Update Linux to v5.10.109

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz

Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/include/asm-generic/4level-fixup.h b/include/asm-generic/4level-fixup.h
deleted file mode 100644
index e3667c9..0000000
--- a/include/asm-generic/4level-fixup.h
+++ /dev/null
@@ -1,40 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _4LEVEL_FIXUP_H
-#define _4LEVEL_FIXUP_H
-
-#define __ARCH_HAS_4LEVEL_HACK
-#define __PAGETABLE_PUD_FOLDED 1
-
-#define PUD_SHIFT			PGDIR_SHIFT
-#define PUD_SIZE			PGDIR_SIZE
-#define PUD_MASK			PGDIR_MASK
-#define PTRS_PER_PUD			1
-
-#define pud_t				pgd_t
-
-#define pmd_alloc(mm, pud, address) \
-	((unlikely(pgd_none(*(pud))) && __pmd_alloc(mm, pud, address))? \
- 		NULL: pmd_offset(pud, address))
-
-#define pud_offset(pgd, start)		(pgd)
-#define pud_none(pud)			0
-#define pud_bad(pud)			0
-#define pud_present(pud)		1
-#define pud_ERROR(pud)			do { } while (0)
-#define pud_clear(pud)			pgd_clear(pud)
-#define pud_val(pud)			pgd_val(pud)
-#define pud_populate(mm, pud, pmd)	pgd_populate(mm, pud, pmd)
-#define pud_page(pud)			pgd_page(pud)
-#define pud_page_vaddr(pud)		pgd_page_vaddr(pud)
-
-#undef pud_free_tlb
-#define pud_free_tlb(tlb, x, addr)	do { } while (0)
-#define pud_free(mm, x)			do { } while (0)
-#define __pud_free_tlb(tlb, x, addr)	do { } while (0)
-
-#undef  pud_addr_end
-#define pud_addr_end(addr, end)		(end)
-
-#include <asm-generic/5level-fixup.h>
-
-#endif
diff --git a/include/asm-generic/5level-fixup.h b/include/asm-generic/5level-fixup.h
deleted file mode 100644
index f6947da..0000000
--- a/include/asm-generic/5level-fixup.h
+++ /dev/null
@@ -1,59 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _5LEVEL_FIXUP_H
-#define _5LEVEL_FIXUP_H
-
-#define __ARCH_HAS_5LEVEL_HACK
-#define __PAGETABLE_P4D_FOLDED 1
-
-#define P4D_SHIFT			PGDIR_SHIFT
-#define P4D_SIZE			PGDIR_SIZE
-#define P4D_MASK			PGDIR_MASK
-#define MAX_PTRS_PER_P4D		1
-#define PTRS_PER_P4D			1
-
-#define p4d_t				pgd_t
-
-#define pud_alloc(mm, p4d, address) \
-	((unlikely(pgd_none(*(p4d))) && __pud_alloc(mm, p4d, address)) ? \
-		NULL : pud_offset(p4d, address))
-
-#define p4d_alloc(mm, pgd, address)	(pgd)
-#define p4d_offset(pgd, start)		(pgd)
-
-#ifndef __ASSEMBLY__
-static inline int p4d_none(p4d_t p4d)
-{
-	return 0;
-}
-
-static inline int p4d_bad(p4d_t p4d)
-{
-	return 0;
-}
-
-static inline int p4d_present(p4d_t p4d)
-{
-	return 1;
-}
-#endif
-
-#define p4d_ERROR(p4d)			do { } while (0)
-#define p4d_clear(p4d)			pgd_clear(p4d)
-#define p4d_val(p4d)			pgd_val(p4d)
-#define p4d_populate(mm, p4d, pud)	pgd_populate(mm, p4d, pud)
-#define p4d_populate_safe(mm, p4d, pud)	pgd_populate(mm, p4d, pud)
-#define p4d_page(p4d)			pgd_page(p4d)
-#define p4d_page_vaddr(p4d)		pgd_page_vaddr(p4d)
-
-#define __p4d(x)			__pgd(x)
-#define set_p4d(p4dp, p4d)		set_pgd(p4dp, p4d)
-
-#undef p4d_free_tlb
-#define p4d_free_tlb(tlb, x, addr)	do { } while (0)
-#define p4d_free(mm, x)			do { } while (0)
-#define __p4d_free_tlb(tlb, x, addr)	do { } while (0)
-
-#undef  p4d_addr_end
-#define p4d_addr_end(addr, end)		(end)
-
-#endif
diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild
index adff14f..d1300c6 100644
--- a/include/asm-generic/Kbuild
+++ b/include/asm-generic/Kbuild
@@ -4,4 +4,61 @@
 # (This file is not included when SRCARCH=um since UML borrows several
 # asm headers from the host architecutre.)
 
