project-edgeos/sys-kernel/lakitu-kernel-rt-5_10/files/0000-patch-5.10.90-rt60.patch

diff --git a/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst
index 72f0f6fbd53c0..6f89cf1e567d0 100644
--- a/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst
+++ b/Documentation/RCU/Design/Expedited-Grace-Periods/Expedited-Grace-Periods.rst
@@ -38,7 +38,7 @@ sections.
 RCU-preempt Expedited Grace Periods
 ===================================
 
-``CONFIG_PREEMPT=y`` kernels implement RCU-preempt.
+``CONFIG_PREEMPTION=y`` 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:
 
@@ -112,7 +112,7 @@ things.
 RCU-sched Expedited Grace Periods
 ---------------------------------
 
-``CONFIG_PREEMPT=n`` kernels implement RCU-sched. The overall flow of
+``CONFIG_PREEMPTION=n`` 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:
 
diff --git a/Documentation/RCU/Design/Requirements/Requirements.rst b/Documentation/RCU/Design/Requirements/Requirements.rst
index 1ae79a10a8de6..17d38480ef5c5 100644
--- a/Documentation/RCU/Design/Requirements/Requirements.rst
+++ b/Documentation/RCU/Design/Requirements/Requirements.rst
@@ -78,7 +78,7 @@ RCU treats a nested set as one big RCU read-side critical section.
 Production-quality implementations of ``rcu_read_lock()`` and
 ``rcu_read_unlock()`` are extremely lightweight, and in fact have
 exactly zero overhead in Linux kernels built for production use with
-``CONFIG_PREEMPT=n``.
+``CONFIG_PREEMPTION=n``.
 
 This guarantee allows ordering to be enforced with extremely low
 overhead to readers, for example:
@@ -1182,7 +1182,7 @@ and has become decreasingly so as memory sizes have expanded and memory
 costs have plummeted. However, as I learned from Matt Mackall's
 `bloatwatch <http://elinux.org/Linux_Tiny-FAQ>`__ efforts, memory
 footprint is critically important on single-CPU systems with
-non-preemptible (``CONFIG_PREEMPT=n``) kernels, and thus `tiny
+non-preemptible (``CONFIG_PREEMPTION=n``) kernels, and thus `tiny
 RCU <https://lkml.kernel.org/g/20090113221724.GA15307@linux.vnet.ibm.com>`__
 was born. Josh Triplett has since taken over the small-memory banner
 with his `Linux kernel tinification <https://tiny.wiki.kernel.org/>`__
@@ -1498,7 +1498,7 @@ limitations.
 
 Implementations of RCU for which ``rcu_read_lock()`` and
 ``rcu_read_unlock()`` generate no code, such as Linux-kernel RCU when
-``CONFIG_PREEMPT=n``, can be nested arbitrarily deeply. After all, there
+``CONFIG_PREEMPTION=n``, can be nested arbitrarily deeply. After all, there
 is no overhead. Except that if all these instances of
 ``rcu_read_lock()`` and ``rcu_read_unlock()`` are visible to the
 compiler, compilation will eventually fail due to exhausting memory,
@@ -1771,7 +1771,7 @@ implementation can be a no-op.
 
 However, once the scheduler has spawned its first kthread, this early
 boot trick fails for ``synchronize_rcu()`` (as well as for
-``synchronize_rcu_expedited()``) in ``CONFIG_PREEMPT=y`` kernels. The
+``synchronize_rcu_expedited()``) in ``CONFIG_PREEMPTION=y`` kernels. The
 reason is that an RCU read-side critical section might be preempted,
 which means that a subsequent ``synchronize_rcu()`` really does have to
 wait for something, as opposed to simply returning immediately.
@@ -2010,7 +2010,7 @@ the following:
        5 rcu_read_unlock();
        6 do_something_with(v, user_v);
 
-If the compiler did make this transformation in a ``CONFIG_PREEMPT=n`` kernel
+If the compiler did make this transformation in a ``CONFIG_PREEMPTION=n`` kernel
 build, and if ``get_user()`` 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 4 being a use-after-free access,
@@ -2289,10 +2289,10 @@ decides to throw at it.
 
 The Linux kernel is used for real-time workloads, especially in
 conjunction with the `-rt
-patchset <https://rt.wiki.kernel.org/index.php/Main_Page>`__. The
+patchset <https://wiki.linuxfoundation.org/realtime/>`__. 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 ``CONFIG_PREEMPT=y`` therefore use
+is inappropriate. Kernels built with ``CONFIG_PREEMPTION=y`` 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
 clear that an earlier `real-time
@@ -2414,7 +2414,7 @@ includes ``rcu_read_lock_bh()``, ``rcu_read_unlock_bh()``,
 ``call_rcu_bh()``, ``rcu_barrier_bh()``, and
 ``rcu_read_lock_bh_held()``. However, the update-side APIs are now
 simple wrappers for other RCU flavors, namely RCU-sched in
-CONFIG_PREEMPT=n kernels and RCU-preempt otherwise.
+CONFIG_PREEMPTION=n kernels and RCU-preempt otherwise.
 
 Sched Flavor (Historical)
 ~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -2432,11 +2432,11 @@ not have this property, given that any point in the code outside of an
 RCU read-side critical section can be a quiescent state. Therefore,
 *RCU-sched* was created, which follows “classic” RCU in that an
 RCU-sched grace period waits for pre-existing interrupt and NMI
-handlers. In kernels built with ``CONFIG_PREEMPT=n``, the RCU and
+handlers. In kernels built with ``CONFIG_PREEMPTION=n``, the RCU and
 RCU-sched APIs have identical implementations, while kernels built with
-``CONFIG_PREEMPT=y`` provide a separate implementation for each.
+``CONFIG_PREEMPTION=y`` provide a separate implementation for each.
 
-Note well that in ``CONFIG_PREEMPT=y`` kernels,
+Note well that in ``CONFIG_PREEMPTION=y`` kernels,
 ``rcu_read_lock_sched()`` and ``rcu_read_unlock_sched()`` disable and
 re-enable preemption, respectively. This means that if there was a
 preemption attempt during the RCU-sched read-side critical section,
@@ -2599,10 +2599,10 @@ userspace execution also delimit tasks-RCU read-side critical sections.
 
 The tasks-RCU API is quite compact, consisting only of
 ``call_rcu_tasks()``, ``synchronize_rcu_tasks()``, and
-``rcu_barrier_tasks()``. In ``CONFIG_PREEMPT=n`` kernels, trampolines
+``rcu_barrier_tasks()``. In ``CONFIG_PREEMPTION=n`` kernels, trampolines
 cannot be preempted, so these APIs map to ``call_rcu()``,
 ``synchronize_rcu()``, and ``rcu_barrier()``, respectively. In
-``CONFIG_PREEMPT=y`` kernels, trampolines can be preempted, and these
+``CONFIG_PREEMPTION=y`` 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.rst b/Documentation/RCU/checklist.rst
index 2efed9926c3f9..7ed4956043bd9 100644
--- a/Documentation/RCU/checklist.rst
+++ b/Documentation/RCU/checklist.rst
@@ -214,7 +214,7 @@ 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.
+	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(),
diff --git a/Documentation/RCU/rcubarrier.rst b/Documentation/RCU/rcubarrier.rst
index f64f4413a47c4..3b4a248774961 100644
--- a/Documentation/RCU/rcubarrier.rst
+++ b/Documentation/RCU/rcubarrier.rst
@@ -9,7 +9,7 @@ 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
+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
@@ -329,10 +329,10 @@ 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.rst b/Documentation/RCU/stallwarn.rst
index c9ab6af4d3be9..e97d1b4876ef4 100644
--- a/Documentation/RCU/stallwarn.rst
+++ b/Documentation/RCU/stallwarn.rst
@@ -25,7 +25,7 @@ warnings:
 
 -	A CPU looping with bottom halves disabled.
 
--	For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel
+-	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().
@@ -44,7 +44,7 @@ warnings:
 	result in the ``rcu_.*kthread starved for`` console-log message,
 	which will include additional debugging information.
 
--	A CPU-bound real-time task in a CONFIG_PREEMPT kernel, which might
+-	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.rst b/Documentation/RCU/whatisRCU.rst
index fb3ff76c3e737..3b2b1479fd0f7 100644
--- a/Documentation/RCU/whatisRCU.rst
+++ b/Documentation/RCU/whatisRCU.rst
@@ -684,7 +684,7 @@ Quick Quiz #1:
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 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
+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.
 ::
@@ -740,7 +740,7 @@ Quick Quiz #2:
 Quick Quiz #3:
 		If it is illegal to block in an RCU read-side
 		critical section, what the heck do you do in
-		PREEMPT_RT, where normal spinlocks can block???
+		CONFIG_PREEMPT_RT, where normal spinlocks can block???
 
 :ref:`Answers to Quick Quiz <8_whatisRCU>`
 
@@ -1094,7 +1094,7 @@ Quick Quiz #2:
 		overhead is **negative**.
 
 Answer:
-		Imagine a single-CPU system with a non-CONFIG_PREEMPT
+		Imagine a single-CPU system with a non-CONFIG_PREEMPTION
 		kernel where a routing table is used by process-context
 		code, but can be updated by irq-context code (for example,
 		by an "ICMP REDIRECT" packet).	The usual way of handling
@@ -1121,10 +1121,10 @@ Answer:
 Quick Quiz #3:
 		If it is illegal to block in an RCU read-side
 		critical section, what the heck do you do in
-		PREEMPT_RT, where normal spinlocks can block???
+		CONFIG_PREEMPT_RT, where normal spinlocks can block???
 
 Answer:
-		Just as PREEMPT_RT permits preemption of spinlock
+		Just as CONFIG_PREEMPT_RT permits preemption of spinlock
 		critical sections, it permits preemption of RCU
 		read-side critical sections.  It also permits
 		spinlocks blocking while in RCU read-side critical
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index d00618967854d..4ee4dca81fbda 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -4097,6 +4097,10 @@
 			value, meaning that RCU_SOFTIRQ is used by default.
 			Specify rcutree.use_softirq=0 to use rcuc kthreads.
 
+			But note that CONFIG_PREEMPT_RT=y kernels disable
+			this kernel boot parameter, forcibly setting it
+			to zero.
+
 	rcutree.rcu_fanout_exact= [KNL]
 			Disable autobalancing of the rcu_node combining
 			tree.  This is used by rcutorture, and might
@@ -4475,6 +4479,13 @@
 			only normal grace-period primitives.  No effect
 			on CONFIG_TINY_RCU kernels.
 
+			But note that CONFIG_PREEMPT_RT=y kernels enables
+			this kernel boot parameter, forcibly setting
+			it to the value one, that is, converting any
+			post-boot attempt at an expedited RCU grace
+			period to instead use normal non-expedited
+			grace-period processing.
+
 	rcupdate.rcu_task_ipi_delay= [KNL]
 			Set time in jiffies during which RCU tasks will
 			avoid sending IPIs, starting with the beginning
diff --git a/Documentation/driver-api/io-mapping.rst b/Documentation/driver-api/io-mapping.rst
index a966239f04e48..a7830c59481f6 100644
--- a/Documentation/driver-api/io-mapping.rst
+++ b/Documentation/driver-api/io-mapping.rst
@@ -20,78 +20,64 @@ A mapping object is created during driver initialization using::
 mappable, while 'size' indicates how large a mapping region to
 enable. Both are in bytes.
 
-This _wc variant provides a mapping which may only be used
-with the io_mapping_map_atomic_wc or io_mapping_map_wc.
+This _wc variant provides a mapping which may only be used with
+io_mapping_map_local_wc() or io_mapping_map_wc().
 
-With this mapping object, individual pages can be mapped either atomically
-or not, depending on the necessary scheduling environment. Of course, atomic
-maps are more efficient::
+With this mapping object, individual pages can be mapped either temporarily
+or long term, depending on the requirements. Of course, temporary maps are
+more efficient.
 
-	void *io_mapping_map_atomic_wc(struct io_mapping *mapping,
-				       unsigned long offset)
+	void *io_mapping_map_local_wc(struct io_mapping *mapping,
+				      unsigned long offset)
 
-'offset' is the offset within the defined mapping region.
-Accessing addresses beyond the region specified in the
-creation function yields undefined results. Using an offset
-which is not page aligned yields an undefined result. The
-return value points to a single page in CPU address space.
+'offset' is the offset within the defined mapping region.  Accessing
+addresses beyond the region specified in the creation function yields
+undefined results. Using an offset which is not page aligned yields an
+undefined result. The return value points to a single page in CPU address
+space.
 
-This _wc variant returns a write-combining map to the
-page and may only be used with mappings created by
-io_mapping_create_wc
+This _wc variant returns a write-combining map to the page and may only be
+used with mappings created by io_mapping_create_wc()
 
-Note that the task may not sleep while holding this page
-mapped.
+Temporary mappings are only valid in the context of the caller. The mapping
+is not guaranteed to be globaly visible.
 
-::
+io_mapping_map_local_wc() has a side effect on X86 32bit as it disables
+migration to make the mapping code work. No caller can rely on this side
+effect.
 
-	void io_mapping_unmap_atomic(void *vaddr)
+Nested mappings need to be undone in reverse order because the mapping
+code uses a stack for keeping track of them::
 
-'vaddr' must be the value returned by the last
-io_mapping_map_atomic_wc call. This unmaps the specified
-page and allows the task to sleep once again.
+ addr1 = io_mapping_map_local_wc(map1, offset1);
+ addr2 = io_mapping_map_local_wc(map2, offset2);
+ ...
+ io_mapping_unmap_local(addr2);
+ io_mapping_unmap_local(addr1);
 
-If you need to sleep while holding the lock, you can use the non-atomic
-variant, although they may be significantly slower.
+The mappings are released with::
 
-::
+	void io_mapping_unmap_local(void *vaddr)
+
+'vaddr' must be the value returned by the last io_mapping_map_local_wc()
+call. This unmaps the specified mapping and undoes eventual side effects of
+the mapping function.
+
+If you need to sleep while holding a mapping, you can use the regular
+variant, although this may be significantly slower::
 
 	void *io_mapping_map_wc(struct io_mapping *mapping,
 				unsigned long offset)
 
-This works like io_mapping_map_atomic_wc except it allows
-the task to sleep while holding the page mapped.
+This works like io_mapping_map_local_wc() except it has no side effects and
+the pointer is globaly visible.
 
-
-::
+The mappings are released with::
 
 	void io_mapping_unmap(void *vaddr)
 
-This works like io_mapping_unmap_atomic, except it is used
-for pages mapped with io_mapping_map_wc.
+Use for pages mapped with io_mapping_map_wc().
 
