	 *			swake()
+	 *					lock(m->wait_lock)
+	 *					lock->writelocked=true
+	 *					unlock(m->wait_lock)
+	 *
+	 *					write_unlock()
+	 *					lock->writelocked=false
+	 *					rtmutex_unlock(m)
+	 *			read_lock()
+	 *					write_lock()
+	 *					rtmutex_lock(m)
+	 *					swait()
+	 * rtmutex_lock(m)
+	 *
+	 * That would put Reader1 behind the writer waiting on
+	 * Reader2 to call read_unlock() which might be unbound.
+	 */
+	rt_mutex_init_waiter(&waiter, true);
+	rt_spin_lock_slowlock_locked(m, &waiter, flags);
+	/*
+	 * The slowlock() above is guaranteed to return with the rtmutex is
+	 * now held, so there can't be a writer active. Increment the reader
+	 * count and immediately drop the rtmutex again.
+	 */
+	atomic_inc(&lock->readers);
+	raw_spin_unlock_irqrestore(&m->wait_lock, flags);
+	rt_spin_lock_slowunlock(m);
+
+	debug_rt_mutex_free_waiter(&waiter);
+}
+
+void __read_rt_unlock(struct rt_rw_lock *lock)
+{
+	struct rt_mutex *m = &lock->rtmutex;
+	struct task_struct *tsk;
+
+	/*
+	 * sem->readers can only hit 0 when a writer is waiting for the
+	 * active readers to leave the critical region.
+	 */
+	if (!atomic_dec_and_test(&lock->readers))
+		return;
+
+	raw_spin_lock_irq(&m->wait_lock);
+	/*
+	 * Wake the writer, i.e. the rtmutex owner. It might release the
+	 * rtmutex concurrently in the fast path, but to clean up the rw
+	 * lock it needs to acquire m->wait_lock. The worst case which can
+	 * happen is a spurious wakeup.
+	 */
+	tsk = rt_mutex_owner(m);
+	if (tsk)
+		wake_up_process(tsk);
+
+	raw_spin_unlock_irq(&m->wait_lock);
+}
+
+static void __write_unlock_common(struct rt_rw_lock *lock, int bias,
+				  unsigned long flags)
+{
+	struct rt_mutex *m = &lock->rtmutex;
+
+	atomic_add(READER_BIAS - bias, &lock->readers);
+	raw_spin_unlock_irqrestore(&m->wait_lock, flags);
+	rt_spin_lock_slowunlock(m);
+}
+
+void __sched __write_rt_lock(struct rt_rw_lock *lock)
+{
+	struct rt_mutex *m = &lock->rtmutex;
+	struct task_struct *self = current;
+	unsigned long flags;
+
+	/* Take the rtmutex as a first step */
+	__rt_spin_lock(m);
+
+	/* Force readers into slow path */
+	atomic_sub(READER_BIAS, &lock->readers);
+
+	raw_spin_lock_irqsave(&m->wait_lock, flags);
+
+	raw_spin_lock(&self->pi_lock);
+	self->saved_state = self->state;
+	__set_current_state_no_track(TASK_UNINTERRUPTIBLE);
+	raw_spin_unlock(&self->pi_lock);
+
+	for (;;) {
+		/* Have all readers left the critical region? */
+		if (!atomic_read(&lock->readers)) {
+			atomic_set(&lock->readers, WRITER_BIAS);
+			raw_spin_lock(&self->pi_lock);
+			__set_current_state_no_track(self->saved_state);
+			self->saved_state = TASK_RUNNING;
+			raw_spin_unlock(&self->pi_lock);
+			raw_spin_unlock_irqrestore(&m->wait_lock, flags);
+			return;
+		}
+
+		raw_spin_unlock_irqrestore(&m->wait_lock, flags);
+
+		if (atomic_read(&lock->readers) != 0)
+			schedule();
+
+		raw_spin_lock_irqsave(&m->wait_lock, flags);
+
+		raw_spin_lock(&self->pi_lock);
+		__set_current_state_no_track(TASK_UNINTERRUPTIBLE);
+		raw_spin_unlock(&self->pi_lock);
+	}
+}
+
+int __write_rt_trylock(struct rt_rw_lock *lock)
+{
+	struct rt_mutex *m = &lock->rtmutex;
+	unsigned long flags;
+
+	if (!__rt_mutex_trylock(m))
+		return 0;
+
+	atomic_sub(READER_BIAS, &lock->readers);
+
+	raw_spin_lock_irqsave(&m->wait_lock, flags);
+	if (!atomic_read(&lock->readers)) {
+		atomic_set(&lock->readers, WRITER_BIAS);
+		raw_spin_unlock_irqrestore(&m->wait_lock, flags);
+		return 1;
+	}
+	__write_unlock_common(lock, 0, flags);
+	return 0;
+}
+
+void __write_rt_unlock(struct rt_rw_lock *lock)
+{
+	struct rt_mutex *m = &lock->rtmutex;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&m->wait_lock, flags);
+	__write_unlock_common(lock, WRITER_BIAS, flags);
+}
+
+/* Map the reader biased implementation */
+static inline int do_read_rt_trylock(rwlock_t *rwlock)
+{
+	return __read_rt_trylock(rwlock);
+}
+
+static inline int do_write_rt_trylock(rwlock_t *rwlock)
+{
+	return __write_rt_trylock(rwlock);
+}
+
+static inline void do_read_rt_lock(rwlock_t *rwlock)
+{
+	__read_rt_lock(rwlock);
+}
+
+static inline void do_write_rt_lock(rwlock_t *rwlock)
+{
+	__write_rt_lock(rwlock);
+}
+
+static inline void do_read_rt_unlock(rwlock_t *rwlock)
+{
+	__read_rt_unlock(rwlock);
+}
+
+static inline void do_write_rt_unlock(rwlock_t *rwlock)
+{
+	__write_rt_unlock(rwlock);
+}
+
+static inline void do_rwlock_rt_init(rwlock_t *rwlock, const char *name,
+				     struct lock_class_key *key)
+{
+	__rwlock_biased_rt_init(rwlock, name, key);
+}
+
+int __lockfunc rt_read_can_lock(rwlock_t *rwlock)
+{
+	return  atomic_read(&rwlock->readers) < 0;
+}
+
+int __lockfunc rt_write_can_lock(rwlock_t *rwlock)
+{
+	return atomic_read(&rwlock->readers) == READER_BIAS;
+}
+
+/*
+ * The common functions which get wrapped into the rwlock API.
+ */
+int __lockfunc rt_read_trylock(rwlock_t *rwlock)
+{
+	int ret;
+
+	sleeping_lock_inc();
+	migrate_disable();
+	ret = do_read_rt_trylock(rwlock);
+	if (ret) {
+		rwlock_acquire_read(&rwlock->dep_map, 0, 1, _RET_IP_);
+		rcu_read_lock();
+	} else {
+		migrate_enable();
+		sleeping_lock_dec();