+mandatory-y += atomic.h
+mandatory-y += barrier.h
+mandatory-y += bitops.h
+mandatory-y += bug.h
+mandatory-y += bugs.h
+mandatory-y += cacheflush.h
+mandatory-y += checksum.h
+mandatory-y += compat.h
+mandatory-y += current.h
+mandatory-y += delay.h
+mandatory-y += device.h
+mandatory-y += div64.h
+mandatory-y += dma-mapping.h
+mandatory-y += dma.h
+mandatory-y += emergency-restart.h
+mandatory-y += exec.h
+mandatory-y += fb.h
+mandatory-y += ftrace.h
+mandatory-y += futex.h
+mandatory-y += hardirq.h
+mandatory-y += hw_irq.h
+mandatory-y += io.h
+mandatory-y += irq.h
+mandatory-y += irq_regs.h
+mandatory-y += irq_work.h
+mandatory-y += kdebug.h
+mandatory-y += kmap_types.h
+mandatory-y += kprobes.h
+mandatory-y += linkage.h
+mandatory-y += local.h
+mandatory-y += local64.h
+mandatory-y += mm-arch-hooks.h
+mandatory-y += mmiowb.h
+mandatory-y += mmu.h
+mandatory-y += mmu_context.h
+mandatory-y += module.h
+mandatory-y += module.lds.h
+mandatory-y += msi.h
+mandatory-y += pci.h
+mandatory-y += percpu.h
+mandatory-y += pgalloc.h
+mandatory-y += preempt.h
+mandatory-y += rwonce.h
+mandatory-y += sections.h
+mandatory-y += serial.h
+mandatory-y += shmparam.h
 mandatory-y += simd.h
+mandatory-y += switch_to.h
+mandatory-y += timex.h
+mandatory-y += tlbflush.h
+mandatory-y += topology.h
+mandatory-y += trace_clock.h
+mandatory-y += uaccess.h
+mandatory-y += unaligned.h
+mandatory-y += vermagic.h
+mandatory-y += vga.h
+mandatory-y += word-at-a-time.h
+mandatory-y += xor.h
diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h
index e8730c6..cd223b6 100644
--- a/include/asm-generic/atomic-instrumented.h
+++ b/include/asm-generic/atomic-instrumented.h
@@ -18,1623 +18,1624 @@
 #define _ASM_GENERIC_ATOMIC_INSTRUMENTED_H
 
 #include <linux/build_bug.h>
-#include <linux/kasan-checks.h>
+#include <linux/compiler.h>
+#include <linux/instrumented.h>
 
-static inline int
+static __always_inline int
 atomic_read(const atomic_t *v)
 {
-	kasan_check_read(v, sizeof(*v));
+	instrument_atomic_read(v, sizeof(*v));
 	return arch_atomic_read(v);
 }
 #define atomic_read atomic_read
 
 #if defined(arch_atomic_read_acquire)
-static inline int
+static __always_inline int
 atomic_read_acquire(const atomic_t *v)
 {
-	kasan_check_read(v, sizeof(*v));
+	instrument_atomic_read(v, sizeof(*v));
 	return arch_atomic_read_acquire(v);
 }
 #define atomic_read_acquire atomic_read_acquire
 #endif
 