 At driver close time, the io_mapping object must be freed::
 
 	void io_mapping_free(struct io_mapping *mapping)
-
-Current Implementation
-======================
-
-The initial implementation of these functions uses existing mapping
-mechanisms and so provides only an abstraction layer and no new
-functionality.
-
-On 64-bit processors, io_mapping_create_wc calls ioremap_wc for the whole
-range, creating a permanent kernel-visible mapping to the resource. The
-map_atomic and map functions add the requested offset to the base of the
-virtual address returned by ioremap_wc.
-
-On 32-bit processors with HIGHMEM defined, io_mapping_map_atomic_wc uses
-kmap_atomic_pfn to map the specified page in an atomic fashion;
-kmap_atomic_pfn isn't really supposed to be used with device pages, but it
-provides an efficient mapping for this usage.
-
-On 32-bit processors without HIGHMEM defined, io_mapping_map_atomic_wc and
-io_mapping_map_wc both use ioremap_wc, a terribly inefficient function which
-performs an IPI to inform all processors about the new mapping. This results
-in a significant performance penalty.
diff --git a/arch/Kconfig b/arch/Kconfig
index 632d60e13494c..c4713403ae3f7 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -37,6 +37,7 @@ 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
@@ -643,6 +644,12 @@ config HAVE_TIF_NOHZ
 config HAVE_VIRT_CPU_ACCOUNTING
 	bool
 
+config HAVE_VIRT_CPU_ACCOUNTING_IDLE
+	bool
+	help
+	  Architecture has its own way to account idle CPU time and therefore
+	  doesn't implement vtime_account_idle().
+
 config ARCH_HAS_SCALED_CPUTIME
 	bool
 
@@ -657,7 +664,6 @@ config HAVE_VIRT_CPU_ACCOUNTING_GEN
 	  some 32-bit arches may require multiple accesses, so proper
 	  locking is needed to protect against concurrent accesses.
 
-
 config HAVE_IRQ_TIME_ACCOUNTING
 	bool
 	help
diff --git a/arch/alpha/include/asm/kmap_types.h b/arch/alpha/include/asm/kmap_types.h
deleted file mode 100644
index 651714b45729a..0000000000000
--- a/arch/alpha/include/asm/kmap_types.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_KMAP_TYPES_H
-#define _ASM_KMAP_TYPES_H
-
-/* Dummy header just to define km_type. */
-
-#ifdef CONFIG_DEBUG_HIGHMEM
-#define  __WITH_KM_FENCE
-#endif
-
-#include <asm-generic/kmap_types.h>
-
-#undef __WITH_KM_FENCE
-
-#endif
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/Kconfig b/arch/arc/Kconfig
index 0a89cc9def651..d8804001d5507 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -507,6 +507,7 @@ config LINUX_RAM_BASE
 config HIGHMEM
 	bool "High Memory Support"
 	select ARCH_DISCONTIGMEM_ENABLE
+	select KMAP_LOCAL
 	help
 	  With ARC 2G:2G address split, only upper 2G is directly addressable by
 	  kernel. Enable this to potentially allow access to rest of 2G and PAE
diff --git a/arch/arc/include/asm/highmem.h b/arch/arc/include/asm/highmem.h
index 6e5eafb3afdd4..a6b8e2c352c44 100644
--- a/arch/arc/include/asm/highmem.h
+++ b/arch/arc/include/asm/highmem.h
@@ -9,17 +9,29 @@
 #ifdef CONFIG_HIGHMEM
 
 #include <uapi/asm/page.h>
-#include <asm/kmap_types.h>
+#include <asm/kmap_size.h>
+
+#define FIXMAP_SIZE		PGDIR_SIZE
+#define PKMAP_SIZE		PGDIR_SIZE
 
 /* start after vmalloc area */
 #define FIXMAP_BASE		(PAGE_OFFSET - FIXMAP_SIZE - PKMAP_SIZE)
-#define FIXMAP_SIZE		PGDIR_SIZE	/* only 1 PGD worth */
-#define KM_TYPE_NR		((FIXMAP_SIZE >> PAGE_SHIFT)/NR_CPUS)
-#define FIXMAP_ADDR(nr)		(FIXMAP_BASE + ((nr) << PAGE_SHIFT))
+
+#define FIX_KMAP_SLOTS		(KM_MAX_IDX * NR_CPUS)
+#define FIX_KMAP_BEGIN		(0UL)
+#define FIX_KMAP_END		((FIX_KMAP_BEGIN + FIX_KMAP_SLOTS) - 1)
+
+#define FIXADDR_TOP		(FIXMAP_BASE + (FIX_KMAP_END << PAGE_SHIFT))
+
+/*
+ * This should be converted to the asm-generic version, but of course this
+ * is needlessly different from all other architectures. Sigh - tglx
+ */
+#define __fix_to_virt(x)	(FIXADDR_TOP - ((x) << PAGE_SHIFT))
+#define __virt_to_fix(x)	(((FIXADDR_TOP - ((x) & PAGE_MASK))) >> PAGE_SHIFT)
 
 /* start after fixmap area */
 #define PKMAP_BASE		(FIXMAP_BASE + FIXMAP_SIZE)
-#define PKMAP_SIZE		PGDIR_SIZE
 #define LAST_PKMAP		(PKMAP_SIZE >> PAGE_SHIFT)
 #define LAST_PKMAP_MASK		(LAST_PKMAP - 1)
 #define PKMAP_ADDR(nr)		(PKMAP_BASE + ((nr) << PAGE_SHIFT))
@@ -29,11 +41,13 @@
 
 extern void kmap_init(void);
 
+#define arch_kmap_local_post_unmap(vaddr)			\
+	local_flush_tlb_kernel_range(vaddr, vaddr + PAGE_SIZE)
+
 static inline void flush_cache_kmaps(void)
 {
 	flush_cache_all();
 }
-
 #endif
 
 #endif
diff --git a/arch/arc/include/asm/kmap_types.h b/arch/arc/include/asm/kmap_types.h
deleted file mode 100644
index fecf7851ec322..0000000000000
--- a/arch/arc/include/asm/kmap_types.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2015 Synopsys, Inc. (www.synopsys.com)
- */
-
-#ifndef _ASM_KMAP_TYPES_H
-#define _ASM_KMAP_TYPES_H
-
-/*
- * We primarily need to define KM_TYPE_NR here but that in turn
- * is a function of PGDIR_SIZE etc.
- * To avoid circular deps issue, put everything in asm/highmem.h
- */
-#endif
diff --git a/arch/arc/mm/highmem.c b/arch/arc/mm/highmem.c
index 1b9f473c63693..c79912a6b1961 100644
--- a/arch/arc/mm/highmem.c
+++ b/arch/arc/mm/highmem.c
@@ -36,9 +36,8 @@
  *   This means each only has 1 PGDIR_SIZE worth of kvaddr mappings, which means
  *   2M of kvaddr space for typical config (8K page and 11:8:13 traversal split)
  *
- * - fixmap anyhow needs a limited number of mappings. So 2M kvaddr == 256 PTE
- *   slots across NR_CPUS would be more than sufficient (generic code defines
- *   KM_TYPE_NR as 20).
+ * - The fixed KMAP slots for kmap_local/atomic() require KM_MAX_IDX slots per
+ *   CPU. So the number of CPUs sharing a single PTE page is limited.
  *
  * - pkmap being preemptible, in theory could do with more than 256 concurrent
  *   mappings. However, generic pkmap code: map_new_virtual(), doesn't traverse
@@ -47,48 +46,6 @@
  */
 
 extern pte_t * pkmap_page_table;
-static pte_t * fixmap_page_table;
-
-void *kmap_atomic_high_prot(struct page *page, pgprot_t prot)
-{
-	int idx, cpu_idx;
-	unsigned long vaddr;
-
-	cpu_idx = kmap_atomic_idx_push();
-	idx = cpu_idx + KM_TYPE_NR * smp_processor_id();
-	vaddr = FIXMAP_ADDR(idx);
-
-	set_pte_at(&init_mm, vaddr, fixmap_page_table + idx,
-		   mk_pte(page, prot));
-
-	return (void *)vaddr;
-}
-EXPORT_SYMBOL(kmap_atomic_high_prot);
-
-void kunmap_atomic_high(void *kv)
-{
-	unsigned long kvaddr = (unsigned long)kv;
-
-	if (kvaddr >= FIXMAP_BASE && kvaddr < (FIXMAP_BASE + FIXMAP_SIZE)) {
-
-		/*
-		 * Because preemption is disabled, this vaddr can be associated
-		 * with the current allocated index.
-		 * But in case of multiple live kmap_atomic(), it still relies on
-		 * callers to unmap in right order.
-		 */
-		int cpu_idx = kmap_atomic_idx();
-		int idx = cpu_idx + KM_TYPE_NR * smp_processor_id();
-
-		WARN_ON(kvaddr != FIXMAP_ADDR(idx));
-
-		pte_clear(&init_mm, kvaddr, fixmap_page_table + idx);
-		local_flush_tlb_kernel_range(kvaddr, kvaddr + PAGE_SIZE);
-
-		kmap_atomic_idx_pop();
-	}
-}
-EXPORT_SYMBOL(kunmap_atomic_high);
 
 static noinline pte_t * __init alloc_kmap_pgtable(unsigned long kvaddr)
 {
@@ -108,10 +65,9 @@ void __init kmap_init(void)
 {
 	/* Due to recursive include hell, we can't do this in processor.h */
 	BUILD_BUG_ON(PAGE_OFFSET < (VMALLOC_END + FIXMAP_SIZE + PKMAP_SIZE));
+	BUILD_BUG_ON(LAST_PKMAP > PTRS_PER_PTE);
+	BUILD_BUG_ON(FIX_KMAP_SLOTS > PTRS_PER_PTE);
 
-	BUILD_BUG_ON(KM_TYPE_NR > PTRS_PER_PTE);
 	pkmap_page_table = alloc_kmap_pgtable(PKMAP_BASE);
-
-	BUILD_BUG_ON(LAST_PKMAP > PTRS_PER_PTE);
-	fixmap_page_table = alloc_kmap_pgtable(FIXMAP_BASE);
+	alloc_kmap_pgtable(FIXMAP_BASE);
 }
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index a0eac00e2c81a..6bcbefad00911 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -31,6 +31,7 @@ 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 if HAVE_POSIX_CPU_TIMERS_TASK_WORK
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT if MMU
@@ -66,7 +67,7 @@ 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
@@ -106,6 +107,7 @@ config ARM
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
+	select HAVE_PREEMPT_LAZY
 	select MMU_GATHER_RCU_TABLE_FREE if SMP && ARM_LPAE
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RSEQ
@@ -121,6 +123,7 @@ config ARM
 	select OLD_SIGSUSPEND3
 	select PCI_SYSCALL if PCI
 	select PERF_USE_VMALLOC
+	select HAVE_POSIX_CPU_TIMERS_TASK_WORK if !KVM
 	select RTC_LIB
 	select SET_FS
 	select SYS_SUPPORTS_APM_EMULATION
@@ -1500,6 +1503,7 @@ config HAVE_ARCH_PFN_VALID
 config HIGHMEM
 	bool "High Memory Support"
 	depends on MMU
+	select KMAP_LOCAL
 	help
 	  The address space of ARM processors is only 4 Gigabytes large
 	  and it has to accommodate user address space, kernel address
diff --git a/arch/arm/include/asm/fixmap.h b/arch/arm/include/asm/fixmap.h
index 9575b404019c9..707068f852c27 100644
--- a/arch/arm/include/asm/fixmap.h
+++ b/arch/arm/include/asm/fixmap.h
@@ -7,14 +7,14 @@
 #define FIXADDR_TOP		(FIXADDR_END - PAGE_SIZE)
 
 #include <linux/pgtable.h>
-#include <asm/kmap_types.h>
+#include <asm/kmap_size.h>
 
 enum fixed_addresses {
 	FIX_EARLYCON_MEM_BASE,
 	__end_of_permanent_fixed_addresses,
 
 	FIX_KMAP_BEGIN = __end_of_permanent_fixed_addresses,
-	FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_TYPE_NR * NR_CPUS) - 1,
+	FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_MAX_IDX * NR_CPUS) - 1,
 
 	/* Support writing RO kernel text via kprobes, jump labels, etc. */
 	FIX_TEXT_POKE0,
diff --git a/arch/arm/include/asm/hardirq.h b/arch/arm/include/asm/hardirq.h
index b95848ed2bc7f..706efafbf9722 100644
--- a/arch/arm/include/asm/hardirq.h
+++ b/arch/arm/include/asm/hardirq.h
@@ -2,16 +2,11 @@
 #ifndef __ASM_HARDIRQ_H
 #define __ASM_HARDIRQ_H
 
-#include <linux/cache.h>
-#include <linux/threads.h>
 #include <asm/irq.h>
 
-typedef struct {
-	unsigned int __softirq_pending;
-} ____cacheline_aligned irq_cpustat_t;
-
-#include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
-
 #define __ARCH_IRQ_EXIT_IRQS_DISABLED	1
+#define ack_bad_irq ack_bad_irq
+
+#include <asm-generic/hardirq.h>
 
 #endif /* __ASM_HARDIRQ_H */
diff --git a/arch/arm/include/asm/highmem.h b/arch/arm/include/asm/highmem.h
index 31811be38d781..b22dffa8c7eb9 100644
--- a/arch/arm/include/asm/highmem.h
+++ b/arch/arm/include/asm/highmem.h
@@ -2,7 +2,8 @@
 #ifndef _ASM_HIGHMEM_H
 #define _ASM_HIGHMEM_H
 
-#include <asm/kmap_types.h>
+#include <asm/kmap_size.h>
+#include <asm/fixmap.h>
 
 #define PKMAP_BASE		(PAGE_OFFSET - PMD_SIZE)
 #define LAST_PKMAP		PTRS_PER_PTE
@@ -46,19 +47,32 @@ extern pte_t *pkmap_page_table;
 
 #ifdef ARCH_NEEDS_KMAP_HIGH_GET
 extern void *kmap_high_get(struct page *page);
-#else
+
+static inline void *arch_kmap_local_high_get(struct page *page)
+{
+	if (IS_ENABLED(CONFIG_DEBUG_HIGHMEM) && !cache_is_vivt())
+		return NULL;
+	return kmap_high_get(page);
+}
+#define arch_kmap_local_high_get arch_kmap_local_high_get
+
+#else /* ARCH_NEEDS_KMAP_HIGH_GET */
 static inline void *kmap_high_get(struct page *page)
 {
 	return NULL;
 }
-#endif
+#endif /* !ARCH_NEEDS_KMAP_HIGH_GET */
 