+	}
+	return ret;
+}
+EXPORT_SYMBOL(rt_read_trylock);
+
+int __lockfunc rt_write_trylock(rwlock_t *rwlock)
+{
+	int ret;
+
+	sleeping_lock_inc();
+	migrate_disable();
+	ret = do_write_rt_trylock(rwlock);
+	if (ret) {
+		rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_);
+		rcu_read_lock();
+	} else {
+		migrate_enable();
+		sleeping_lock_dec();
+	}
+	return ret;
+}
+EXPORT_SYMBOL(rt_write_trylock);
+
+void __lockfunc rt_read_lock(rwlock_t *rwlock)
+{
+	sleeping_lock_inc();
+	rcu_read_lock();
+	migrate_disable();
+	rwlock_acquire_read(&rwlock->dep_map, 0, 0, _RET_IP_);
+	do_read_rt_lock(rwlock);
+}
+EXPORT_SYMBOL(rt_read_lock);
+
+void __lockfunc rt_write_lock(rwlock_t *rwlock)
+{
+	sleeping_lock_inc();
+	rcu_read_lock();
+	migrate_disable();
+	rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_);
+	do_write_rt_lock(rwlock);
+}
+EXPORT_SYMBOL(rt_write_lock);
+
+void __lockfunc rt_read_unlock(rwlock_t *rwlock)
+{
+	rwlock_release(&rwlock->dep_map, 1, _RET_IP_);
+	do_read_rt_unlock(rwlock);
+	migrate_enable();
+	rcu_read_unlock();
+	sleeping_lock_dec();
+}
+EXPORT_SYMBOL(rt_read_unlock);
+
+void __lockfunc rt_write_unlock(rwlock_t *rwlock)
+{
+	rwlock_release(&rwlock->dep_map, 1, _RET_IP_);
+	do_write_rt_unlock(rwlock);
+	migrate_enable();
+	rcu_read_unlock();
+	sleeping_lock_dec();
+}
+EXPORT_SYMBOL(rt_write_unlock);
+
+void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key)
+{
+	do_rwlock_rt_init(rwlock, name, key);
+}
+EXPORT_SYMBOL(__rt_rwlock_init);
diff --git a/kernel/locking/rwsem-rt.c b/kernel/locking/rwsem-rt.c
new file mode 100644
index 0000000000000..f518495bd6ccd
--- /dev/null
+++ b/kernel/locking/rwsem-rt.c
@@ -0,0 +1,302 @@
+/*
+ */
+#include <linux/blkdev.h>
+#include <linux/rwsem.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/signal.h>
+#include <linux/export.h>
+
+#include "rtmutex_common.h"
+
+/*
+ * RT-specific reader/writer semaphores
+ *
+ * down_write()
+ *  1) Lock sem->rtmutex
+ *  2) Remove the reader BIAS to force readers into the slow path
+ *  3) Wait until all readers have left the critical region
+ *  4) Mark it write locked
+ *
+ * up_write()
+ *  1) Remove the write locked marker
+ *  2) Set the reader BIAS so readers can use the fast path again
+ *  3) Unlock sem->rtmutex to release blocked readers
+ *
+ * down_read()
+ *  1) Try fast path acquisition (reader BIAS is set)
+ *  2) Take sem->rtmutex.wait_lock which protects the writelocked flag
+ *  3) If !writelocked, acquire it for read
+ *  4) If writelocked, block on sem->rtmutex
+ *  5) unlock sem->rtmutex, goto 1)
+ *
+ * up_read()
+ *  1) Try fast path release (reader count != 1)
+ *  2) Wake the writer waiting in down_write()#3
+ *
+ * down_read()#3 has the consequence, that rw semaphores on RT are not writer
+ * fair, but writers, which should be avoided in RT tasks (think mmap_sem),
+ * are subject to the rtmutex priority/DL inheritance mechanism.
+ *
+ * It's possible to make the rw semaphores writer fair by keeping a list of
+ * active readers. A blocked writer would force all newly incoming readers to
+ * block on the rtmutex, but the rtmutex would have to be proxy locked for one
+ * reader after the other. We can't use multi-reader inheritance because there
+ * is no way to support that with SCHED_DEADLINE. Implementing the one by one
+ * reader boosting/handover mechanism is a major surgery for a very dubious
+ * value.
+ *
+ * The risk of writer starvation is there, but the pathological use cases
+ * which trigger it are not necessarily the typical RT workloads.
+ */
+
+void __rwsem_init(struct rw_semaphore *sem, const char *name,
+		  struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/*
+	 * Make sure we are not reinitializing a held semaphore:
+	 */
+	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
+	lockdep_init_map(&sem->dep_map, name, key, 0);
+#endif
+	atomic_set(&sem->readers, READER_BIAS);
+}
+EXPORT_SYMBOL(__rwsem_init);
+
+int __down_read_trylock(struct rw_semaphore *sem)
+{
+	int r, old;
+
+	/*
+	 * Increment reader count, if sem->readers < 0, i.e. READER_BIAS is
+	 * set.
+	 */
+	for (r = atomic_read(&sem->readers); r < 0;) {
+		old = atomic_cmpxchg(&sem->readers, r, r + 1);
+		if (likely(old == r))
+			return 1;
+		r = old;
+	}
+	return 0;
+}
+
+static int __sched __down_read_common(struct rw_semaphore *sem, int state)
+{
+	struct rt_mutex *m = &sem->rtmutex;
+	struct rt_mutex_waiter waiter;
+	int ret;
+
+	if (__down_read_trylock(sem))
+		return 0;
+	/*
+	 * If rt_mutex blocks, the function sched_submit_work will not call
+	 * blk_schedule_flush_plug (because tsk_is_pi_blocked would be true).
+	 * We must call blk_schedule_flush_plug here, if we don't call it,
+	 * a deadlock in I/O may happen.
+	 */
+	if (unlikely(blk_needs_flush_plug(current)))
+		blk_schedule_flush_plug(current);
+
+	might_sleep();
+	raw_spin_lock_irq(&m->wait_lock);
+	/*
+	 * Allow readers as long as the writer has not completely
+	 * acquired the semaphore for write.
+	 */
+	if (atomic_read(&sem->readers) != WRITER_BIAS) {
+		atomic_inc(&sem->readers);
+		raw_spin_unlock_irq(&m->wait_lock);