-static inline void
+static __always_inline void
 atomic_set(atomic_t *v, int i)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_write(v, sizeof(*v));
 	arch_atomic_set(v, i);
 }
 #define atomic_set atomic_set
 
 #if defined(arch_atomic_set_release)
-static inline void
+static __always_inline void
 atomic_set_release(atomic_t *v, int i)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_write(v, sizeof(*v));
 	arch_atomic_set_release(v, i);
 }
 #define atomic_set_release atomic_set_release
 #endif
 
-static inline void
+static __always_inline void
 atomic_add(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic_add(i, v);
 }
 #define atomic_add atomic_add
 
 #if !defined(arch_atomic_add_return_relaxed) || defined(arch_atomic_add_return)
-static inline int
+static __always_inline int
 atomic_add_return(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_add_return(i, v);
 }
 #define atomic_add_return atomic_add_return
 #endif
 
 #if defined(arch_atomic_add_return_acquire)
-static inline int
+static __always_inline int
 atomic_add_return_acquire(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_add_return_acquire(i, v);
 }
 #define atomic_add_return_acquire atomic_add_return_acquire
 #endif
 
 #if defined(arch_atomic_add_return_release)
-static inline int
+static __always_inline int
 atomic_add_return_release(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_add_return_release(i, v);
 }
 #define atomic_add_return_release atomic_add_return_release
 #endif
 
 #if defined(arch_atomic_add_return_relaxed)
-static inline int
+static __always_inline int
 atomic_add_return_relaxed(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_add_return_relaxed(i, v);
 }
 #define atomic_add_return_relaxed atomic_add_return_relaxed
 #endif
 
 #if !defined(arch_atomic_fetch_add_relaxed) || defined(arch_atomic_fetch_add)
-static inline int
+static __always_inline int
 atomic_fetch_add(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_add(i, v);
 }
 #define atomic_fetch_add atomic_fetch_add
 #endif
 
 #if defined(arch_atomic_fetch_add_acquire)
-static inline int
+static __always_inline int
 atomic_fetch_add_acquire(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_add_acquire(i, v);
 }
 #define atomic_fetch_add_acquire atomic_fetch_add_acquire
 #endif
 
 #if defined(arch_atomic_fetch_add_release)
-static inline int
+static __always_inline int
 atomic_fetch_add_release(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_add_release(i, v);
 }
 #define atomic_fetch_add_release atomic_fetch_add_release
 #endif
 
 #if defined(arch_atomic_fetch_add_relaxed)
-static inline int
+static __always_inline int
 atomic_fetch_add_relaxed(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_add_relaxed(i, v);
 }
 #define atomic_fetch_add_relaxed atomic_fetch_add_relaxed
 #endif
 
-static inline void
+static __always_inline void
 atomic_sub(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic_sub(i, v);
 }
 #define atomic_sub atomic_sub
 
 #if !defined(arch_atomic_sub_return_relaxed) || defined(arch_atomic_sub_return)
-static inline int
+static __always_inline int
 atomic_sub_return(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_sub_return(i, v);
 }
 #define atomic_sub_return atomic_sub_return
 #endif
 
 #if defined(arch_atomic_sub_return_acquire)
-static inline int
+static __always_inline int
 atomic_sub_return_acquire(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_sub_return_acquire(i, v);
 }
 #define atomic_sub_return_acquire atomic_sub_return_acquire
 #endif
 
 #if defined(arch_atomic_sub_return_release)
-static inline int
+static __always_inline int
 atomic_sub_return_release(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_sub_return_release(i, v);
 }
 #define atomic_sub_return_release atomic_sub_return_release
 #endif
 
 #if defined(arch_atomic_sub_return_relaxed)
-static inline int
+static __always_inline int
 atomic_sub_return_relaxed(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_sub_return_relaxed(i, v);
 }
 #define atomic_sub_return_relaxed atomic_sub_return_relaxed
 #endif
 