-/*
- * The following functions are already defined by <linux/highmem.h>
- * when CONFIG_HIGHMEM is not set.
- */
-#ifdef CONFIG_HIGHMEM
-extern void *kmap_atomic_pfn(unsigned long pfn);
-#endif
+#define arch_kmap_local_post_map(vaddr, pteval)				\
+	local_flush_tlb_kernel_page(vaddr)
+
+#define arch_kmap_local_pre_unmap(vaddr)				\
+do {									\
+	if (cache_is_vivt())						\
+		__cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE);	\
+} while (0)
+
+#define arch_kmap_local_post_unmap(vaddr)				\
+	local_flush_tlb_kernel_page(vaddr)
 
 #endif
diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h
index 46d41140df27d..1cbcc462b07e8 100644
--- a/arch/arm/include/asm/irq.h
+++ b/arch/arm/include/asm/irq.h
@@ -31,6 +31,8 @@ void handle_IRQ(unsigned int, struct pt_regs *);
 void init_IRQ(void);
 
 #ifdef CONFIG_SMP
+#include <linux/cpumask.h>
+
 extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask,
 					   bool exclude_self);
 #define arch_trigger_cpumask_backtrace arch_trigger_cpumask_backtrace
diff --git a/arch/arm/include/asm/kmap_types.h b/arch/arm/include/asm/kmap_types.h
deleted file mode 100644
index 5590940ee43d7..0000000000000
--- a/arch/arm/include/asm/kmap_types.h
+++ /dev/null
@@ -1,10 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __ARM_KMAP_TYPES_H
-#define __ARM_KMAP_TYPES_H
-
-/*
- * This is the "bare minimum".  AIO seems to require this.
- */
-#define KM_TYPE_NR 16
-
-#endif
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/thread_info.h b/arch/arm/include/asm/thread_info.h
index 536b6b979f634..875aaf9af9465 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 */
@@ -134,7 +135,8 @@ 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_NEED_RESCHED_LAZY	7
+#define TIF_SECCOMP		8	/* seccomp syscall filtering active */
 
 #define TIF_USING_IWMMXT	17
 #define TIF_MEMDIE		18	/* is terminating due to OOM killer */
@@ -143,6 +145,7 @@ 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)
@@ -158,7 +161,8 @@ 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 70993af22d80c..024c65c3a0f23 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -43,6 +43,7 @@ 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 63fbcdc97ded9..4a9594fdb0048 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -206,11 +206,18 @@ __irq_svc:
 
 #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
@@ -225,8 +232,14 @@ svc_preempt:
 1:	bl	preempt_schedule_irq		@ irq en/disable is done inside
 	ldr	r0, [tsk, #TI_FLAGS]		@ get new tasks TI_FLAGS
 	tst	r0, #_TIF_NEED_RESCHED
+	bne	1b
+	tst	r0, #_TIF_NEED_RESCHED_LAZY
 	reteq	r8				@ go again
-	b	1b
+	ldr	r0, [tsk, #TI_PREEMPT_LAZY]	@ get preempt lazy count
+	teq	r0, #0				@ if preempt lazy count != 0
+	beq	1b
+	ret	r8				@ go again
+
 #endif
 
 __und_fault:
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 271cb8a1eba1e..fd039b1b37319 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -53,7 +53,9 @@ __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	fast_work_pending
+	tst	r1, #_TIF_SECCOMP
 	bne	fast_work_pending
 
 
@@ -90,8 +92,11 @@ __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 2f81d3af5f9af..6e69f7b3d5813 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 8aa7fa949c232..3693706ba0a1a 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -671,9 +671,7 @@ static void do_handle_IPI(int ipinr)
 		break;
 
 	case IPI_CPU_BACKTRACE:
-		printk_nmi_enter();
 		nmi_cpu_backtrace(get_irq_regs());
-		printk_nmi_exit();
 		break;
 
 	default:
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index 7cb1699fbfc4f..c4ce477c52611 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -19,7 +19,6 @@ obj-$(CONFIG_MODULES)		+= proc-syms.o
 obj-$(CONFIG_DEBUG_VIRTUAL)	+= physaddr.o
 
 obj-$(CONFIG_ALIGNMENT_TRAP)	+= alignment.o
-obj-$(CONFIG_HIGHMEM)		+= highmem.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_ARM_PV_FIXUP)	+= pv-fixup-asm.o
 
diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c
index 5c1b7a7b9af63..87328766e9102 100644
--- a/arch/arm/mm/cache-feroceon-l2.c
+++ b/arch/arm/mm/cache-feroceon-l2.c
@@ -49,9 +49,9 @@ static inline unsigned long l2_get_va(unsigned long paddr)
 	 * we simply install a virtual mapping for it only for the
 	 * TLB lookup to occur, hence no need to flush the untouched
 	 * memory mapping afterwards (note: a cache flush may happen
-	 * in some circumstances depending on the path taken in kunmap_atomic).
+	 * in some circumstances depending on the path taken in kunmap_local).
 	 */
-	void *vaddr = kmap_atomic_pfn(paddr >> PAGE_SHIFT);
+	void *vaddr = kmap_local_pfn(paddr >> PAGE_SHIFT);
 	return (unsigned long)vaddr + (paddr & ~PAGE_MASK);
 #else
 	return __phys_to_virt(paddr);
@@ -61,7 +61,7 @@ static inline unsigned long l2_get_va(unsigned long paddr)
 static inline void l2_put_va(unsigned long vaddr)
 {
 #ifdef CONFIG_HIGHMEM
-	kunmap_atomic((void *)vaddr);
+	kunmap_local((void *)vaddr);
 #endif
 }
 
diff --git a/arch/arm/mm/cache-xsc3l2.c b/arch/arm/mm/cache-xsc3l2.c
index d20d7af02d10f..0e0a3abd81743 100644
--- a/arch/arm/mm/cache-xsc3l2.c
+++ b/arch/arm/mm/cache-xsc3l2.c
@@ -59,7 +59,7 @@ static inline void l2_unmap_va(unsigned long va)
 {
 #ifdef CONFIG_HIGHMEM
 	if (va != -1)
-		kunmap_atomic((void *)va);
+		kunmap_local((void *)va);
 #endif
 }
 
@@ -75,7 +75,7 @@ static inline unsigned long l2_map_va(unsigned long pa, unsigned long prev_va)
 		 * in place for it.
 		 */
 		l2_unmap_va(prev_va);
-		va = (unsigned long)kmap_atomic_pfn(pa >> PAGE_SHIFT);
+		va = (unsigned long)kmap_local_pfn(pa >> PAGE_SHIFT);
 	}
 	return va + (pa_offset >> (32 - PAGE_SHIFT));
 #else
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index efa4020250315..59487ee9fd612 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -400,6 +400,9 @@ 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;
 
@@ -470,6 +473,9 @@ 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
deleted file mode 100644
index 187fab227b509..0000000000000
--- a/arch/arm/mm/highmem.c
+++ /dev/null
@@ -1,121 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * arch/arm/mm/highmem.c -- ARM highmem support
- *
- * Author:	Nicolas Pitre
- * Created:	september 8, 2008
- * Copyright:	Marvell Semiconductors Inc.
- */
-
-#include <linux/module.h>
-#include <linux/highmem.h>
-#include <linux/interrupt.h>
-#include <asm/fixmap.h>
-#include <asm/cacheflush.h>
-#include <asm/tlbflush.h>
-#include "mm.h"
-
-static inline void set_fixmap_pte(int idx, pte_t pte)
-{
-	unsigned long vaddr = __fix_to_virt(idx);
-	pte_t *ptep = virt_to_kpte(vaddr);
-
-	set_pte_ext(ptep, pte, 0);
-	local_flush_tlb_kernel_page(vaddr);
-}
-
-static inline pte_t get_fixmap_pte(unsigned long vaddr)
-{
-	pte_t *ptep = virt_to_kpte(vaddr);
-
-	return *ptep;
-}
-
-void *kmap_atomic_high_prot(struct page *page, pgprot_t prot)
-{
-	unsigned int idx;
-	unsigned long vaddr;
-	void *kmap;
-	int type;
-
-#ifdef CONFIG_DEBUG_HIGHMEM
-	/*
-	 * There is no cache coherency issue when non VIVT, so force the
-	 * dedicated kmap usage for better debugging purposes in that case.
-	 */
-	if (!cache_is_vivt())
-		kmap = NULL;
-	else
-#endif
-		kmap = kmap_high_get(page);
-	if (kmap)
-		return kmap;
-
-	type = kmap_atomic_idx_push();
-
-	idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id();
-	vaddr = __fix_to_virt(idx);
-#ifdef CONFIG_DEBUG_HIGHMEM
-	/*
-	 * With debugging enabled, kunmap_atomic forces that entry to 0.
-	 * Make sure it was indeed properly unmapped.
-	 */
-	BUG_ON(!pte_none(get_fixmap_pte(vaddr)));
-#endif
-	/*
-	 * When debugging is off, kunmap_atomic leaves the previous mapping
-	 * in place, so the contained TLB flush ensures the TLB is updated
-	 * with the new mapping.
-	 */
-	set_fixmap_pte(idx, mk_pte(page, prot));
-
-	return (void *)vaddr;
-}
-EXPORT_SYMBOL(kmap_atomic_high_prot);
-
-void kunmap_atomic_high(void *kvaddr)
-{
-	unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
-	int idx, type;
-
-	if (kvaddr >= (void *)FIXADDR_START) {
-		type = kmap_atomic_idx();
-		idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id();
-
-		if (cache_is_vivt())
-			__cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE);
-#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
-		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)]));
-	}
-}
-EXPORT_SYMBOL(kunmap_atomic_high);
-
-void *kmap_atomic_pfn(unsigned long pfn)
-{
-	unsigned long vaddr;
-	int idx, type;
-	struct page *page = pfn_to_page(pfn);
-
-	preempt_disable();
-	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();
-	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));
-
-	return (void *)vaddr;
-}
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 3da71fe56b922..3ba7b561d2564 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -76,6 +76,7 @@ config ARM64
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_INT128 if CC_HAS_INT128 && (GCC_VERSION >= 50000 || CC_IS_CLANG)
 	select ARCH_SUPPORTS_NUMA_BALANCING
+	select ARCH_SUPPORTS_RT if HAVE_POSIX_CPU_TIMERS_TASK_WORK
 	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION if COMPAT
 	select ARCH_WANT_DEFAULT_BPF_JIT
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
@@ -173,6 +174,7 @@ 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_FUTEX_CMPXCHG if FUTEX
@@ -194,6 +196,7 @@ config ARM64
 	select PCI_DOMAINS_GENERIC if PCI
 	select PCI_ECAM if (ACPI && PCI)
 	select PCI_SYSCALL if PCI
+	select HAVE_POSIX_CPU_TIMERS_TASK_WORK if !KVM
 	select POWER_RESET
 	select POWER_SUPPLY
 	select SET_FS
diff --git a/arch/arm64/include/asm/hardirq.h b/arch/arm64/include/asm/hardirq.h
index 5ffa4bacdad38..cbfa7b6f2e098 100644
--- a/arch/arm64/include/asm/hardirq.h
+++ b/arch/arm64/include/asm/hardirq.h
@@ -13,11 +13,8 @@
 #include <asm/kvm_arm.h>
 #include <asm/sysreg.h>
 
-typedef struct {
-	unsigned int __softirq_pending;
-} ____cacheline_aligned irq_cpustat_t;
-
-#include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
+#define ack_bad_irq ack_bad_irq
+#include <asm-generic/hardirq.h>
 
 #define __ARCH_IRQ_EXIT_IRQS_DISABLED	1
 
diff --git a/arch/arm64/include/asm/preempt.h b/arch/arm64/include/asm/preempt.h
index e83f0982b99c1..7a5770d825b91 100644
--- a/arch/arm64/include/asm/preempt.h
+++ b/arch/arm64/include/asm/preempt.h
@@ -70,17 +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_PREEMPTION
 void preempt_schedule(void);
+#ifdef CONFIG_PREEMPT_RT
+void preempt_schedule_lock(void);
+#endif
 #define __preempt_schedule() preempt_schedule()
 void preempt_schedule_notrace(void);
 #define __preempt_schedule_notrace() preempt_schedule_notrace()
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 1fbab854a51b0..148b53dc2840e 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 {
@@ -68,6 +69,7 @@ void arch_release_task_struct(struct task_struct *tsk);
 #define TIF_UPROBE		4	/* uprobe breakpoint or singlestep */
 #define TIF_FSCHECK		5	/* Check FS is USER_DS on return */
 #define TIF_MTE_ASYNC_FAULT	6	/* MTE Asynchronous Tag Check Fault */
+#define TIF_NEED_RESCHED_LAZY	7
 #define TIF_SYSCALL_TRACE	8	/* syscall trace active */
 #define TIF_SYSCALL_AUDIT	9	/* syscall auditing */
 #define TIF_SYSCALL_TRACEPOINT	10	/* syscall tracepoint for ftrace */
@@ -98,11 +100,14 @@ void arch_release_task_struct(struct task_struct *tsk);
 #define _TIF_32BIT		(1 << TIF_32BIT)
 #define _TIF_SVE		(1 << TIF_SVE)
 #define _TIF_MTE_ASYNC_FAULT	(1 << TIF_MTE_ASYNC_FAULT)
+#define _TIF_NEED_RESCHED_LAZY	(1 << TIF_NEED_RESCHED_LAZY)
 
 #define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
 				 _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \
-				 _TIF_UPROBE | _TIF_FSCHECK | _TIF_MTE_ASYNC_FAULT)
+				 _TIF_UPROBE | _TIF_FSCHECK | _TIF_MTE_ASYNC_FAULT | \
+				 _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_SYSCALL_EMU)
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index 7d32fc959b1a0..b2f29bd2ae871 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 fe83d6d67ec3d..cd2fc5556c8db 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -515,9 +515,18 @@ 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
 
 	mov	x0, sp
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index a9bbfb800ec2b..aa631771e0dcd 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -226,6 +226,16 @@ 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
@@ -1022,6 +1032,7 @@ 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;
@@ -1034,7 +1045,7 @@ 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.
@@ -1068,6 +1079,7 @@ 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 e62005317ce29..fe94a3e1f849b 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -919,7 +919,7 @@ 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/kvm/arm.c b/arch/arm64/kvm/arm.c
index 5bc978be80434..f262bb64e029a 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -708,7 +708,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 * involves poking the GIC, which must be done in a
 		 * non-preemptible context.
 		 */
-		preempt_disable();
+		migrate_disable();
 
 		kvm_pmu_flush_hwstate(vcpu);
 