+		return 0;
+	}
+
+	/*
+	 * Call into the slow lock path with the rtmutex->wait_lock
+	 * held, so this can't result in the following race:
+	 *
+	 * Reader1		Reader2		Writer
+	 *			down_read()
+	 *					down_write()
+	 *					rtmutex_lock(m)
+	 *					swait()
+	 * down_read()
+	 * unlock(m->wait_lock)
+	 *			up_read()
+	 *			swake()
+	 *					lock(m->wait_lock)
+	 *					sem->writelocked=true
+	 *					unlock(m->wait_lock)
+	 *
+	 *					up_write()
+	 *					sem->writelocked=false
+	 *					rtmutex_unlock(m)
+	 *			down_read()
+	 *					down_write()
+	 *					rtmutex_lock(m)
+	 *					swait()
+	 * rtmutex_lock(m)
+	 *
+	 * That would put Reader1 behind the writer waiting on
+	 * Reader2 to call up_read() which might be unbound.
+	 */
+	rt_mutex_init_waiter(&waiter, false);
+	ret = rt_mutex_slowlock_locked(m, state, NULL, RT_MUTEX_MIN_CHAINWALK,
+				       NULL, &waiter);
+	/*
+	 * The slowlock() above is guaranteed to return with the rtmutex (for
+	 * ret = 0) is now held, so there can't be a writer active. Increment
+	 * the reader count and immediately drop the rtmutex again.
+	 * For ret != 0 we don't hold the rtmutex and need unlock the wait_lock.
+	 * We don't own the lock then.
+	 */
+	if (!ret)
+		atomic_inc(&sem->readers);
+	raw_spin_unlock_irq(&m->wait_lock);
+	if (!ret)
+		__rt_mutex_unlock(m);
+
+	debug_rt_mutex_free_waiter(&waiter);
+	return ret;
+}
+
+void __down_read(struct rw_semaphore *sem)
+{
+	int ret;
+
+	ret = __down_read_common(sem, TASK_UNINTERRUPTIBLE);
+	WARN_ON_ONCE(ret);
+}
+
+int __down_read_killable(struct rw_semaphore *sem)
+{
+	int ret;
+
+	ret = __down_read_common(sem, TASK_KILLABLE);
+	if (likely(!ret))
+		return ret;
+	WARN_ONCE(ret != -EINTR, "Unexpected state: %d\n", ret);
+	return -EINTR;
+}
+
+void __up_read(struct rw_semaphore *sem)
+{
+	struct rt_mutex *m = &sem->rtmutex;
+	struct task_struct *tsk;
+
+	/*
+	 * sem->readers can only hit 0 when a writer is waiting for the
+	 * active readers to leave the critical region.
+	 */
+	if (!atomic_dec_and_test(&sem->readers))
+		return;
+
+	might_sleep();
+	raw_spin_lock_irq(&m->wait_lock);
+	/*
+	 * Wake the writer, i.e. the rtmutex owner. It might release the
+	 * rtmutex concurrently in the fast path (due to a signal), but to
+	 * clean up the rwsem it needs to acquire m->wait_lock. The worst
+	 * case which can happen is a spurious wakeup.
+	 */
+	tsk = rt_mutex_owner(m);
+	if (tsk)
+		wake_up_process(tsk);
+
+	raw_spin_unlock_irq(&m->wait_lock);
+}
+
+static void __up_write_unlock(struct rw_semaphore *sem, int bias,
+			      unsigned long flags)
+{
+	struct rt_mutex *m = &sem->rtmutex;
+
+	atomic_add(READER_BIAS - bias, &sem->readers);
+	raw_spin_unlock_irqrestore(&m->wait_lock, flags);
+	__rt_mutex_unlock(m);
+}
+
+static int __sched __down_write_common(struct rw_semaphore *sem, int state)
+{
+	struct rt_mutex *m = &sem->rtmutex;
+	unsigned long flags;
+
+	/* Take the rtmutex as a first step */
+	if (__rt_mutex_lock_state(m, state))
+		return -EINTR;
+
+	/* Force readers into slow path */
+	atomic_sub(READER_BIAS, &sem->readers);
+	might_sleep();
+
+	set_current_state(state);
+	for (;;) {
+		raw_spin_lock_irqsave(&m->wait_lock, flags);
+		/* Have all readers left the critical region? */
+		if (!atomic_read(&sem->readers)) {
+			atomic_set(&sem->readers, WRITER_BIAS);
+			__set_current_state(TASK_RUNNING);
+			raw_spin_unlock_irqrestore(&m->wait_lock, flags);
+			return 0;
+		}
+
+		if (signal_pending_state(state, current)) {
+			__set_current_state(TASK_RUNNING);
+			__up_write_unlock(sem, 0, flags);
+			return -EINTR;
+		}
+		raw_spin_unlock_irqrestore(&m->wait_lock, flags);
+
+		if (atomic_read(&sem->readers) != 0) {
+			schedule();
+			set_current_state(state);
+		}
+	}
+}
+
+void __sched __down_write(struct rw_semaphore *sem)
+{
+	__down_write_common(sem, TASK_UNINTERRUPTIBLE);
+}
+
+int __sched __down_write_killable(struct rw_semaphore *sem)
+{
+	return __down_write_common(sem, TASK_KILLABLE);
+}
+
+int __down_write_trylock(struct rw_semaphore *sem)
+{
+	struct rt_mutex *m = &sem->rtmutex;
+	unsigned long flags;
+
+	if (!__rt_mutex_trylock(m))
+		return 0;
+
+	atomic_sub(READER_BIAS, &sem->readers);
+
+	raw_spin_lock_irqsave(&m->wait_lock, flags);
+	if (!atomic_read(&sem->readers)) {
+		atomic_set(&sem->readers, WRITER_BIAS);
+		raw_spin_unlock_irqrestore(&m->wait_lock, flags);
+		return 1;
+	}
+	__up_write_unlock(sem, 0, flags);
+	return 0;
+}
+
+void __up_write(struct rw_semaphore *sem)
+{
+	struct rt_mutex *m = &sem->rtmutex;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&m->wait_lock, flags);
+	__up_write_unlock(sem, WRITER_BIAS, flags);
+}
+
+void __downgrade_write(struct rw_semaphore *sem)
+{
+	struct rt_mutex *m = &sem->rtmutex;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&m->wait_lock, flags);
+	/* Release it and account current as reader */
+	__up_write_unlock(sem, WRITER_BIAS - 1, flags);
+}
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index eef04551eae71..dba6ee0b85fe8 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -29,6 +29,8 @@
 #include <linux/atomic.h>
 