 #if !defined(arch_atomic_fetch_sub_relaxed) || defined(arch_atomic_fetch_sub)
-static inline int
+static __always_inline int
 atomic_fetch_sub(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_sub(i, v);
 }
 #define atomic_fetch_sub atomic_fetch_sub
 #endif
 
 #if defined(arch_atomic_fetch_sub_acquire)
-static inline int
+static __always_inline int
 atomic_fetch_sub_acquire(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_sub_acquire(i, v);
 }
 #define atomic_fetch_sub_acquire atomic_fetch_sub_acquire
 #endif
 
 #if defined(arch_atomic_fetch_sub_release)
-static inline int
+static __always_inline int
 atomic_fetch_sub_release(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_sub_release(i, v);
 }
 #define atomic_fetch_sub_release atomic_fetch_sub_release
 #endif
 
 #if defined(arch_atomic_fetch_sub_relaxed)
-static inline int
+static __always_inline int
 atomic_fetch_sub_relaxed(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_sub_relaxed(i, v);
 }
 #define atomic_fetch_sub_relaxed atomic_fetch_sub_relaxed
 #endif
 
 #if defined(arch_atomic_inc)
-static inline void
+static __always_inline void
 atomic_inc(atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic_inc(v);
 }
 #define atomic_inc atomic_inc
 #endif
 
 #if defined(arch_atomic_inc_return)
-static inline int
+static __always_inline int
 atomic_inc_return(atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_inc_return(v);
 }
 #define atomic_inc_return atomic_inc_return
 #endif
 
 #if defined(arch_atomic_inc_return_acquire)
-static inline int
+static __always_inline int
 atomic_inc_return_acquire(atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_inc_return_acquire(v);
 }
 #define atomic_inc_return_acquire atomic_inc_return_acquire
 #endif
 
 #if defined(arch_atomic_inc_return_release)
-static inline int
+static __always_inline int
 atomic_inc_return_release(atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_inc_return_release(v);
 }
 #define atomic_inc_return_release atomic_inc_return_release
 #endif
 
 #if defined(arch_atomic_inc_return_relaxed)
-static inline int
+static __always_inline int
 atomic_inc_return_relaxed(atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_inc_return_relaxed(v);
 }
 #define atomic_inc_return_relaxed atomic_inc_return_relaxed
 #endif
 
 #if defined(arch_atomic_fetch_inc)
-static inline int
+static __always_inline int
 atomic_fetch_inc(atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_inc(v);
 }
 #define atomic_fetch_inc atomic_fetch_inc
 #endif
 
 #if defined(arch_atomic_fetch_inc_acquire)
-static inline int
+static __always_inline int
 atomic_fetch_inc_acquire(atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_inc_acquire(v);
 }
 #define atomic_fetch_inc_acquire atomic_fetch_inc_acquire
 #endif
 
 #if defined(arch_atomic_fetch_inc_release)
-static inline int
+static __always_inline int
 atomic_fetch_inc_release(atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_inc_release(v);
 }
 #define atomic_fetch_inc_release atomic_fetch_inc_release
 #endif
 
 #if defined(arch_atomic_fetch_inc_relaxed)
-static inline int
+static __always_inline int
 atomic_fetch_inc_relaxed(atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_inc_relaxed(v);
 }
 #define atomic_fetch_inc_relaxed atomic_fetch_inc_relaxed
 #endif
 
 #if defined(arch_atomic_dec)
-static inline void
+static __always_inline void
 atomic_dec(atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic_dec(v);
 }
 #define atomic_dec atomic_dec
 #endif
 
 #if defined(arch_atomic_dec_return)
-static inline int
+static __always_inline int
 atomic_dec_return(atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_dec_return(v);
 }
 #define atomic_dec_return atomic_dec_return
 #endif
 
 #if defined(arch_atomic_dec_return_acquire)
-static inline int
+static __always_inline int
 atomic_dec_return_acquire(atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_dec_return_acquire(v);
 }
 #define atomic_dec_return_acquire atomic_dec_return_acquire
 #endif
 
 #if defined(arch_atomic_dec_return_release)
-static inline int
+static __always_inline int
 atomic_dec_return_release(atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_dec_return_release(v);
 }
 #define atomic_dec_return_release atomic_dec_return_release
 #endif
 