@@ -757,7 +757,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 				kvm_timer_sync_user(vcpu);
 			kvm_vgic_sync_hwstate(vcpu);
 			local_irq_enable();
-			preempt_enable();
+			migrate_enable();
 			continue;
 		}
 
@@ -829,7 +829,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		/* Exit types that need handling before we can be preempted */
 		handle_exit_early(vcpu, ret);
 
-		preempt_enable();
+		migrate_enable();
 
 		/*
 		 * The ARMv8 architecture doesn't give the hypervisor
diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig
index 7bf0a617e94c3..c9f2533cc53db 100644
--- a/arch/csky/Kconfig
+++ b/arch/csky/Kconfig
@@ -286,6 +286,7 @@ config NR_CPUS
 config HIGHMEM
 	bool "High Memory Support"
 	depends on !CPU_CK610
+	select KMAP_LOCAL
 	default y
 
 config FORCE_MAX_ZONEORDER
diff --git a/arch/csky/include/asm/fixmap.h b/arch/csky/include/asm/fixmap.h
index 81f9477d5330c..4b589cc209000 100644
--- a/arch/csky/include/asm/fixmap.h
+++ b/arch/csky/include/asm/fixmap.h
@@ -8,7 +8,7 @@
 #include <asm/memory.h>
 #ifdef CONFIG_HIGHMEM
 #include <linux/threads.h>
-#include <asm/kmap_types.h>
+#include <asm/kmap_size.h>
 #endif
 
 enum fixed_addresses {
@@ -17,7 +17,7 @@ enum fixed_addresses {
 #endif
 #ifdef CONFIG_HIGHMEM
 	FIX_KMAP_BEGIN,
-	FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_TYPE_NR * NR_CPUS) - 1,
+	FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_MAX_IDX * NR_CPUS) - 1,
 #endif
 	__end_of_fixed_addresses
 };
diff --git a/arch/csky/include/asm/highmem.h b/arch/csky/include/asm/highmem.h
index 14645e3d5cd52..1f4ed3f4c0d9b 100644
--- a/arch/csky/include/asm/highmem.h
+++ b/arch/csky/include/asm/highmem.h
@@ -9,7 +9,7 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/uaccess.h>
-#include <asm/kmap_types.h>
+#include <asm/kmap_size.h>
 #include <asm/cache.h>
 
 /* undef for production */
@@ -32,10 +32,12 @@ extern pte_t *pkmap_page_table;
 
 #define ARCH_HAS_KMAP_FLUSH_TLB
 extern void kmap_flush_tlb(unsigned long addr);
-extern void *kmap_atomic_pfn(unsigned long pfn);
 
 #define flush_cache_kmaps() do {} while (0)
 
+#define arch_kmap_local_post_map(vaddr, pteval)	kmap_flush_tlb(vaddr)
+#define arch_kmap_local_post_unmap(vaddr)	kmap_flush_tlb(vaddr)
+
 extern void kmap_init(void);
 
 #endif /* __KERNEL__ */
diff --git a/arch/csky/mm/highmem.c b/arch/csky/mm/highmem.c
index 89c10800a002e..4161df3c6c152 100644
--- a/arch/csky/mm/highmem.c
+++ b/arch/csky/mm/highmem.c
@@ -9,8 +9,6 @@
 #include <asm/tlbflush.h>
 #include <asm/cacheflush.h>
 
-static pte_t *kmap_pte;
-
 unsigned long highstart_pfn, highend_pfn;
 
 void kmap_flush_tlb(unsigned long addr)
@@ -19,67 +17,7 @@ void kmap_flush_tlb(unsigned long addr)
 }
 EXPORT_SYMBOL(kmap_flush_tlb);
 
-void *kmap_atomic_high_prot(struct page *page, pgprot_t prot)
-{
-	unsigned long vaddr;
-	int idx, type;
-
-	type = kmap_atomic_idx_push();
-	idx = type + KM_TYPE_NR*smp_processor_id();
-	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-#ifdef CONFIG_DEBUG_HIGHMEM
-	BUG_ON(!pte_none(*(kmap_pte - idx)));
-#endif
-	set_pte(kmap_pte-idx, mk_pte(page, prot));
-	flush_tlb_one((unsigned long)vaddr);
-
-	return (void *)vaddr;
-}
-EXPORT_SYMBOL(kmap_atomic_high_prot);
-
-void kunmap_atomic_high(void *kvaddr)
-{
-	unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
-	int idx;
-
-	if (vaddr < FIXADDR_START)
-		return;
-
-#ifdef CONFIG_DEBUG_HIGHMEM
-	idx = KM_TYPE_NR*smp_processor_id() + kmap_atomic_idx();
-
-	BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
-
-	pte_clear(&init_mm, vaddr, kmap_pte - idx);
-	flush_tlb_one(vaddr);
-#else
-	(void) idx; /* to kill a warning */
-#endif
-	kmap_atomic_idx_pop();
-}
-EXPORT_SYMBOL(kunmap_atomic_high);
-
-/*
- * This is the same as kmap_atomic() but can map memory that doesn't
- * have a struct page associated with it.
- */
-void *kmap_atomic_pfn(unsigned long pfn)
-{
-	unsigned long vaddr;
-	int idx, type;
-
-	pagefault_disable();
-
-	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, PAGE_KERNEL));
-	flush_tlb_one(vaddr);
-
-	return (void *) vaddr;
-}
-
-static void __init kmap_pages_init(void)
+void __init kmap_init(void)
 {
 	unsigned long vaddr;
 	pgd_t *pgd;
@@ -96,14 +34,3 @@ static void __init kmap_pages_init(void)
 	pte = pte_offset_kernel(pmd, vaddr);
 	pkmap_page_table = pte;
 }
-
-void __init kmap_init(void)
-{
-	unsigned long vaddr;
-
-	kmap_pages_init();
-
-	vaddr = __fix_to_virt(FIX_KMAP_BEGIN);
-
-	kmap_pte = pte_offset_kernel((pmd_t *)pgd_offset_k(vaddr), vaddr);
-}
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/ia64/include/asm/kmap_types.h b/arch/ia64/include/asm/kmap_types.h
deleted file mode 100644
index 5c268cf7c2bd5..0000000000000
--- a/arch/ia64/include/asm/kmap_types.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_IA64_KMAP_TYPES_H
-#define _ASM_IA64_KMAP_TYPES_H
-
-#ifdef CONFIG_DEBUG_HIGHMEM
-#define  __WITH_KM_FENCE
-#endif
-
-#include <asm-generic/kmap_types.h>
-
-#undef __WITH_KM_FENCE
-
-#endif /* _ASM_IA64_KMAP_TYPES_H */
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/time.c b/arch/ia64/kernel/time.c
index 7abc5f37bfaf9..733e0e3324b80 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -138,12 +138,8 @@ void vtime_account_kernel(struct task_struct *tsk)
 	struct thread_info *ti = task_thread_info(tsk);
 	__u64 stime = vtime_delta(tsk);
 
-	if ((tsk->flags & PF_VCPU) && !irq_count())
+	if (tsk->flags & PF_VCPU)
 		ti->gtime += stime;
-	else if (hardirq_count())
-		ti->hardirq_time += stime;
-	else if (in_serving_softirq())
-		ti->softirq_time += stime;
 	else
 		ti->stime += stime;
 }
@@ -156,6 +152,20 @@ void vtime_account_idle(struct task_struct *tsk)
 	ti->idle_time += vtime_delta(tsk);
 }
 
+void vtime_account_softirq(struct task_struct *tsk)
+{
+	struct thread_info *ti = task_thread_info(tsk);
+
+	ti->softirq_time += vtime_delta(tsk);
+}
+
+void vtime_account_hardirq(struct task_struct *tsk)
+{
+	struct thread_info *ti = task_thread_info(tsk);
+
+	ti->hardirq_time += vtime_delta(tsk);
+}
+
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 
 static irqreturn_t
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index 33925ffed68fd..7f6ca0ab4f81f 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -155,6 +155,7 @@ config XILINX_UNCACHED_SHADOW
 config HIGHMEM
 	bool "High memory support"
 	depends on MMU
+	select KMAP_LOCAL
 	help
 	  The address space of Microblaze processors is only 4 Gigabytes large
 	  and it has to accommodate user address space, kernel address
diff --git a/arch/microblaze/include/asm/fixmap.h b/arch/microblaze/include/asm/fixmap.h
index 0379ce5229e3a..e6e9288bff761 100644
--- a/arch/microblaze/include/asm/fixmap.h
+++ b/arch/microblaze/include/asm/fixmap.h
@@ -20,7 +20,7 @@
 #include <asm/page.h>
 #ifdef CONFIG_HIGHMEM
 #include <linux/threads.h>
-#include <asm/kmap_types.h>
+#include <asm/kmap_size.h>
 #endif
 
 #define FIXADDR_TOP	((unsigned long)(-PAGE_SIZE))
@@ -47,7 +47,7 @@ enum fixed_addresses {
 	FIX_HOLE,
 #ifdef CONFIG_HIGHMEM
 	FIX_KMAP_BEGIN,	/* reserved pte's for temporary kernel mappings */
-	FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_TYPE_NR * num_possible_cpus()) - 1,
+	FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_MAX_IDX * num_possible_cpus()) - 1,
 #endif
 	__end_of_fixed_addresses
 };
diff --git a/arch/microblaze/include/asm/highmem.h b/arch/microblaze/include/asm/highmem.h
index 284ca8fb54c1d..4418633fb1632 100644
--- a/arch/microblaze/include/asm/highmem.h
+++ b/arch/microblaze/include/asm/highmem.h
@@ -25,7 +25,6 @@
 #include <linux/uaccess.h>
 #include <asm/fixmap.h>
 
-extern pte_t *kmap_pte;
 extern pte_t *pkmap_page_table;
 
 /*
@@ -52,6 +51,11 @@ extern pte_t *pkmap_page_table;
 
 #define flush_cache_kmaps()	{ flush_icache(); flush_dcache(); }
 
+#define arch_kmap_local_post_map(vaddr, pteval)	\
+	local_flush_tlb_page(NULL, vaddr);
+#define arch_kmap_local_post_unmap(vaddr)	\
+	local_flush_tlb_page(NULL, vaddr);
+
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_HIGHMEM_H */
diff --git a/arch/microblaze/mm/Makefile b/arch/microblaze/mm/Makefile
index 1b16875cea704..8ced711000471 100644
--- a/arch/microblaze/mm/Makefile
+++ b/arch/microblaze/mm/Makefile
@@ -6,4 +6,3 @@
 obj-y := consistent.o init.o
 
 obj-$(CONFIG_MMU) += pgtable.o mmu_context.o fault.o
-obj-$(CONFIG_HIGHMEM) += highmem.o
diff --git a/arch/microblaze/mm/highmem.c b/arch/microblaze/mm/highmem.c
deleted file mode 100644
index 92e0890416c91..0000000000000
--- a/arch/microblaze/mm/highmem.c
+++ /dev/null
@@ -1,78 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * highmem.c: virtual kernel memory mappings for high memory
- *
- * PowerPC version, stolen from the i386 version.
- *
- * Used in CONFIG_HIGHMEM systems for memory pages which
- * are not addressable by direct kernel virtual addresses.
- *
- * Copyright (C) 1999 Gerhard Wichert, Siemens AG
- *		      Gerhard.Wichert@pdb.siemens.de
- *
- *
- * Redesigned the x86 32-bit VM architecture to deal with
- * up to 16 Terrabyte physical memory. With current x86 CPUs
- * we now support up to 64 Gigabytes physical RAM.
- *
- * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
- *
- * Reworked for PowerPC by various contributors. Moved from
- * highmem.h by Benjamin Herrenschmidt (c) 2009 IBM Corp.
- */
-
-#include <linux/export.h>
-#include <linux/highmem.h>
-
-/*
- * The use of kmap_atomic/kunmap_atomic is discouraged - kmap/kunmap
- * gives a more generic (and caching) interface. But kmap_atomic can
- * be used in IRQ contexts, so in some (very limited) cases we need
- * it.
- */
-#include <asm/tlbflush.h>
-
-void *kmap_atomic_high_prot(struct page *page, pgprot_t prot)
-{
-
-	unsigned long vaddr;
-	int idx, type;
-
-	type = kmap_atomic_idx_push();
-	idx = type + KM_TYPE_NR*smp_processor_id();
-	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-#ifdef CONFIG_DEBUG_HIGHMEM
-	BUG_ON(!pte_none(*(kmap_pte-idx)));
-#endif
-	set_pte_at(&init_mm, vaddr, kmap_pte-idx, mk_pte(page, prot));
-	local_flush_tlb_page(NULL, vaddr);
-
-	return (void *) vaddr;
-}
-EXPORT_SYMBOL(kmap_atomic_high_prot);
-
-void kunmap_atomic_high(void *kvaddr)
-{
-	unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
-	int type;
-	unsigned int idx;
-
-	if (vaddr < __fix_to_virt(FIX_KMAP_END))
-		return;
-
-	type = kmap_atomic_idx();
-
-	idx = type + KM_TYPE_NR * smp_processor_id();
-#ifdef CONFIG_DEBUG_HIGHMEM
-	BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
-#endif
-	/*
-	 * force other mappings to Oops if they'll try to access
-	 * this pte without first remap it
-	 */
-	pte_clear(&init_mm, vaddr, kmap_pte-idx);
-	local_flush_tlb_page(NULL, vaddr);
-
-	kmap_atomic_idx_pop();
-}
-EXPORT_SYMBOL(kunmap_atomic_high);
diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
index 45da639bd22ca..1f4b5b34e6004 100644
--- a/arch/microblaze/mm/init.c
+++ b/arch/microblaze/mm/init.c
@@ -49,17 +49,11 @@ unsigned long lowmem_size;
 EXPORT_SYMBOL(min_low_pfn);
 EXPORT_SYMBOL(max_low_pfn);
 
-#ifdef CONFIG_HIGHMEM
-pte_t *kmap_pte;
-EXPORT_SYMBOL(kmap_pte);
-
 static void __init highmem_init(void)
 {
 	pr_debug("%x\n", (u32)PKMAP_BASE);
 	map_page(PKMAP_BASE, 0, 0);	/* XXX gross */
 	pkmap_page_table = virt_to_kpte(PKMAP_BASE);
-
-	kmap_pte = virt_to_kpte(__fix_to_virt(FIX_KMAP_BEGIN));
 }
 
 static void highmem_setup(void)
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 23d756fe0fd6c..4ea224e9add20 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2726,6 +2726,7 @@ config WAR_MIPS34K_MISSED_ITLB
 config HIGHMEM
 	bool "High Memory Support"
 	depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !CPU_MIPS32_3_5_EVA
+	select KMAP_LOCAL
 
 config CPU_SUPPORTS_HIGHMEM
 	bool
diff --git a/arch/mips/include/asm/fixmap.h b/arch/mips/include/asm/fixmap.h
index 743535be7528c..beea14761cef0 100644
--- a/arch/mips/include/asm/fixmap.h
+++ b/arch/mips/include/asm/fixmap.h
@@ -17,7 +17,7 @@
 #include <spaces.h>
 #ifdef CONFIG_HIGHMEM
 #include <linux/threads.h>
-#include <asm/kmap_types.h>
+#include <asm/kmap_size.h>
 #endif
 