 #include "rwsem.h"
+
+#ifndef CONFIG_PREEMPT_RT
 #include "lock_events.h"
 
 /*
@@ -1335,6 +1337,7 @@ static struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
 	return sem;
 }
 
+
 /*
  * lock for reading
  */
@@ -1485,6 +1488,7 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 	if (tmp & RWSEM_FLAG_WAITERS)
 		rwsem_downgrade_wake(sem);
 }
+#endif
 
 /*
  * lock for reading
@@ -1616,6 +1620,7 @@ void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest)
 }
 EXPORT_SYMBOL(_down_write_nest_lock);
 
+#ifndef CONFIG_PREEMPT_RT
 void down_read_non_owner(struct rw_semaphore *sem)
 {
 	might_sleep();
@@ -1623,6 +1628,7 @@ void down_read_non_owner(struct rw_semaphore *sem)
 	__rwsem_set_reader_owned(sem, NULL);
 }
 EXPORT_SYMBOL(down_read_non_owner);
+#endif
 
 void down_write_nested(struct rw_semaphore *sem, int subclass)
 {
@@ -1647,11 +1653,13 @@ int __sched down_write_killable_nested(struct rw_semaphore *sem, int subclass)
 }
 EXPORT_SYMBOL(down_write_killable_nested);
 
+#ifndef CONFIG_PREEMPT_RT
 void up_read_non_owner(struct rw_semaphore *sem)
 {
 	DEBUG_RWSEMS_WARN_ON(!is_rwsem_reader_owned(sem), sem);
 	__up_read(sem);
 }
 EXPORT_SYMBOL(up_read_non_owner);
+#endif
 
 #endif
diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h
index 2534ce49f6480..cd7820880a4f4 100644
--- a/kernel/locking/rwsem.h
+++ b/kernel/locking/rwsem.h
@@ -4,7 +4,9 @@
 #define __INTERNAL_RWSEM_H
 #include <linux/rwsem.h>
 
+#ifndef CONFIG_PREEMPT_RT
 extern void __down_read(struct rw_semaphore *sem);
 extern void __up_read(struct rw_semaphore *sem);
+#endif
 
 #endif /* __INTERNAL_RWSEM_H */
diff --git a/kernel/locking/spinlock.c b/kernel/locking/spinlock.c
index 0ff08380f5318..45445a2f1799a 100644
--- a/kernel/locking/spinlock.c
+++ b/kernel/locking/spinlock.c
@@ -124,8 +124,11 @@ void __lockfunc __raw_##op##_lock_bh(locktype##_t *lock)		\
  *         __[spin|read|write]_lock_bh()
  */
 BUILD_LOCK_OPS(spin, raw_spinlock);
+
+#ifndef CONFIG_PREEMPT_RT
 BUILD_LOCK_OPS(read, rwlock);
 BUILD_LOCK_OPS(write, rwlock);
+#endif
 
 #endif
 
@@ -209,6 +212,8 @@ void __lockfunc _raw_spin_unlock_bh(raw_spinlock_t *lock)
 EXPORT_SYMBOL(_raw_spin_unlock_bh);
 #endif
 
+#ifndef CONFIG_PREEMPT_RT
+
 #ifndef CONFIG_INLINE_READ_TRYLOCK
 int __lockfunc _raw_read_trylock(rwlock_t *lock)
 {
@@ -353,6 +358,8 @@ void __lockfunc _raw_write_unlock_bh(rwlock_t *lock)
 EXPORT_SYMBOL(_raw_write_unlock_bh);
 #endif
 
+#endif /* !PREEMPT_RT */
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 
 void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass)
diff --git a/kernel/locking/spinlock_debug.c b/kernel/locking/spinlock_debug.c
index 399669f7eba8e..a1c68fd94d130 100644
--- a/kernel/locking/spinlock_debug.c
+++ b/kernel/locking/spinlock_debug.c
@@ -31,6 +31,7 @@ void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name,
 
 EXPORT_SYMBOL(__raw_spin_lock_init);
 
+#ifndef CONFIG_PREEMPT_RT
 void __rwlock_init(rwlock_t *lock, const char *name,
 		   struct lock_class_key *key)
 {
@@ -48,6 +49,7 @@ void __rwlock_init(rwlock_t *lock, const char *name,
 }
 
 EXPORT_SYMBOL(__rwlock_init);
+#endif
 
 static void spin_dump(raw_spinlock_t *lock, const char *msg)
 {
@@ -139,6 +141,7 @@ void do_raw_spin_unlock(raw_spinlock_t *lock)
 	arch_spin_unlock(&lock->raw_lock);
 }
 
+#ifndef CONFIG_PREEMPT_RT
 static void rwlock_bug(rwlock_t *lock, const char *msg)
 {
 	if (!debug_locks_off())
@@ -228,3 +231,5 @@ void do_raw_write_unlock(rwlock_t *lock)
 	debug_write_unlock(lock);
 	arch_write_unlock(&lock->raw_lock);
 }
+
+#endif
diff --git a/kernel/panic.c b/kernel/panic.c
index f470a038b05bd..cf00fca838174 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -237,7 +237,6 @@ void panic(const char *fmt, ...)
 	 * Bypass the panic_cpu check and call __crash_kexec directly.
 	 */
 	if (!_crash_kexec_post_notifiers) {
-		printk_safe_flush_on_panic();
 		__crash_kexec(NULL);
 
 		/*
@@ -261,8 +260,6 @@ void panic(const char *fmt, ...)
 	 */
 	atomic_notifier_call_chain(&panic_notifier_list, 0, buf);
 