 #if defined(arch_atomic_dec_return_relaxed)
-static inline int
+static __always_inline int
 atomic_dec_return_relaxed(atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_dec_return_relaxed(v);
 }
 #define atomic_dec_return_relaxed atomic_dec_return_relaxed
 #endif
 
 #if defined(arch_atomic_fetch_dec)
-static inline int
+static __always_inline int
 atomic_fetch_dec(atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_dec(v);
 }
 #define atomic_fetch_dec atomic_fetch_dec
 #endif
 
 #if defined(arch_atomic_fetch_dec_acquire)
-static inline int
+static __always_inline int
 atomic_fetch_dec_acquire(atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_dec_acquire(v);
 }
 #define atomic_fetch_dec_acquire atomic_fetch_dec_acquire
 #endif
 
 #if defined(arch_atomic_fetch_dec_release)
-static inline int
+static __always_inline int
 atomic_fetch_dec_release(atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_dec_release(v);
 }
 #define atomic_fetch_dec_release atomic_fetch_dec_release
 #endif
 
 #if defined(arch_atomic_fetch_dec_relaxed)
-static inline int
+static __always_inline int
 atomic_fetch_dec_relaxed(atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_dec_relaxed(v);
 }
 #define atomic_fetch_dec_relaxed atomic_fetch_dec_relaxed
 #endif
 
-static inline void
+static __always_inline void
 atomic_and(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic_and(i, v);
 }
 #define atomic_and atomic_and
 
 #if !defined(arch_atomic_fetch_and_relaxed) || defined(arch_atomic_fetch_and)
-static inline int
+static __always_inline int
 atomic_fetch_and(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_and(i, v);
 }
 #define atomic_fetch_and atomic_fetch_and
 #endif
 
 #if defined(arch_atomic_fetch_and_acquire)
-static inline int
+static __always_inline int
 atomic_fetch_and_acquire(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_and_acquire(i, v);
 }
 #define atomic_fetch_and_acquire atomic_fetch_and_acquire
 #endif
 
 #if defined(arch_atomic_fetch_and_release)
-static inline int
+static __always_inline int
 atomic_fetch_and_release(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_and_release(i, v);
 }
 #define atomic_fetch_and_release atomic_fetch_and_release
 #endif
 
 #if defined(arch_atomic_fetch_and_relaxed)
-static inline int
+static __always_inline int
 atomic_fetch_and_relaxed(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_and_relaxed(i, v);
 }
 #define atomic_fetch_and_relaxed atomic_fetch_and_relaxed
 #endif
 
 #if defined(arch_atomic_andnot)
-static inline void
+static __always_inline void
 atomic_andnot(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic_andnot(i, v);
 }
 #define atomic_andnot atomic_andnot
 #endif
 
 #if defined(arch_atomic_fetch_andnot)
-static inline int
+static __always_inline int
 atomic_fetch_andnot(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_andnot(i, v);
 }
 #define atomic_fetch_andnot atomic_fetch_andnot
 #endif
 
 #if defined(arch_atomic_fetch_andnot_acquire)
-static inline int
+static __always_inline int
 atomic_fetch_andnot_acquire(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_andnot_acquire(i, v);
 }
 #define atomic_fetch_andnot_acquire atomic_fetch_andnot_acquire
 #endif
 
 #if defined(arch_atomic_fetch_andnot_release)
-static inline int
+static __always_inline int
 atomic_fetch_andnot_release(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_andnot_release(i, v);
 }
 #define atomic_fetch_andnot_release atomic_fetch_andnot_release
 #endif
 
 #if defined(arch_atomic_fetch_andnot_relaxed)
-static inline int
+static __always_inline int
 atomic_fetch_andnot_relaxed(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_andnot_relaxed(i, v);
 }
 #define atomic_fetch_andnot_relaxed atomic_fetch_andnot_relaxed
 #endif
 