 /*
@@ -52,7 +52,7 @@ enum fixed_addresses {
 #ifdef CONFIG_HIGHMEM
 	/* reserved pte's for temporary kernel mappings */
 	FIX_KMAP_BEGIN = FIX_CMAP_END + 1,
-	FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
+	FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_MAX_IDX * NR_CPUS) - 1,
 #endif
 	__end_of_fixed_addresses
 };
diff --git a/arch/mips/include/asm/highmem.h b/arch/mips/include/asm/highmem.h
index 9f021cf51aa71..1716181ea66dd 100644
--- a/arch/mips/include/asm/highmem.h
+++ b/arch/mips/include/asm/highmem.h
@@ -24,7 +24,7 @@
 #include <linux/interrupt.h>
 #include <linux/uaccess.h>
 #include <asm/cpu-features.h>
-#include <asm/kmap_types.h>
+#include <asm/kmap_size.h>
 
 /* declarations for highmem.c */
 extern unsigned long highstart_pfn, highend_pfn;
@@ -48,11 +48,11 @@ extern pte_t *pkmap_page_table;
 
 #define ARCH_HAS_KMAP_FLUSH_TLB
 extern void kmap_flush_tlb(unsigned long addr);
-extern void *kmap_atomic_pfn(unsigned long pfn);
 
 #define flush_cache_kmaps()	BUG_ON(cpu_has_dc_aliases)
 
-extern void kmap_init(void);
+#define arch_kmap_local_post_map(vaddr, pteval)	local_flush_tlb_one(vaddr)
+#define arch_kmap_local_post_unmap(vaddr)	local_flush_tlb_one(vaddr)
 
 #endif /* __KERNEL__ */
 
diff --git a/arch/mips/include/asm/kmap_types.h b/arch/mips/include/asm/kmap_types.h
deleted file mode 100644
index 16665dc2431b6..0000000000000
--- a/arch/mips/include/asm/kmap_types.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_KMAP_TYPES_H
-#define _ASM_KMAP_TYPES_H
-
-#ifdef CONFIG_DEBUG_HIGHMEM
-#define	 __WITH_KM_FENCE
-#endif
-
-#include <asm-generic/kmap_types.h>
-
-#undef __WITH_KM_FENCE
-
-#endif
diff --git a/arch/mips/kernel/crash_dump.c b/arch/mips/kernel/crash_dump.c
index 01b2bd95ba1f7..9aba83e1eeb4e 100644
--- a/arch/mips/kernel/crash_dump.c
+++ b/arch/mips/kernel/crash_dump.c
@@ -5,8 +5,6 @@
 #include <linux/uaccess.h>
 #include <linux/slab.h>
 
-static void *kdump_buf_page;
-
 /**
  * copy_oldmem_page - copy one page from "oldmem"
  * @pfn: page frame number to be copied
@@ -17,51 +15,25 @@ static void *kdump_buf_page;
  * @userbuf: if set, @buf is in user address space, use copy_to_user(),
  *	otherwise @buf is in kernel address space, use memcpy().
  *
- * Copy a page from "oldmem". For this page, there is no pte mapped
+ * Copy a page from "oldmem". For this page, there might be no pte mapped
  * in the current kernel.
- *
- * Calling copy_to_user() in atomic context is not desirable. Hence first
- * copying the data to a pre-allocated kernel page and then copying to user
- * space in non-atomic context.
  */
-ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
-			 size_t csize, unsigned long offset, int userbuf)
+ssize_t copy_oldmem_page(unsigned long pfn, char *buf, size_t csize,
+			 unsigned long offset, int userbuf)
 {
 	void  *vaddr;
 
 	if (!csize)
 		return 0;
 
-	vaddr = kmap_atomic_pfn(pfn);
+	vaddr = kmap_local_pfn(pfn);
 
 	if (!userbuf) {
-		memcpy(buf, (vaddr + offset), csize);
-		kunmap_atomic(vaddr);
+		memcpy(buf, vaddr + offset, csize);
 	} else {
-		if (!kdump_buf_page) {
-			pr_warn("Kdump: Kdump buffer page not allocated\n");
-
-			return -EFAULT;
-		}
-		copy_page(kdump_buf_page, vaddr);
-		kunmap_atomic(vaddr);
-		if (copy_to_user(buf, (kdump_buf_page + offset), csize))
-			return -EFAULT;
+		if (copy_to_user(buf, vaddr + offset, csize))
+			csize = -EFAULT;
 	}
 
 	return csize;
 }
-
-static int __init kdump_buf_page_init(void)
-{
-	int ret = 0;
-
-	kdump_buf_page = kmalloc(PAGE_SIZE, GFP_KERNEL);
-	if (!kdump_buf_page) {
-		pr_warn("Kdump: Failed to allocate kdump buffer page\n");
-		ret = -ENOMEM;
-	}
-
-	return ret;
-}
-arch_initcall(kdump_buf_page_init);
diff --git a/arch/mips/mm/highmem.c b/arch/mips/mm/highmem.c
index 5fec7f45d79a8..57e2f08f00d0c 100644
--- a/arch/mips/mm/highmem.c
+++ b/arch/mips/mm/highmem.c
@@ -8,8 +8,6 @@
 #include <asm/fixmap.h>
 #include <asm/tlbflush.h>
 
-static pte_t *kmap_pte;
-
 unsigned long highstart_pfn, highend_pfn;
 
 void kmap_flush_tlb(unsigned long addr)
@@ -17,78 +15,3 @@ void kmap_flush_tlb(unsigned long addr)
 	flush_tlb_one(addr);
 }
 EXPORT_SYMBOL(kmap_flush_tlb);
-
-void *kmap_atomic_high_prot(struct page *page, pgprot_t prot)
-{
-	unsigned long vaddr;
-	int idx, type;
-
-	type = kmap_atomic_idx_push();
-	idx = type + KM_TYPE_NR*smp_processor_id();
-	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-#ifdef CONFIG_DEBUG_HIGHMEM
-	BUG_ON(!pte_none(*(kmap_pte - idx)));
-#endif
-	set_pte(kmap_pte-idx, mk_pte(page, prot));
-	local_flush_tlb_one((unsigned long)vaddr);
-
-	return (void*) vaddr;
-}
-EXPORT_SYMBOL(kmap_atomic_high_prot);
-
-void kunmap_atomic_high(void *kvaddr)
-{
-	unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
-	int type __maybe_unused;
-
-	if (vaddr < FIXADDR_START)
-		return;
-
-	type = kmap_atomic_idx();
-#ifdef CONFIG_DEBUG_HIGHMEM
-	{
-		int idx = type + KM_TYPE_NR * smp_processor_id();
-
-		BUG_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
-
-		/*
-		 * force other mappings to Oops if they'll try to access
-		 * this pte without first remap it
-		 */
-		pte_clear(&init_mm, vaddr, kmap_pte-idx);
-		local_flush_tlb_one(vaddr);
-	}
-#endif
-	kmap_atomic_idx_pop();
-}
-EXPORT_SYMBOL(kunmap_atomic_high);
-
-/*
- * This is the same as kmap_atomic() but can map memory that doesn't
- * have a struct page associated with it.
- */
-void *kmap_atomic_pfn(unsigned long pfn)
-{
-	unsigned long vaddr;
-	int idx, type;
-
-	preempt_disable();
-	pagefault_disable();
-
-	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, PAGE_KERNEL));
-	flush_tlb_one(vaddr);
-
-	return (void*) vaddr;
-}
-
-void __init kmap_init(void)
-{
-	unsigned long kmap_vstart;
-
-	/* cache the first kmap pte */
-	kmap_vstart = __fix_to_virt(FIX_KMAP_BEGIN);
-	kmap_pte = virt_to_kpte(kmap_vstart);
-}
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 07e84a7749387..bc80893e5c0f8 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -36,7 +36,6 @@
 #include <asm/cachectl.h>
 #include <asm/cpu.h>
 #include <asm/dma.h>
-#include <asm/kmap_types.h>
 #include <asm/maar.h>
 #include <asm/mmu_context.h>
 #include <asm/sections.h>
@@ -402,9 +401,6 @@ void __init paging_init(void)
 
 	pagetable_init();
 
-#ifdef CONFIG_HIGHMEM
-	kmap_init();
-#endif
 #ifdef CONFIG_ZONE_DMA
 	max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
 #endif
diff --git a/arch/nds32/Kconfig.cpu b/arch/nds32/Kconfig.cpu
index f88a12fdf0f35..c107599524855 100644
--- a/arch/nds32/Kconfig.cpu
+++ b/arch/nds32/Kconfig.cpu
@@ -157,6 +157,7 @@ config HW_SUPPORT_UNALIGNMENT_ACCESS
 config HIGHMEM
 	bool "High Memory Support"
 	depends on MMU && !CPU_CACHE_ALIASING
+	select KMAP_LOCAL
 	help
 	  The address space of Andes processors is only 4 Gigabytes large
 	  and it has to accommodate user address space, kernel address
diff --git a/arch/nds32/include/asm/fixmap.h b/arch/nds32/include/asm/fixmap.h
index 5a4bf11e58003..2fa09a2de4281 100644
--- a/arch/nds32/include/asm/fixmap.h
+++ b/arch/nds32/include/asm/fixmap.h
@@ -6,7 +6,7 @@
 
 #ifdef CONFIG_HIGHMEM
 #include <linux/threads.h>
-#include <asm/kmap_types.h>
+#include <asm/kmap_size.h>
 #endif
 
 enum fixed_addresses {
@@ -14,7 +14,7 @@ enum fixed_addresses {
 	FIX_KMAP_RESERVED,
 	FIX_KMAP_BEGIN,
 #ifdef CONFIG_HIGHMEM
-	FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_TYPE_NR * NR_CPUS),
+	FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_MAX_IDX * NR_CPUS) - 1,
 #endif
 	FIX_EARLYCON_MEM_BASE,
 	__end_of_fixed_addresses
diff --git a/arch/nds32/include/asm/highmem.h b/arch/nds32/include/asm/highmem.h
index fe986d0e6e3ff..16159a8716f22 100644
--- a/arch/nds32/include/asm/highmem.h
+++ b/arch/nds32/include/asm/highmem.h
@@ -5,7 +5,6 @@
 #define _ASM_HIGHMEM_H
 
 #include <asm/proc-fns.h>
-#include <asm/kmap_types.h>
 #include <asm/fixmap.h>
 
 /*
@@ -45,11 +44,22 @@ extern pte_t *pkmap_page_table;
 extern void kmap_init(void);
 
 /*
- * The following functions are already defined by <linux/highmem.h>
- * when CONFIG_HIGHMEM is not set.
+ * FIXME: The below looks broken vs. a kmap_atomic() in task context which
+ * is interupted and another kmap_atomic() happens in interrupt context.
+ * But what do I know about nds32. -- tglx
  */
-#ifdef CONFIG_HIGHMEM
-extern void *kmap_atomic_pfn(unsigned long pfn);
-#endif
+#define arch_kmap_local_post_map(vaddr, pteval)			\
+	do {							\
+		__nds32__tlbop_inv(vaddr);			\
+		__nds32__mtsr_dsb(vaddr, NDS32_SR_TLB_VPN);	\
+		__nds32__tlbop_rwr(pteval);			\
+		__nds32__isb();					\
+	} while (0)
+
+#define arch_kmap_local_pre_unmap(vaddr)			\
+	do {							\
+		__nds32__tlbop_inv(vaddr);			\
+		__nds32__isb();					\
+	} while (0)
 
 #endif
diff --git a/arch/nds32/mm/Makefile b/arch/nds32/mm/Makefile
index 897ecaf5cf54b..14fb2e8eb0368 100644
--- a/arch/nds32/mm/Makefile
+++ b/arch/nds32/mm/Makefile
@@ -3,7 +3,6 @@ obj-y				:= extable.o tlb.o fault.o init.o mmap.o \
                                    mm-nds32.o cacheflush.o proc.o
 
 obj-$(CONFIG_ALIGNMENT_TRAP)	+= alignment.o
-obj-$(CONFIG_HIGHMEM)           += highmem.o
 
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_proc.o     = $(CC_FLAGS_FTRACE)
diff --git a/arch/nds32/mm/highmem.c b/arch/nds32/mm/highmem.c
deleted file mode 100644
index 4284cd59e21ad..0000000000000
--- a/arch/nds32/mm/highmem.c
+++ /dev/null
@@ -1,48 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-// Copyright (C) 2005-2017 Andes Technology Corporation
-
-#include <linux/export.h>
-#include <linux/highmem.h>
-#include <linux/sched.h>
-#include <linux/smp.h>
-#include <linux/interrupt.h>
-#include <linux/memblock.h>
-#include <asm/fixmap.h>
-#include <asm/tlbflush.h>
-
-void *kmap_atomic_high_prot(struct page *page, pgprot_t prot)
-{
-	unsigned int idx;
-	unsigned long vaddr, pte;
-	int type;
-	pte_t *ptep;
-
-	type = kmap_atomic_idx_push();
-
-	idx = type + KM_TYPE_NR * smp_processor_id();
-	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-	pte = (page_to_pfn(page) << PAGE_SHIFT) | prot;
-	ptep = pte_offset_kernel(pmd_off_k(vaddr), vaddr);
-	set_pte(ptep, pte);
-
-	__nds32__tlbop_inv(vaddr);
-	__nds32__mtsr_dsb(vaddr, NDS32_SR_TLB_VPN);
-	__nds32__tlbop_rwr(pte);
-	__nds32__isb();
-	return (void *)vaddr;
-}
-EXPORT_SYMBOL(kmap_atomic_high_prot);
-
-void kunmap_atomic_high(void *kvaddr)
-{
-	if (kvaddr >= (void *)FIXADDR_START) {
-		unsigned long vaddr = (unsigned long)kvaddr;
-		pte_t *ptep;
-		kmap_atomic_idx_pop();
-		__nds32__tlbop_inv(vaddr);
-		__nds32__isb();
-		ptep = pte_offset_kernel(pmd_off_k(vaddr), vaddr);
-		set_pte(ptep, 0);
-	}
-}
-EXPORT_SYMBOL(kunmap_atomic_high);
diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c
index 5e88c351e6a45..f3fa02b8838af 100644
--- a/arch/openrisc/mm/init.c
+++ b/arch/openrisc/mm/init.c
@@ -33,7 +33,6 @@
 #include <asm/io.h>
 #include <asm/tlb.h>
 #include <asm/mmu_context.h>
-#include <asm/kmap_types.h>
 #include <asm/fixmap.h>
 #include <asm/tlbflush.h>
 #include <asm/sections.h>
diff --git a/arch/openrisc/mm/ioremap.c b/arch/openrisc/mm/ioremap.c
index a978590d802d0..5aed97a18bac9 100644
--- a/arch/openrisc/mm/ioremap.c
+++ b/arch/openrisc/mm/ioremap.c
@@ -15,7 +15,6 @@
 #include <linux/io.h>
 #include <linux/pgtable.h>
 #include <asm/pgalloc.h>
-#include <asm/kmap_types.h>
 #include <asm/fixmap.h>
 #include <asm/bug.h>
 #include <linux/sched.h>
diff --git a/arch/parisc/include/asm/hardirq.h b/arch/parisc/include/asm/hardirq.h
index 7f7039516e53f..fad29aa6f45fa 100644
--- a/arch/parisc/include/asm/hardirq.h
+++ b/arch/parisc/include/asm/hardirq.h
@@ -32,7 +32,6 @@ typedef struct {
 DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
 