-	/* Call flush even twice. It tries harder with a single online CPU */
-	printk_safe_flush_on_panic();
 	kmsg_dump(KMSG_DUMP_PANIC);
 
 	/*
@@ -524,9 +521,11 @@ static u64 oops_id;
 
 static int init_oops_id(void)
 {
+#ifndef CONFIG_PREEMPT_RT
 	if (!oops_id)
 		get_random_bytes(&oops_id, sizeof(oops_id));
 	else
+#endif
 		oops_id++;
 
 	return 0;
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 3c0a5a8170b02..c8713bbc44810 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -689,6 +689,10 @@ static int load_image_and_restore(void)
 	return error;
 }
 
+#ifndef CONFIG_SUSPEND
+bool pm_in_action;
+#endif
+
 /**
  * hibernate - Carry out system hibernation, including saving the image.
  */
@@ -702,6 +706,8 @@ int hibernate(void)
 		return -EPERM;
 	}
 
+	pm_in_action = true;
+
 	lock_system_sleep();
 	/* The snapshot device should not be opened while we're running */
 	if (!atomic_add_unless(&snapshot_device_available, -1, 0)) {
@@ -778,6 +784,7 @@ int hibernate(void)
 	atomic_inc(&snapshot_device_available);
  Unlock:
 	unlock_system_sleep();
+	pm_in_action = false;
 	pr_info("hibernation exit\n");
 
 	return error;
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index f3b7239f1892f..3205c45155eee 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -594,6 +594,8 @@ static int enter_state(suspend_state_t state)
 	return error;
 }
 
+bool pm_in_action;
+
 /**
  * pm_suspend - Externally visible function for suspending the system.
  * @state: System sleep state to enter.
@@ -608,6 +610,7 @@ int pm_suspend(suspend_state_t state)
 	if (state <= PM_SUSPEND_ON || state >= PM_SUSPEND_MAX)
 		return -EINVAL;
 
+	pm_in_action = true;
 	pr_info("suspend entry (%s)\n", mem_sleep_labels[state]);
 	error = enter_state(state);
 	if (error) {
@@ -617,6 +620,7 @@ int pm_suspend(suspend_state_t state)
 		suspend_stats.success++;
 	}
 	pr_info("suspend exit\n");
+	pm_in_action = false;
 	return error;
 }
 EXPORT_SYMBOL(pm_suspend);
diff --git a/kernel/printk/Makefile b/kernel/printk/Makefile
index 4d052fc6bcde7..7b219d824c0fb 100644
--- a/kernel/printk/Makefile
+++ b/kernel/printk/Makefile
@@ -1,4 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-y	= printk.o
-obj-$(CONFIG_PRINTK)	+= printk_safe.o
 obj-$(CONFIG_A11Y_BRAILLE_CONSOLE)	+= braille.o
diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h
deleted file mode 100644
index c8e6ab689d42f..0000000000000
--- a/kernel/printk/internal.h
+++ /dev/null
@@ -1,67 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * internal.h - printk internal definitions
- */
-#include <linux/percpu.h>
-
-#ifdef CONFIG_PRINTK
-
-#define PRINTK_SAFE_CONTEXT_MASK	 0x3fffffff
-#define PRINTK_NMI_DIRECT_CONTEXT_MASK	 0x40000000
-#define PRINTK_NMI_CONTEXT_MASK		 0x80000000
-
-extern raw_spinlock_t logbuf_lock;
-
-__printf(5, 0)
-int vprintk_store(int facility, int level,
-		  const char *dict, size_t dictlen,
-		  const char *fmt, va_list args);
-
-__printf(1, 0) int vprintk_default(const char *fmt, va_list args);
-__printf(1, 0) int vprintk_deferred(const char *fmt, va_list args);
-__printf(1, 0) int vprintk_func(const char *fmt, va_list args);
-void __printk_safe_enter(void);
-void __printk_safe_exit(void);
-
-#define printk_safe_enter_irqsave(flags)	\
-	do {					\
-		local_irq_save(flags);		\
-		__printk_safe_enter();		\
-	} while (0)
-
-#define printk_safe_exit_irqrestore(flags)	\
-	do {					\
-		__printk_safe_exit();		\
-		local_irq_restore(flags);	\
-	} while (0)
-
-#define printk_safe_enter_irq()		\
-	do {					\
-		local_irq_disable();		\
-		__printk_safe_enter();		\
-	} while (0)
-
-#define printk_safe_exit_irq()			\
-	do {					\
-		__printk_safe_exit();		\
-		local_irq_enable();		\
-	} while (0)
-
-void defer_console_output(void);
-
-#else
-
-__printf(1, 0) int vprintk_func(const char *fmt, va_list args) { return 0; }
-
-/*
- * In !PRINTK builds we still export logbuf_lock spin_lock, console_sem
- * semaphore and some of console functions (console_unlock()/etc.), so
- * printk-safe must preserve the existing local IRQ guarantees.
- */
-#define printk_safe_enter_irqsave(flags) local_irq_save(flags)
-#define printk_safe_exit_irqrestore(flags) local_irq_restore(flags)
-
-#define printk_safe_enter_irq() local_irq_disable()
-#define printk_safe_exit_irq() local_irq_enable()
-
-#endif /* CONFIG_PRINTK */
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index ca65327a6de8c..0605a74ad76b9 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -45,6 +45,9 @@
 #include <linux/irq_work.h>
 #include <linux/ctype.h>
 #include <linux/uio.h>
+#include <linux/kthread.h>
+#include <linux/clocksource.h>
+#include <linux/printk_ringbuffer.h>
 #include <linux/sched/clock.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task_stack.h>
@@ -58,13 +61,13 @@
 
 #include "console_cmdline.h"
 #include "braille.h"
-#include "internal.h"
 
-int console_printk[4] = {
+int console_printk[5] = {
 	CONSOLE_LOGLEVEL_DEFAULT,	/* console_loglevel */
 	MESSAGE_LOGLEVEL_DEFAULT,	/* default_message_loglevel */
 	CONSOLE_LOGLEVEL_MIN,		/* minimum_console_loglevel */
 	CONSOLE_LOGLEVEL_DEFAULT,	/* default_console_loglevel */
+	CONSOLE_LOGLEVEL_EMERGENCY,	/* emergency_console_loglevel */
 };
 EXPORT_SYMBOL_GPL(console_printk);
 
@@ -225,19 +228,7 @@ static int nr_ext_console_drivers;
 
 static int __down_trylock_console_sem(unsigned long ip)
 {
-	int lock_failed;
-	unsigned long flags;
-
-	/*
-	 * Here and in __up_console_sem() we need to be in safe mode,
-	 * because spindump/WARN/etc from under console ->lock will
-	 * deadlock in printk()->down_trylock_console_sem() otherwise.
-	 */
-	printk_safe_enter_irqsave(flags);
-	lock_failed = down_trylock(&console_sem);
-	printk_safe_exit_irqrestore(flags);
-
-	if (lock_failed)
+	if (down_trylock(&console_sem))
 		return 1;
 	mutex_acquire(&console_lock_dep_map, 0, 1, ip);
 	return 0;
@@ -246,13 +237,9 @@ static int __down_trylock_console_sem(unsigned long ip)
 
 static void __up_console_sem(unsigned long ip)
 {
-	unsigned long flags;
-
 	mutex_release(&console_lock_dep_map, 1, ip);
 
-	printk_safe_enter_irqsave(flags);
 	up(&console_sem);
-	printk_safe_exit_irqrestore(flags);
 }
 #define up_console_sem() __up_console_sem(_RET_IP_)
 
@@ -266,11 +253,6 @@ static void __up_console_sem(unsigned long ip)
  */
 static int console_locked, console_suspended;
 
-/*
- * If exclusive_console is non-NULL then only this console is to be printed to.
- */
-static struct console *exclusive_console;
-
 /*
  *	Array of consoles built from command line options (console=)
  */
@@ -367,6 +349,7 @@ enum log_flags {
 
 struct printk_log {
 	u64 ts_nsec;		/* timestamp in nanoseconds */
+	u16 cpu;		/* cpu that generated record */
 	u16 len;		/* length of entire record */
 	u16 text_len;		/* length of text buffer */
 	u16 dict_len;		/* length of dictionary buffer */
@@ -382,65 +365,22 @@ __packed __aligned(4)
 #endif
 ;
 
-/*
- * The logbuf_lock protects kmsg buffer, indices, counters.  This can be taken
- * within the scheduler's rq lock. It must be released before calling
- * console_unlock() or anything else that might wake up a process.
- */
-DEFINE_RAW_SPINLOCK(logbuf_lock);
-
-/*
- * Helper macros to lock/unlock logbuf_lock and switch between
- * printk-safe/unsafe modes.
- */
-#define logbuf_lock_irq()				\
-	do {						\
-		printk_safe_enter_irq();		\
-		raw_spin_lock(&logbuf_lock);		\
-	} while (0)
-
-#define logbuf_unlock_irq()				\
-	do {						\
-		raw_spin_unlock(&logbuf_lock);		\
-		printk_safe_exit_irq();			\
-	} while (0)
-
-#define logbuf_lock_irqsave(flags)			\
-	do {						\
-		printk_safe_enter_irqsave(flags);	\
-		raw_spin_lock(&logbuf_lock);		\
-	} while (0)
-
-#define logbuf_unlock_irqrestore(flags)		\
-	do {						\
-		raw_spin_unlock(&logbuf_lock);		\
-		printk_safe_exit_irqrestore(flags);	\
-	} while (0)
+DECLARE_STATIC_PRINTKRB_CPULOCK(printk_cpulock);
 
 #ifdef CONFIG_PRINTK
-DECLARE_WAIT_QUEUE_HEAD(log_wait);
-/* the next printk record to read by syslog(READ) or /proc/kmsg */
+/* record buffer */
+DECLARE_STATIC_PRINTKRB(printk_rb, CONFIG_LOG_BUF_SHIFT, &printk_cpulock);
+
+static DEFINE_MUTEX(syslog_lock);
+DECLARE_STATIC_PRINTKRB_ITER(syslog_iter, &printk_rb);
+
+/* the last printk record to read by syslog(READ) or /proc/kmsg */
 static u64 syslog_seq;
-static u32 syslog_idx;
 static size_t syslog_partial;
 static bool syslog_time;
 
-/* index and sequence number of the first record stored in the buffer */
-static u64 log_first_seq;
-static u32 log_first_idx;
-
-/* index and sequence number of the next record to store in the buffer */
-static u64 log_next_seq;
-static u32 log_next_idx;
-
-/* the next printk record to write to the console */
-static u64 console_seq;
-static u32 console_idx;
-static u64 exclusive_console_stop_seq;
-
 /* the next printk record to read after the last 'clear' command */
 static u64 clear_seq;
-static u32 clear_idx;
 
 #ifdef CONFIG_PRINTK_CALLER
 #define PREFIX_MAX		48
@@ -452,24 +392,16 @@ static u32 clear_idx;
 #define LOG_LEVEL(v)		((v) & 0x07)
 #define LOG_FACILITY(v)		((v) >> 3 & 0xff)
 
-/* record buffer */
-#define LOG_ALIGN __alignof__(struct printk_log)
-#define __LOG_BUF_LEN (1 << CONFIG_LOG_BUF_SHIFT)
-#define LOG_BUF_LEN_MAX (u32)(1 << 31)
-static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN);
-static char *log_buf = __log_buf;
-static u32 log_buf_len = __LOG_BUF_LEN;
-
 /* Return log buffer address */
 char *log_buf_addr_get(void)
 {
-	return log_buf;
+	return printk_rb.buffer;
 }
 
 /* Return log buffer size */
 u32 log_buf_len_get(void)
 {
-	return log_buf_len;
+	return (1 << printk_rb.size_bits);
 }
 
 /* human readable text of the record */
@@ -484,180 +416,50 @@ static char *log_dict(const struct printk_log *msg)
 	return (char *)msg + sizeof(struct printk_log) + msg->text_len;
 }
 