 #define __ARCH_IRQ_STAT
-#define __IRQ_STAT(cpu, member) (irq_stat[cpu].member)
 #define inc_irq_stat(member)	this_cpu_inc(irq_stat.member)
 #define __inc_irq_stat(member)	__this_cpu_inc(irq_stat.member)
 #define ack_bad_irq(irq) WARN(1, "unexpected IRQ trap at vector %02x\n", irq)
diff --git a/arch/parisc/include/asm/kmap_types.h b/arch/parisc/include/asm/kmap_types.h
deleted file mode 100644
index 3e70b5cd11231..0000000000000
--- a/arch/parisc/include/asm/kmap_types.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_KMAP_TYPES_H
-#define _ASM_KMAP_TYPES_H
-
-#ifdef CONFIG_DEBUG_HIGHMEM
-#define  __WITH_KM_FENCE
-#endif
-
-#include <asm-generic/kmap_types.h>
-
-#undef __WITH_KM_FENCE
-
-#endif
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 5afa0ebd78ca5..1d3e6f351bf2f 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -146,6 +146,7 @@ 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 if HAVE_POSIX_CPU_TIMERS_TASK_WORK
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF		if PPC64
 	select ARCH_USE_QUEUED_RWLOCKS		if PPC_QUEUED_SPINLOCKS
@@ -230,6 +231,7 @@ 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 MMU_GATHER_RCU_TABLE_FREE
 	select MMU_GATHER_PAGE_SIZE
 	select HAVE_REGS_AND_STACK_ACCESS_API
@@ -237,6 +239,7 @@ config PPC
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_VIRT_CPU_ACCOUNTING
 	select HAVE_IRQ_TIME_ACCOUNTING
+	select HAVE_POSIX_CPU_TIMERS_TASK_WORK  if !KVM
 	select HAVE_RSEQ
 	select IOMMU_HELPER			if PPC64
 	select IRQ_DOMAIN
@@ -410,6 +413,7 @@ menu "Kernel options"
 config HIGHMEM
 	bool "High memory support"
 	depends on PPC32
+	select KMAP_LOCAL
 
 source "kernel/Kconfig.hz"
 
diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h
index cf091c4c22e53..7371f7e23c357 100644
--- a/arch/powerpc/include/asm/cmpxchg.h
+++ b/arch/powerpc/include/asm/cmpxchg.h
@@ -5,7 +5,7 @@
 #ifdef __KERNEL__
 #include <linux/compiler.h>
 #include <asm/synch.h>
-#include <linux/bug.h>
+#include <linux/bits.h>
 
 #ifdef __BIG_ENDIAN
 #define BITOFF_CAL(size, off)	((sizeof(u32) - size - off) * BITS_PER_BYTE)
diff --git a/arch/powerpc/include/asm/fixmap.h b/arch/powerpc/include/asm/fixmap.h
index 591b2f4deed53..947b5b9c44241 100644
--- a/arch/powerpc/include/asm/fixmap.h
+++ b/arch/powerpc/include/asm/fixmap.h
@@ -20,7 +20,7 @@
 #include <asm/page.h>
 #ifdef CONFIG_HIGHMEM
 #include <linux/threads.h>
-#include <asm/kmap_types.h>
+#include <asm/kmap_size.h>
 #endif
 
 #ifdef CONFIG_PPC64
@@ -61,7 +61,7 @@ enum fixed_addresses {
 	FIX_EARLY_DEBUG_BASE = FIX_EARLY_DEBUG_TOP+(ALIGN(SZ_128K, PAGE_SIZE)/PAGE_SIZE)-1,
 #ifdef CONFIG_HIGHMEM
 	FIX_KMAP_BEGIN,	/* reserved pte's for temporary kernel mappings */
-	FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
+	FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_MAX_IDX * NR_CPUS) - 1,
 #endif
 #ifdef CONFIG_PPC_8xx
 	/* For IMMR we need an aligned 512K area */
diff --git a/arch/powerpc/include/asm/highmem.h b/arch/powerpc/include/asm/highmem.h
index 104026f7d6bc2..80a5ae771c653 100644
--- a/arch/powerpc/include/asm/highmem.h
+++ b/arch/powerpc/include/asm/highmem.h
@@ -24,12 +24,10 @@
 #ifdef __KERNEL__
 
 #include <linux/interrupt.h>
-#include <asm/kmap_types.h>
 #include <asm/cacheflush.h>
 #include <asm/page.h>
 #include <asm/fixmap.h>
 
-extern pte_t *kmap_pte;
 extern pte_t *pkmap_page_table;
 
 /*
@@ -60,6 +58,11 @@ extern pte_t *pkmap_page_table;
 
 #define flush_cache_kmaps()	flush_cache_all()
 
+#define arch_kmap_local_post_map(vaddr, pteval)	\
+	local_flush_tlb_page(NULL, vaddr)
+#define arch_kmap_local_post_unmap(vaddr)	\
+	local_flush_tlb_page(NULL, vaddr)
+
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_HIGHMEM_H */
diff --git a/arch/powerpc/include/asm/kmap_types.h b/arch/powerpc/include/asm/kmap_types.h
deleted file mode 100644
index c8fa182d48c8e..0000000000000
--- a/arch/powerpc/include/asm/kmap_types.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-#ifndef _ASM_POWERPC_KMAP_TYPES_H
-#define _ASM_POWERPC_KMAP_TYPES_H
-
-#ifdef __KERNEL__
-
-/*
- */
-
-#define KM_TYPE_NR 16
-
-#endif	/* __KERNEL__ */
-#endif	/* _ASM_POWERPC_KMAP_TYPES_H */
diff --git a/arch/powerpc/include/asm/simple_spinlock_types.h b/arch/powerpc/include/asm/simple_spinlock_types.h
index 0f3cdd8faa959..d45561e9e6bab 100644
--- a/arch/powerpc/include/asm/simple_spinlock_types.h
+++ b/arch/powerpc/include/asm/simple_spinlock_types.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_POWERPC_SIMPLE_SPINLOCK_TYPES_H
 #define _ASM_POWERPC_SIMPLE_SPINLOCK_TYPES_H
 
-#ifndef __LINUX_SPINLOCK_TYPES_H
+#if !defined(__LINUX_SPINLOCK_TYPES_H) && !defined(__LINUX_RT_MUTEX_H)
 # error "please don't include this file directly"
 #endif
 
diff --git a/arch/powerpc/include/asm/spinlock_types.h b/arch/powerpc/include/asm/spinlock_types.h
index c5d742f18021d..cc6922a011ba1 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
-
 #ifdef CONFIG_PPC_QUEUED_SPINLOCKS
 #include <asm-generic/qspinlock_types.h>
 #include <asm-generic/qrwlock_types.h>
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 46a210b03d2b8..0e316b44b2d73 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -48,6 +48,8 @@
 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;
@@ -97,11 +99,12 @@ 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 */
@@ -110,6 +113,9 @@ 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)
@@ -129,6 +135,7 @@ 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_SYSCALL_EMU	(1<<TIF_SYSCALL_EMU)
 #define _TIF_SYSCALL_DOTRACE	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
 				 _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \
@@ -136,8 +143,10 @@ 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_RESTORE_TM | _TIF_PATCH_PENDING | \
+				 _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 5c125255571cd..597379121407a 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -189,6 +189,7 @@ 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 459f5d00b9904..fc9517a976407 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -414,7 +414,9 @@ ret_from_syscall:
 	mtmsr	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
@@ -530,13 +532,13 @@ syscall_dotrace:
 	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
@@ -545,12 +547,12 @@ syscall_exit_work:
 
 1:	stw	r6,RESULT(r1)	/* Save result */
 	stw	r3,GPR3(r1)	/* Update return value */
-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,r2,TI_FLAGS
 3:	lwarx	r8,0,r12
 	andc	r8,r8,r11
@@ -927,7 +929,14 @@ resume_kernel:
 	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 */
@@ -1248,7 +1257,7 @@ global_dbcr0:
 #endif /* !(CONFIG_4xx || CONFIG_BOOKE) */
 
 do_work:			/* r10 contains MSR_KERNEL here */
-	andi.	r0,r9,_TIF_NEED_RESCHED
+	andi.	r0,r9,_TIF_NEED_RESCHED_MASK
 	beq	do_user_signal
 
 do_resched:			/* r10 contains MSR_KERNEL here */
@@ -1267,7 +1276,7 @@ recheck:
 	LOAD_REG_IMMEDIATE(r10,MSR_KERNEL)
 	mtmsr	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/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S
index f579ce46eef2d..715ff292a8f8a 100644
--- a/arch/powerpc/kernel/exceptions-64e.S
+++ b/arch/powerpc/kernel/exceptions-64e.S
@@ -1080,7 +1080,7 @@ _GLOBAL(ret_from_except_lite)
 	li	r10, -1
 	mtspr	SPRN_DBSR,r10
 	b	restore
-1:	andi.	r0,r4,_TIF_NEED_RESCHED
+1:	andi.	r0,r4,_TIF_NEED_RESCHED_MASK
 	beq	2f
 	bl	restore_interrupts
 	SCHEDULE_USER
@@ -1132,12 +1132,20 @@ resume_kernel:
 	bne-	0b
 1:
 
-#ifdef CONFIG_PREEMPT
+#ifdef CONFIG_PREEMPTION
 	/* Check if we need to preempt */
+	lwz	r8,TI_PREEMPT(r9)
+	cmpwi	0,r8,0		/* if non-zero, just restore regs and return */
+	bne	restore
 	andi.	r0,r4,_TIF_NEED_RESCHED
+	bne+	check_count
+
+	andi.	r0,r4,_TIF_NEED_RESCHED_LAZY
 	beq+	restore
+	lwz	r8,TI_PREEMPT_LAZY(r9)
+
 	/* Check that preempt_count() == 0 and interrupts are enabled */
-	lwz	r8,TI_PREEMPT(r9)
+check_count:
 	cmpwi	cr0,r8,0
 	bne	restore
 	ld	r0,SOFTE(r1)
@@ -1158,7 +1166,7 @@ resume_kernel:
 	 * interrupted after loading SRR0/1.
 	 */
 	wrteei	0
-#endif /* CONFIG_PREEMPT */
+#endif /* CONFIG_PREEMPTION */
 
 restore:
 	/*
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index e8a548447dd68..5ad4f27cba104 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -753,10 +753,12 @@ 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 717e658b90fd8..08ee95ad6593a 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -31,6 +31,7 @@
  * 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)
@@ -46,6 +47,7 @@ _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 070465825c210..a6b33f7b32646 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/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index 532f226377831..1ef55f4b389a2 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -73,7 +73,8 @@ static const char *nvram_os_partitions[] = {
 };
 
 static void oops_to_nvram(struct kmsg_dumper *dumper,
-			  enum kmsg_dump_reason reason);
+			  enum kmsg_dump_reason reason,
+			  struct kmsg_dumper_iter *iter);
 
 static struct kmsg_dumper nvram_kmsg_dumper = {
 	.dump = oops_to_nvram
@@ -643,7 +644,8 @@ void __init nvram_init_oops_partition(int rtas_partition_exists)
  * partition.  If that's too much, go back and capture uncompressed text.
  */
 static void oops_to_nvram(struct kmsg_dumper *dumper,
-			  enum kmsg_dump_reason reason)
+			  enum kmsg_dump_reason reason,
+			  struct kmsg_dumper_iter *iter)
 {
 	struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf;
 	static unsigned int oops_count = 0;
@@ -681,13 +683,13 @@ static void oops_to_nvram(struct kmsg_dumper *dumper,
 		return;
 
 	if (big_oops_buf) {
-		kmsg_dump_get_buffer(dumper, false,
+		kmsg_dump_get_buffer(iter, false,
 				     big_oops_buf, big_oops_buf_sz, &text_len);
 		rc = zip_oops(text_len);
 	}
 	if (rc != 0) {
-		kmsg_dump_rewind(dumper);
-		kmsg_dump_get_buffer(dumper, false,
+		kmsg_dump_rewind(iter);
+		kmsg_dump_get_buffer(iter, false,
 				     oops_data, oops_data_sz, &text_len);
 		err_type = ERR_TYPE_KERNEL_PANIC;
 		oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
diff --git a/arch/powerpc/kernel/syscall_64.c b/arch/powerpc/kernel/syscall_64.c
index 310bcd768cd5a..ae3212dcf5627 100644
--- a/arch/powerpc/kernel/syscall_64.c
+++ b/arch/powerpc/kernel/syscall_64.c
@@ -193,7 +193,7 @@ notrace unsigned long syscall_exit_prepare(unsigned long r3,
 	ti_flags = READ_ONCE(*ti_flagsp);
 	while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) {
 		local_irq_enable();
-		if (ti_flags & _TIF_NEED_RESCHED) {
+		if (ti_flags & _TIF_NEED_RESCHED_MASK) {
 			schedule();
 		} else {
 			/*
@@ -277,7 +277,7 @@ notrace unsigned long interrupt_exit_user_prepare(struct pt_regs *regs, unsigned
 	ti_flags = READ_ONCE(*ti_flagsp);
 	while (unlikely(ti_flags & (_TIF_USER_WORK_MASK & ~_TIF_RESTORE_TM))) {
 		local_irq_enable(); /* returning to user: may enable */
-		if (ti_flags & _TIF_NEED_RESCHED) {
+		if (ti_flags & _TIF_NEED_RESCHED_MASK) {
 			schedule();
 		} else {
 			if (ti_flags & _TIF_SIGPENDING)
@@ -361,11 +361,15 @@ notrace unsigned long interrupt_exit_kernel_prepare(struct pt_regs *regs, unsign
 		/* Returning to a kernel context with local irqs enabled. */
 		WARN_ON_ONCE(!(regs->msr & MSR_EE));
 again:
-		if (IS_ENABLED(CONFIG_PREEMPT)) {
+		if (IS_ENABLED(CONFIG_PREEMPTION)) {
 			/* Return to preemptible kernel context */
 			if (unlikely(*ti_flagsp & _TIF_NEED_RESCHED)) {
 				if (preempt_count() == 0)
 					preempt_schedule_irq();
+			} else if (unlikely(*ti_flagsp & _TIF_NEED_RESCHED_LAZY)) {
+				if ((preempt_count() == 0) &&
+				    (current_thread_info()->preempt_lazy_count == 0))
+					preempt_schedule_irq();
 			}
 		}
 