-/* get record by index; idx must point to valid msg */
-static struct printk_log *log_from_idx(u32 idx)
-{
-	struct printk_log *msg = (struct printk_log *)(log_buf + idx);
-
-	/*
-	 * A length == 0 record is the end of buffer marker. Wrap around and
-	 * read the message at the start of the buffer.
-	 */
-	if (!msg->len)
-		return (struct printk_log *)log_buf;
-	return msg;
-}
-
-/* get next record; idx must point to valid msg */
-static u32 log_next(u32 idx)
-{
-	struct printk_log *msg = (struct printk_log *)(log_buf + idx);
-
-	/* length == 0 indicates the end of the buffer; wrap */
-	/*
-	 * A length == 0 record is the end of buffer marker. Wrap around and
-	 * read the message at the start of the buffer as *this* one, and
-	 * return the one after that.
-	 */
-	if (!msg->len) {
-		msg = (struct printk_log *)log_buf;
-		return msg->len;
-	}
-	return idx + msg->len;
-}
-
-/*
- * Check whether there is enough free space for the given message.
- *
- * The same values of first_idx and next_idx mean that the buffer
- * is either empty or full.
- *
- * If the buffer is empty, we must respect the position of the indexes.
- * They cannot be reset to the beginning of the buffer.
- */
-static int logbuf_has_space(u32 msg_size, bool empty)
-{
-	u32 free;
-
-	if (log_next_idx > log_first_idx || empty)
-		free = max(log_buf_len - log_next_idx, log_first_idx);
-	else
-		free = log_first_idx - log_next_idx;
-
-	/*
-	 * We need space also for an empty header that signalizes wrapping
-	 * of the buffer.
-	 */
-	return free >= msg_size + sizeof(struct printk_log);
-}
-
-static int log_make_free_space(u32 msg_size)
-{
-	while (log_first_seq < log_next_seq &&
-	       !logbuf_has_space(msg_size, false)) {
-		/* drop old messages until we have enough contiguous space */
-		log_first_idx = log_next(log_first_idx);
-		log_first_seq++;
-	}
-
-	if (clear_seq < log_first_seq) {
-		clear_seq = log_first_seq;
-		clear_idx = log_first_idx;
-	}
-
-	/* sequence numbers are equal, so the log buffer is empty */
-	if (logbuf_has_space(msg_size, log_first_seq == log_next_seq))
-		return 0;
-
-	return -ENOMEM;
-}
-
-/* compute the message size including the padding bytes */
-static u32 msg_used_size(u16 text_len, u16 dict_len, u32 *pad_len)
-{
-	u32 size;
-
-	size = sizeof(struct printk_log) + text_len + dict_len;
-	*pad_len = (-size) & (LOG_ALIGN - 1);
-	size += *pad_len;
-
-	return size;
-}
-
-/*
- * Define how much of the log buffer we could take at maximum. The value
- * must be greater than two. Note that only half of the buffer is available
- * when the index points to the middle.
- */
-#define MAX_LOG_TAKE_PART 4
-static const char trunc_msg[] = "<truncated>";
-
-static u32 truncate_msg(u16 *text_len, u16 *trunc_msg_len,
-			u16 *dict_len, u32 *pad_len)
-{
-	/*
-	 * The message should not take the whole buffer. Otherwise, it might
-	 * get removed too soon.
-	 */
-	u32 max_text_len = log_buf_len / MAX_LOG_TAKE_PART;
-	if (*text_len > max_text_len)
-		*text_len = max_text_len;
-	/* enable the warning message */
-	*trunc_msg_len = strlen(trunc_msg);
-	/* disable the "dict" completely */
-	*dict_len = 0;
-	/* compute the size again, count also the warning message */
-	return msg_used_size(*text_len + *trunc_msg_len, 0, pad_len);
-}
+static void printk_emergency(char *buffer, int level, u64 ts_nsec, u16 cpu,
+			     char *text, u16 text_len);
 
 /* insert record into the buffer, discard old ones, update heads */
 static int log_store(u32 caller_id, int facility, int level,
-		     enum log_flags flags, u64 ts_nsec,
+		     enum log_flags flags, u64 ts_nsec, u16 cpu,
 		     const char *dict, u16 dict_len,
 		     const char *text, u16 text_len)
 {
 	struct printk_log *msg;
-	u32 size, pad_len;
-	u16 trunc_msg_len = 0;
+	struct prb_handle h;
+	char *rbuf;
+	u32 size;
 
-	/* number of '\0' padding bytes to next message */
-	size = msg_used_size(text_len, dict_len, &pad_len);
+	size = sizeof(*msg) + text_len + dict_len;
 
-	if (log_make_free_space(size)) {
-		/* truncate the message if it is too long for empty buffer */
-		size = truncate_msg(&text_len, &trunc_msg_len,
-				    &dict_len, &pad_len);
-		/* survive when the log buffer is too small for trunc_msg */
-		if (log_make_free_space(size))
-			return 0;
-	}
-
-	if (log_next_idx + size + sizeof(struct printk_log) > log_buf_len) {
+	rbuf = prb_reserve(&h, &printk_rb, size);
+	if (!rbuf) {
 		/*
-		 * This message + an additional empty header does not fit
-		 * at the end of the buffer. Add an empty header with len == 0
-		 * to signify a wrap around.
+		 * An emergency message would have been printed, but
+		 * it cannot be stored in the log.
 		 */
-		memset(log_buf + log_next_idx, 0, sizeof(struct printk_log));
-		log_next_idx = 0;
+		prb_inc_lost(&printk_rb);
+		return 0;
 	}
 
 	/* fill message */
-	msg = (struct printk_log *)(log_buf + log_next_idx);
+	msg = (struct printk_log *)rbuf;
 	memcpy(log_text(msg), text, text_len);
 	msg->text_len = text_len;
-	if (trunc_msg_len) {
-		memcpy(log_text(msg) + text_len, trunc_msg, trunc_msg_len);
-		msg->text_len += trunc_msg_len;
-	}
 	memcpy(log_dict(msg), dict, dict_len);
 	msg->dict_len = dict_len;
 	msg->facility = facility;
 	msg->level = level & 7;
 	msg->flags = flags & 0x1f;
-	if (ts_nsec > 0)
-		msg->ts_nsec = ts_nsec;
-	else
-		msg->ts_nsec = local_clock();
+	msg->ts_nsec = ts_nsec;
 #ifdef CONFIG_PRINTK_CALLER
 	msg->caller_id = caller_id;
 #endif
-	memset(log_dict(msg) + dict_len, 0, pad_len);
+	msg->cpu = cpu;
 	msg->len = size;
 
 	/* insert message */
-	log_next_idx += msg->len;
-	log_next_seq++;
+	prb_commit(&h);
 
 	return msg->text_len;
 }
@@ -727,9 +529,9 @@ static ssize_t msg_print_ext_header(char *buf, size_t size,
 
 	do_div(ts_usec, 1000);
 