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 1d20f0f77a920..7e0a497a36ee3 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -312,12 +312,11 @@ static unsigned long vtime_delta_scaled(struct cpu_accounting_data *acct,
 	return stime_scaled;
 }
 
-static unsigned long vtime_delta(struct task_struct *tsk,
+static unsigned long vtime_delta(struct cpu_accounting_data *acct,
 				 unsigned long *stime_scaled,
 				 unsigned long *steal_time)
 {
 	unsigned long now, stime;
-	struct cpu_accounting_data *acct = get_accounting(tsk);
 
 	WARN_ON_ONCE(!irqs_disabled());
 
@@ -332,29 +331,30 @@ static unsigned long vtime_delta(struct task_struct *tsk,
 	return stime;
 }
 
+static void vtime_delta_kernel(struct cpu_accounting_data *acct,
+			       unsigned long *stime, unsigned long *stime_scaled)
+{
+	unsigned long steal_time;
+
+	*stime = vtime_delta(acct, stime_scaled, &steal_time);
+	*stime -= min(*stime, steal_time);
+	acct->steal_time += steal_time;
+}
+
 void vtime_account_kernel(struct task_struct *tsk)
 {
-	unsigned long stime, stime_scaled, steal_time;
 	struct cpu_accounting_data *acct = get_accounting(tsk);
+	unsigned long stime, stime_scaled;
 
-	stime = vtime_delta(tsk, &stime_scaled, &steal_time);
-
-	stime -= min(stime, steal_time);
-	acct->steal_time += steal_time;
+	vtime_delta_kernel(acct, &stime, &stime_scaled);
 
-	if ((tsk->flags & PF_VCPU) && !irq_count()) {
+	if (tsk->flags & PF_VCPU) {
 		acct->gtime += stime;
 #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
 		acct->utime_scaled += stime_scaled;
 #endif
 	} else {
-		if (hardirq_count())
-			acct->hardirq_time += stime;
-		else if (in_serving_softirq())
-			acct->softirq_time += stime;
-		else
-			acct->stime += stime;
-
+		acct->stime += stime;
 #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
 		acct->stime_scaled += stime_scaled;
 #endif
@@ -367,10 +367,34 @@ void vtime_account_idle(struct task_struct *tsk)
 	unsigned long stime, stime_scaled, steal_time;
 	struct cpu_accounting_data *acct = get_accounting(tsk);
 
-	stime = vtime_delta(tsk, &stime_scaled, &steal_time);
+	stime = vtime_delta(acct, &stime_scaled, &steal_time);
 	acct->idle_time += stime + steal_time;
 }
 
+static void vtime_account_irq_field(struct cpu_accounting_data *acct,
+				    unsigned long *field)
+{
+	unsigned long stime, stime_scaled;
+
+	vtime_delta_kernel(acct, &stime, &stime_scaled);
+	*field += stime;
+#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME
+	acct->stime_scaled += stime_scaled;
+#endif
+}
+
+void vtime_account_softirq(struct task_struct *tsk)
+{
+	struct cpu_accounting_data *acct = get_accounting(tsk);
+	vtime_account_irq_field(acct, &acct->softirq_time);
+}
+
+void vtime_account_hardirq(struct task_struct *tsk)
+{
+	struct cpu_accounting_data *acct = get_accounting(tsk);
+	vtime_account_irq_field(acct, &acct->hardirq_time);
+}
+
 static void vtime_flush_scaled(struct task_struct *tsk,
 			       struct cpu_accounting_data *acct)
 {
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 77dffea3d5373..34861e39d03a4 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -170,7 +170,6 @@ 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();
@@ -260,12 +259,17 @@ static char *get_mmu_str(void)
 
 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\n",
 	       IS_ENABLED(CONFIG_CPU_LITTLE_ENDIAN) ? "LE" : "BE",
 	       PAGE_SIZE / 1024, get_mmu_str(),
-	       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/kexec/crash.c b/arch/powerpc/kexec/crash.c
index c9a889880214e..d488311efab1f 100644
--- a/arch/powerpc/kexec/crash.c
+++ b/arch/powerpc/kexec/crash.c
@@ -311,9 +311,6 @@ void default_machine_crash_shutdown(struct pt_regs *regs)
 	unsigned int i;
 	int (*old_handler)(struct pt_regs *regs);
 
-	/* Avoid hardlocking with irresponsive CPU holding logbuf_lock */
-	printk_nmi_enter();
-
 	/*
 	 * This function is only called after the system
 	 * has panicked or is otherwise in a critical state.
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 549591d9aaa2c..efb5bfe93f705 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/mm/Makefile b/arch/powerpc/mm/Makefile
index 55b4a8bd408ab..3b4e9e4e25eaa 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -16,7 +16,6 @@ obj-$(CONFIG_NEED_MULTIPLE_NODES) += numa.o
 obj-$(CONFIG_PPC_MM_SLICES)	+= slice.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o
-obj-$(CONFIG_HIGHMEM)		+= highmem.o
 obj-$(CONFIG_PPC_COPRO_BASE)	+= copro_fault.o
 obj-$(CONFIG_PPC_PTDUMP)	+= ptdump/
 obj-$(CONFIG_KASAN)		+= kasan/
diff --git a/arch/powerpc/mm/highmem.c b/arch/powerpc/mm/highmem.c
deleted file mode 100644
index 624b4438aff9d..0000000000000
--- a/arch/powerpc/mm/highmem.c
+++ /dev/null
@@ -1,67 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * highmem.c: virtual kernel memory mappings for high memory
- *
- * PowerPC version, stolen from the i386 version.
- *
- * Used in CONFIG_HIGHMEM systems for memory pages which
- * are not addressable by direct kernel virtual addresses.
- *
- * Copyright (C) 1999 Gerhard Wichert, Siemens AG
- *		      Gerhard.Wichert@pdb.siemens.de
- *
- *
- * Redesigned the x86 32-bit VM architecture to deal with
- * up to 16 Terrabyte physical memory. With current x86 CPUs
- * we now support up to 64 Gigabytes physical RAM.
- *
- * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
- *
- * Reworked for PowerPC by various contributors. Moved from
- * highmem.h by Benjamin Herrenschmidt (c) 2009 IBM Corp.
- */
-
-#include <linux/highmem.h>
-#include <linux/module.h>
-
-void *kmap_atomic_high_prot(struct page *page, pgprot_t prot)
-{
-	unsigned long vaddr;
-	int idx, type;
-
-	type = kmap_atomic_idx_push();
-	idx = type + KM_TYPE_NR*smp_processor_id();
-	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-	WARN_ON(IS_ENABLED(CONFIG_DEBUG_HIGHMEM) && !pte_none(*(kmap_pte - idx)));
-	__set_pte_at(&init_mm, vaddr, kmap_pte-idx, mk_pte(page, prot), 1);
-	local_flush_tlb_page(NULL, vaddr);
-
-	return (void*) vaddr;
-}
-EXPORT_SYMBOL(kmap_atomic_high_prot);
-
-void kunmap_atomic_high(void *kvaddr)
-{
-	unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
-
-	if (vaddr < __fix_to_virt(FIX_KMAP_END))
-		return;
-
-	if (IS_ENABLED(CONFIG_DEBUG_HIGHMEM)) {
-		int type = kmap_atomic_idx();
-		unsigned int idx;
-
-		idx = type + KM_TYPE_NR * smp_processor_id();
-		WARN_ON(vaddr != __fix_to_virt(FIX_KMAP_BEGIN + idx));
-
-		/*
-		 * force other mappings to Oops if they'll try to access
-		 * this pte without first remap it
-		 */
-		pte_clear(&init_mm, vaddr, kmap_pte-idx);
-		local_flush_tlb_page(NULL, vaddr);
-	}
-
-	kmap_atomic_idx_pop();
-}
-EXPORT_SYMBOL(kunmap_atomic_high);
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 22eb1c718e622..1b74565b3e168 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -62,11 +62,6 @@
 unsigned long long memory_limit;
 bool init_mem_is_free;
 
-#ifdef CONFIG_HIGHMEM
-pte_t *kmap_pte;
-EXPORT_SYMBOL(kmap_pte);
-#endif
-
 pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 			      unsigned long size, pgprot_t vma_prot)
 {
@@ -236,8 +231,6 @@ void __init paging_init(void)
 
 	map_kernel_page(PKMAP_BASE, 0, __pgprot(0));	/* XXX gross */
 	pkmap_page_table = virt_to_kpte(PKMAP_BASE);
-
-	kmap_pte = virt_to_kpte(__fix_to_virt(FIX_KMAP_BEGIN));
 #endif /* CONFIG_HIGHMEM */
 
 	printk(KERN_DEBUG "Top of RAM: 0x%llx, Total RAM: 0x%llx\n",
diff --git a/arch/powerpc/platforms/powernv/opal-kmsg.c b/arch/powerpc/platforms/powernv/opal-kmsg.c
index 6c3bc4b4da983..ec862846bc82c 100644
--- a/arch/powerpc/platforms/powernv/opal-kmsg.c
+++ b/arch/powerpc/platforms/powernv/opal-kmsg.c
@@ -20,7 +20,8 @@
  * message, it just ensures that OPAL completely flushes the console buffer.
  */
 static void kmsg_dump_opal_console_flush(struct kmsg_dumper *dumper,
-				     enum kmsg_dump_reason reason)
+					 enum kmsg_dump_reason reason,
+					 struct kmsg_dumper_iter *iter)
 {
 	/*
 	 * Outside of a panic context the pollers will continue to run,
diff --git a/arch/powerpc/platforms/pseries/iommu.c b/arch/powerpc/platforms/pseries/iommu.c
index 245f1f8df6563..f05555dde8e7f 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/local_lock.h>
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/rtas.h>
@@ -190,7 +191,13 @@ static int tce_build_pSeriesLP(unsigned long liobn, long tcenum, long tceshift,
 	return ret;
 }
 
-static DEFINE_PER_CPU(__be64 *, tce_page);
+struct tce_page {
+	__be64 * page;
+	local_lock_t lock;
+};
+static DEFINE_PER_CPU(struct tce_page, tce_page) = {
+	.lock = INIT_LOCAL_LOCK(lock),
+};
 
 static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 				     long npages, unsigned long uaddr,
@@ -212,9 +219,10 @@ 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(&tce_page.lock, flags);
 
-	tcep = __this_cpu_read(tce_page);
+	tcep = __this_cpu_read(tce_page.page);
 
 	/* This is safe to do since interrupts are off when we're called
 	 * from iommu_alloc{,_sg}()
@@ -223,12 +231,12 @@ 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(&tce_page.lock, flags);
 			return tce_build_pSeriesLP(tbl->it_index, tcenum,
 					tbl->it_page_shift,
 					npages, uaddr, direction, attrs);
 		}
-		__this_cpu_write(tce_page, tcep);
+		__this_cpu_write(tce_page.page, tcep);
 	}
 
 	rpn = __pa(uaddr) >> TCE_SHIFT;
@@ -258,7 +266,7 @@ static int tce_buildmulti_pSeriesLP(struct iommu_table *tbl, long tcenum,
 		tcenum += limit;
 	} while (npages > 0 && !rc);
 
-	local_irq_restore(flags);
+	local_unlock_irqrestore(&tce_page.lock, flags);
 
 	if (unlikely(rc == H_NOT_ENOUGH_RESOURCES)) {
 		ret = (int)rc;
@@ -429,16 +437,17 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn,
 				DMA_BIDIRECTIONAL, 0);
 	}
 
-	local_irq_disable();	/* to protect tcep and the page behind it */
-	tcep = __this_cpu_read(tce_page);
+	/* to protect tcep and the page behind it */
+	local_lock_irq(&tce_page.lock);
+	tcep = __this_cpu_read(tce_page.page);
 
 	if (!tcep) {
 		tcep = (__be64 *)__get_free_page(GFP_ATOMIC);
 		if (!tcep) {
-			local_irq_enable();
+			local_unlock_irq(&tce_page.lock);
 			return -ENOMEM;
 		}
-		__this_cpu_write(tce_page, tcep);
+		__this_cpu_write(tce_page.page, tcep);
 	}
 
 	proto_tce = TCE_PCI_READ | TCE_PCI_WRITE;
@@ -481,7 +490,7 @@ static int tce_setrange_multi_pSeriesLP(unsigned long start_pfn,
 
 	/* error cleanup: caller will clear whole range */
 
-	local_irq_enable();
+	local_unlock_irq(&tce_page.lock);
 	return rc;
 }
 
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 5559edf36756c..d62b8e053d4c8 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -3005,7 +3005,7 @@ print_address(unsigned long addr)
 static void
 dump_log_buf(void)
 {
-	struct kmsg_dumper dumper = { .active = 1 };
+	struct kmsg_dumper_iter iter = { .active = 1 };
 	unsigned char buf[128];
 	size_t len;
 
@@ -3017,9 +3017,9 @@ dump_log_buf(void)
 	catch_memory_errors = 1;
 	sync();
 