-	return scnprintf(buf, size, "%u,%llu,%llu,%c%s;",
+	return scnprintf(buf, size, "%u,%llu,%llu,%c%s,%hu;",
 			 (msg->facility << 3) | msg->level, seq, ts_usec,
-			 msg->flags & LOG_CONT ? 'c' : '-', caller);
+			 msg->flags & LOG_CONT ? 'c' : '-', caller, msg->cpu);
 }
 
 static ssize_t msg_print_ext_body(char *buf, size_t size,
@@ -780,13 +582,18 @@ static ssize_t msg_print_ext_body(char *buf, size_t size,
 	return p - buf;
 }
 
+#define PRINTK_SPRINT_MAX (LOG_LINE_MAX + PREFIX_MAX)
+#define PRINTK_RECORD_MAX (sizeof(struct printk_log) + \
+				CONSOLE_EXT_LOG_MAX + PRINTK_SPRINT_MAX)
+
 /* /dev/kmsg - userspace message inject/listen interface */
 struct devkmsg_user {
 	u64 seq;
-	u32 idx;
+	struct prb_iterator iter;
 	struct ratelimit_state rs;
 	struct mutex lock;
 	char buf[CONSOLE_EXT_LOG_MAX];
+	char msgbuf[PRINTK_RECORD_MAX];
 };
 
 static __printf(3, 4) __cold
@@ -869,9 +676,11 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf,
 			    size_t count, loff_t *ppos)
 {
 	struct devkmsg_user *user = file->private_data;
+	struct prb_iterator backup_iter;
 	struct printk_log *msg;
-	size_t len;
 	ssize_t ret;
+	size_t len;
+	u64 seq;
 
 	if (!user)
 		return -EBADF;
@@ -880,52 +689,63 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf,
 	if (ret)
 		return ret;
 
-	logbuf_lock_irq();
-	while (user->seq == log_next_seq) {
-		if (file->f_flags & O_NONBLOCK) {
-			ret = -EAGAIN;
-			logbuf_unlock_irq();
-			goto out;
-		}
+	/* make a backup copy in case there is a problem */
+	prb_iter_copy(&backup_iter, &user->iter);
 
-		logbuf_unlock_irq();
-		ret = wait_event_interruptible(log_wait,
-					       user->seq != log_next_seq);
-		if (ret)
-			goto out;
-		logbuf_lock_irq();
+	if (file->f_flags & O_NONBLOCK) {
+		ret = prb_iter_next(&user->iter, &user->msgbuf[0],
+				      sizeof(user->msgbuf), &seq);
+	} else {
+		ret = prb_iter_wait_next(&user->iter, &user->msgbuf[0],
+					   sizeof(user->msgbuf), &seq);
 	}
-
-	if (user->seq < log_first_seq) {
-		/* our last seen message is gone, return error and reset */
-		user->idx = log_first_idx;
-		user->seq = log_first_seq;
+	if (ret == 0) {
+		/* end of list */
+		ret = -EAGAIN;
+		goto out;
+	} else if (ret == -EINVAL) {
+		/* iterator invalid, return error and reset */
 		ret = -EPIPE;
-		logbuf_unlock_irq();
+		prb_iter_init(&user->iter, &printk_rb, &user->seq);
+		goto out;
+	} else if (ret < 0) {
+		/* interrupted by signal */
 		goto out;
 	}
 
-	msg = log_from_idx(user->idx);
+	user->seq++;
+	if (user->seq < seq) {
+		ret = -EPIPE;
+		goto restore_out;
+	}
+
+	msg = (struct printk_log *)&user->msgbuf[0];
 	len = msg_print_ext_header(user->buf, sizeof(user->buf),
 				   msg, user->seq);
 	len += msg_print_ext_body(user->buf + len, sizeof(user->buf) - len,
 				  log_dict(msg), msg->dict_len,
 				  log_text(msg), msg->text_len);
 
-	user->idx = log_next(user->idx);
-	user->seq++;
-	logbuf_unlock_irq();
-
 	if (len > count) {
 		ret = -EINVAL;
-		goto out;
+		goto restore_out;
 	}
 
 	if (copy_to_user(buf, user->buf, len)) {
 		ret = -EFAULT;
-		goto out;
+		goto restore_out;
 	}
+
 	ret = len;
+	goto out;
+restore_out:
+	/*
+	 * There was an error, but this message should not be
+	 * lost because of it. Restore the backup and setup
+	 * seq so that it will work with the next read.
+	 */
+	prb_iter_copy(&user->iter, &backup_iter);
+	user->seq = seq - 1;
 out:
 	mutex_unlock(&user->lock);
 	return ret;
@@ -934,19 +754,22 @@ static ssize_t devkmsg_read(struct file *file, char __user *buf,
 static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct devkmsg_user *user = file->private_data;
-	loff_t ret = 0;
+	loff_t ret;
+	u64 seq;
 
 	if (!user)
 		return -EBADF;
 	if (offset)
 		return -ESPIPE;
 
-	logbuf_lock_irq();
+	ret = mutex_lock_interruptible(&user->lock);
+	if (ret)
+		return ret;
+
 	switch (whence) {
 	case SEEK_SET:
 		/* the first record */
-		user->idx = log_first_idx;
-		user->seq = log_first_seq;
+		prb_iter_init(&user->iter, &printk_rb, &user->seq);
 		break;
 	case SEEK_DATA:
 		/*
@@ -954,40 +777,87 @@ static loff_t devkmsg_llseek(struct file *file, loff_t offset, int whence)
 		 * like issued by 'dmesg -c'. Reading /dev/kmsg itself
 		 * changes no global state, and does not clear anything.
 		 */
-		user->idx = clear_idx;
-		user->seq = clear_seq;
+		for (;;) {
+			prb_iter_init(&user->iter, &printk_rb, &seq);
+			ret = prb_iter_seek(&user->iter, clear_seq);
+			if (ret > 0) {
+				/* seeked to clear seq */
+				user->seq = clear_seq;
+				break;
+			} else if (ret == 0) {
+				/*
+				 * The end of the list was hit without
+				 * ever seeing the clear seq. Just
+				 * seek to the beginning of the list.
+				 */
+				prb_iter_init(&user->iter, &printk_rb,
+						&user->seq);
+