-	kmsg_dump_rewind_nolock(&dumper);
+	kmsg_dump_rewind(&iter);
 	xmon_start_pagination();
-	while (kmsg_dump_get_line_nolock(&dumper, false, buf, sizeof(buf), &len)) {
+	while (kmsg_dump_get_line(&iter, false, buf, sizeof(buf), &len)) {
 		buf[len] = '\0';
 		printf("%s", buf);
 	}
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 896b68e541b2e..54a4e77f2d2a3 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -183,6 +183,7 @@ config S390
 	select HAVE_RSEQ
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_VIRT_CPU_ACCOUNTING
+	select HAVE_VIRT_CPU_ACCOUNTING_IDLE
 	select IOMMU_HELPER		if PCI
 	select IOMMU_SUPPORT		if PCI
 	select MODULES_USE_ELF_RELA
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/include/asm/vtime.h b/arch/s390/include/asm/vtime.h
index 3622d4ebc73aa..fac6a67988eb5 100644
--- a/arch/s390/include/asm/vtime.h
+++ b/arch/s390/include/asm/vtime.h
@@ -2,7 +2,6 @@
 #ifndef _S390_VTIME_H
 #define _S390_VTIME_H
 
-#define __ARCH_HAS_VTIME_ACCOUNT
 #define __ARCH_HAS_VTIME_TASK_SWITCH
 
 #endif /* _S390_VTIME_H */
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 579ec3a8c816f..9b3c5978b6683 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -223,35 +223,50 @@ void vtime_flush(struct task_struct *tsk)
 	S390_lowcore.avg_steal_timer = avg_steal;
 }
 
+static u64 vtime_delta(void)
+{
+	u64 timer = S390_lowcore.last_update_timer;
+
+	S390_lowcore.last_update_timer = get_vtimer();
+
+	return timer - S390_lowcore.last_update_timer;
+}
+
 /*
  * Update process times based on virtual cpu times stored by entry.S
  * to the lowcore fields user_timer, system_timer & steal_clock.
  */
-void vtime_account_irq_enter(struct task_struct *tsk)
+void vtime_account_kernel(struct task_struct *tsk)
 {
-	u64 timer;
-
-	timer = S390_lowcore.last_update_timer;
-	S390_lowcore.last_update_timer = get_vtimer();
-	timer -= S390_lowcore.last_update_timer;
+	u64 delta = vtime_delta();
 
-	if ((tsk->flags & PF_VCPU) && (irq_count() == 0))
-		S390_lowcore.guest_timer += timer;
-	else if (hardirq_count())
-		S390_lowcore.hardirq_timer += timer;
-	else if (in_serving_softirq())
-		S390_lowcore.softirq_timer += timer;
+	if (tsk->flags & PF_VCPU)
+		S390_lowcore.guest_timer += delta;
 	else
-		S390_lowcore.system_timer += timer;
+		S390_lowcore.system_timer += delta;
 
-	virt_timer_forward(timer);
+	virt_timer_forward(delta);
 }
-EXPORT_SYMBOL_GPL(vtime_account_irq_enter);
-
-void vtime_account_kernel(struct task_struct *tsk)
-__attribute__((alias("vtime_account_irq_enter")));
 EXPORT_SYMBOL_GPL(vtime_account_kernel);
 
+void vtime_account_softirq(struct task_struct *tsk)
+{
+	u64 delta = vtime_delta();
+
+	S390_lowcore.softirq_timer += delta;
+
+	virt_timer_forward(delta);
+}
+
+void vtime_account_hardirq(struct task_struct *tsk)
+{
+	u64 delta = vtime_delta();
+
+	S390_lowcore.hardirq_timer += delta;
+
+	virt_timer_forward(delta);
+}
+
 /*
  * Sorted add to a list. List is linear searched until first bigger
  * element is found.
diff --git a/arch/sh/include/asm/fixmap.h b/arch/sh/include/asm/fixmap.h
index f38adc189b832..b07fbc7f7bc6a 100644
--- a/arch/sh/include/asm/fixmap.h
+++ b/arch/sh/include/asm/fixmap.h
@@ -13,9 +13,6 @@
 #include <linux/kernel.h>
 #include <linux/threads.h>
 #include <asm/page.h>
-#ifdef CONFIG_HIGHMEM
-#include <asm/kmap_types.h>
-#endif
 
 /*
  * Here we define all the compile-time 'special' virtual
@@ -53,11 +50,6 @@ enum fixed_addresses {
 	FIX_CMAP_BEGIN,
 	FIX_CMAP_END = FIX_CMAP_BEGIN + (FIX_N_COLOURS * NR_CPUS) - 1,
 
-#ifdef CONFIG_HIGHMEM
-	FIX_KMAP_BEGIN,	/* reserved pte's for temporary kernel mappings */
-	FIX_KMAP_END = FIX_KMAP_BEGIN + (KM_TYPE_NR * NR_CPUS) - 1,
-#endif
-
 #ifdef CONFIG_IOREMAP_FIXED
 	/*
 	 * FIX_IOREMAP entries are useful for mapping physical address
diff --git a/arch/sh/include/asm/hardirq.h b/arch/sh/include/asm/hardirq.h
index edaea3559a232..9fe4495a8e90b 100644
--- a/arch/sh/include/asm/hardirq.h
+++ b/arch/sh/include/asm/hardirq.h
@@ -2,16 +2,10 @@
 #ifndef __ASM_SH_HARDIRQ_H
 #define __ASM_SH_HARDIRQ_H
 
-#include <linux/threads.h>
-#include <linux/irq.h>
-
-typedef struct {
-	unsigned int __softirq_pending;
-	unsigned int __nmi_count;		/* arch dependent */
-} ____cacheline_aligned irq_cpustat_t;
-
-#include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
-
 extern void ack_bad_irq(unsigned int irq);
+#define ack_bad_irq ack_bad_irq
+#define ARCH_WANTS_NMI_IRQSTAT
+
+#include <asm-generic/hardirq.h>
 
 #endif /* __ASM_SH_HARDIRQ_H */
diff --git a/arch/sh/include/asm/kmap_types.h b/arch/sh/include/asm/kmap_types.h
deleted file mode 100644
index b78107f923dd3..0000000000000
--- a/arch/sh/include/asm/kmap_types.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __SH_KMAP_TYPES_H
-#define __SH_KMAP_TYPES_H
-
-/* Dummy header just to define km_type. */
-
-#ifdef CONFIG_DEBUG_HIGHMEM
-#define  __WITH_KM_FENCE
-#endif
-
-#include <asm-generic/kmap_types.h>
-
-#undef __WITH_KM_FENCE
-
-#endif
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/irq.c b/arch/sh/kernel/irq.c
index 5717c7cbdd97a..5db7af565decc 100644
--- a/arch/sh/kernel/irq.c
+++ b/arch/sh/kernel/irq.c
@@ -44,7 +44,7 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 
 	seq_printf(p, "%*s: ", prec, "NMI");
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", nmi_count(j));
+		seq_printf(p, "%10u ", per_cpu(irq_stat.__nmi_count, j));
 	seq_printf(p, "  Non-maskable interrupts\n");
 
 	seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count));
@@ -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/sh/kernel/traps.c b/arch/sh/kernel/traps.c
index 9c3d32b80038a..f5beecdac6938 100644
--- a/arch/sh/kernel/traps.c
+++ b/arch/sh/kernel/traps.c
@@ -186,7 +186,7 @@ BUILD_TRAP_HANDLER(nmi)
 	arch_ftrace_nmi_enter();
 
 	nmi_enter();
-	nmi_count(cpu)++;
+	this_cpu_inc(irq_stat.__nmi_count);
 
 	switch (notify_die(DIE_NMI, "NMI", regs, 0, vec & 0xff, SIGINT)) {
 	case NOTIFY_OK:
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index 3348e0c4d7698..0db6919af8d32 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -362,9 +362,6 @@ void __init mem_init(void)
 	mem_init_print_info(NULL);
 	pr_info("virtual kernel memory layout:\n"
 		"    fixmap  : 0x%08lx - 0x%08lx   (%4ld kB)\n"
-#ifdef CONFIG_HIGHMEM
-		"    pkmap   : 0x%08lx - 0x%08lx   (%4ld kB)\n"
-#endif
 		"    vmalloc : 0x%08lx - 0x%08lx   (%4ld MB)\n"
 		"    lowmem  : 0x%08lx - 0x%08lx   (%4ld MB) (cached)\n"
 #ifdef CONFIG_UNCACHED_MAPPING
@@ -376,11 +373,6 @@ void __init mem_init(void)
 		FIXADDR_START, FIXADDR_TOP,
 		(FIXADDR_TOP - FIXADDR_START) >> 10,
 
-#ifdef CONFIG_HIGHMEM
-		PKMAP_BASE, PKMAP_BASE+LAST_PKMAP*PAGE_SIZE,
-		(LAST_PKMAP*PAGE_SIZE) >> 10,
-#endif
-
 		(unsigned long)VMALLOC_START, VMALLOC_END,
 		(VMALLOC_END - VMALLOC_START) >> 20,
 
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 530b7ec5d3ca9..a38d00d8b7839 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -139,6 +139,7 @@ config MMU
 config HIGHMEM
 	bool
 	default y if SPARC32
+	select KMAP_LOCAL
 
 config ZONE_DMA
 	bool
diff --git a/arch/sparc/include/asm/highmem.h b/arch/sparc/include/asm/highmem.h
index 6c35f0d27ee1a..875116209ec14 100644
--- a/arch/sparc/include/asm/highmem.h
+++ b/arch/sparc/include/asm/highmem.h
@@ -24,7 +24,6 @@
 #include <linux/interrupt.h>
 #include <linux/pgtable.h>
 #include <asm/vaddrs.h>
-#include <asm/kmap_types.h>
 #include <asm/pgtsrmmu.h>
 
 /* declarations for highmem.c */
@@ -33,8 +32,6 @@ extern unsigned long highstart_pfn, highend_pfn;
 #define kmap_prot __pgprot(SRMMU_ET_PTE | SRMMU_PRIV | SRMMU_CACHE)
 extern pte_t *pkmap_page_table;
 
-void kmap_init(void) __init;
-
 /*
  * Right now we initialize only a single pte table. It can be extended
  * easily, subsequent pte tables have to be allocated in one physical
@@ -53,6 +50,11 @@ void kmap_init(void) __init;
 
 #define flush_cache_kmaps()	flush_cache_all()
 
+/* FIXME: Use __flush_tlb_one(vaddr) instead of flush_cache_all() -- Anton */
+#define arch_kmap_local_post_map(vaddr, pteval)	flush_cache_all()
+#define arch_kmap_local_post_unmap(vaddr)	flush_cache_all()
+
+
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_HIGHMEM_H */
diff --git a/arch/sparc/include/asm/kmap_types.h b/arch/sparc/include/asm/kmap_types.h
deleted file mode 100644
index 55a99b6bd91e0..0000000000000
--- a/arch/sparc/include/asm/kmap_types.h
+++ /dev/null
@@ -1,11 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_KMAP_TYPES_H
-#define _ASM_KMAP_TYPES_H
-
-/* Dummy header just to define km_type.  None of this
- * is actually used on sparc.  -DaveM
- */
-
-#include <asm-generic/kmap_types.h>
-
-#endif
diff --git a/arch/sparc/include/asm/vaddrs.h b/arch/sparc/include/asm/vaddrs.h
index 84d054b07a6ff..4fec0341e2a81 100644
--- a/arch/sparc/include/asm/vaddrs.h
+++ b/arch/sparc/include/asm/vaddrs.h
@@ -32,13 +32,13 @@
 #define SRMMU_NOCACHE_ALCRATIO	64	/* 256 pages per 64MB of system RAM */
 
 #ifndef __ASSEMBLY__
-#include <asm/kmap_types.h>
+#include <asm/kmap_size.h>
 
 enum fixed_addresses {
 	FIX_HOLE,
 #ifdef CONFIG_HIGHMEM
 	FIX_KMAP_BEGIN,
-	FIX_KMAP_END = (KM_TYPE_NR * NR_CPUS),
+	FIX_KMAP_END = (KM_MAX_IDX * NR_CPUS),
 #endif
 	__end_of_fixed_addresses
 };
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/mm/Makefile b/arch/sparc/mm/Makefile
index b078205b70e0b..68db1f859b028 100644
--- a/arch/sparc/mm/Makefile
+++ b/arch/sparc/mm/Makefile
@@ -15,6 +15,3 @@ obj-$(CONFIG_SPARC32)   += leon_mm.o
 
 # Only used by sparc64
 obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
-
-# Only used by sparc32
-obj-$(CONFIG_HIGHMEM)   += highmem.o
diff --git a/arch/sparc/mm/highmem.c b/arch/sparc/mm/highmem.c
deleted file mode 100644
index 8f2a2afb048a2..0000000000000
--- a/arch/sparc/mm/highmem.c
+++ /dev/null
@@ -1,115 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- *  highmem.c: virtual kernel memory mappings for high memory
- *
- *  Provides kernel-static versions of atomic kmap functions originally
- *  found as inlines in include/asm-sparc/highmem.h.  These became
- *  needed as kmap_atomic() and kunmap_atomic() started getting
- *  called from within modules.
- *  -- Tomas Szepe <szepe@pinerecords.com>, September 2002
- *
- *  But kmap_atomic() and kunmap_atomic() cannot be inlined in
- *  modules because they are loaded with btfixup-ped functions.
- */
-
-/*
- * The use of kmap_atomic/kunmap_atomic is discouraged - kmap/kunmap
- * gives a more generic (and caching) interface. But kmap_atomic can
- * be used in IRQ contexts, so in some (very limited) cases we need it.
- *
- * XXX This is an old text. Actually, it's good to use atomic kmaps,
- * provided you remember that they are atomic and not try to sleep
- * with a kmap taken, much like a spinlock. Non-atomic kmaps are
- * shared by CPUs, and so precious, and establishing them requires IPI.
- * Atomic kmaps are lightweight and we may have NCPUS more of them.
- */
-#include <linux/highmem.h>
-#include <linux/export.h>
-#include <linux/mm.h>
-
-#include <asm/cacheflush.h>
-#include <asm/tlbflush.h>
-#include <asm/vaddrs.h>
-
-static pte_t *kmap_pte;
-
-void __init kmap_init(void)
-{
-	unsigned long address = __fix_to_virt(FIX_KMAP_BEGIN);
-
-        /* cache the first kmap pte */
-        kmap_pte = virt_to_kpte(address);
-}
-
-void *kmap_atomic_high_prot(struct page *page, pgprot_t prot)
-{
-	unsigned long vaddr;
-	long idx, type;
-
-	type = kmap_atomic_idx_push();
-	idx = type + KM_TYPE_NR*smp_processor_id();
-	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
-
-/* XXX Fix - Anton */
-#if 0
-	__flush_cache_one(vaddr);
-#else
-	flush_cache_all();
-#endif
-
-#ifdef CONFIG_DEBUG_HIGHMEM
-	BUG_ON(!pte_none(*(kmap_pte-idx)));
-#endif