-static inline void
+static __always_inline void
 atomic_or(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic_or(i, v);
 }
 #define atomic_or atomic_or
 
 #if !defined(arch_atomic_fetch_or_relaxed) || defined(arch_atomic_fetch_or)
-static inline int
+static __always_inline int
 atomic_fetch_or(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_or(i, v);
 }
 #define atomic_fetch_or atomic_fetch_or
 #endif
 
 #if defined(arch_atomic_fetch_or_acquire)
-static inline int
+static __always_inline int
 atomic_fetch_or_acquire(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_or_acquire(i, v);
 }
 #define atomic_fetch_or_acquire atomic_fetch_or_acquire
 #endif
 
 #if defined(arch_atomic_fetch_or_release)
-static inline int
+static __always_inline int
 atomic_fetch_or_release(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_or_release(i, v);
 }
 #define atomic_fetch_or_release atomic_fetch_or_release
 #endif
 
 #if defined(arch_atomic_fetch_or_relaxed)
-static inline int
+static __always_inline int
 atomic_fetch_or_relaxed(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_or_relaxed(i, v);
 }
 #define atomic_fetch_or_relaxed atomic_fetch_or_relaxed
 #endif
 
-static inline void
+static __always_inline void
 atomic_xor(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic_xor(i, v);
 }
 #define atomic_xor atomic_xor
 
 #if !defined(arch_atomic_fetch_xor_relaxed) || defined(arch_atomic_fetch_xor)
-static inline int
+static __always_inline int
 atomic_fetch_xor(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_xor(i, v);
 }
 #define atomic_fetch_xor atomic_fetch_xor
 #endif
 
 #if defined(arch_atomic_fetch_xor_acquire)
-static inline int
+static __always_inline int
 atomic_fetch_xor_acquire(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_xor_acquire(i, v);
 }
 #define atomic_fetch_xor_acquire atomic_fetch_xor_acquire
 #endif
 
 #if defined(arch_atomic_fetch_xor_release)
-static inline int
+static __always_inline int
 atomic_fetch_xor_release(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_xor_release(i, v);
 }
 #define atomic_fetch_xor_release atomic_fetch_xor_release
 #endif
 
 #if defined(arch_atomic_fetch_xor_relaxed)
-static inline int
+static __always_inline int
 atomic_fetch_xor_relaxed(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_xor_relaxed(i, v);
 }
 #define atomic_fetch_xor_relaxed atomic_fetch_xor_relaxed
 #endif
 
 #if !defined(arch_atomic_xchg_relaxed) || defined(arch_atomic_xchg)
-static inline int
+static __always_inline int
 atomic_xchg(atomic_t *v, int i)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_xchg(v, i);
 }
 #define atomic_xchg atomic_xchg
 #endif
 
 #if defined(arch_atomic_xchg_acquire)
-static inline int
+static __always_inline int
 atomic_xchg_acquire(atomic_t *v, int i)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_xchg_acquire(v, i);
 }
 #define atomic_xchg_acquire atomic_xchg_acquire
 #endif
 
 #if defined(arch_atomic_xchg_release)
-static inline int
+static __always_inline int
 atomic_xchg_release(atomic_t *v, int i)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_xchg_release(v, i);
 }
 #define atomic_xchg_release atomic_xchg_release
 #endif
 
 #if defined(arch_atomic_xchg_relaxed)
-static inline int
+static __always_inline int
 atomic_xchg_relaxed(atomic_t *v, int i)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_xchg_relaxed(v, i);
 }
 #define atomic_xchg_relaxed atomic_xchg_relaxed
 #endif
 
 #if !defined(arch_atomic_cmpxchg_relaxed) || defined(arch_atomic_cmpxchg)
-static inline int
+static __always_inline int
 atomic_cmpxchg(atomic_t *v, int old, int new)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_cmpxchg(v, old, new);
 }
 #define atomic_cmpxchg atomic_cmpxchg
 #endif
 
 #if defined(arch_atomic_cmpxchg_acquire)
-static inline int
+static __always_inline int
 atomic_cmpxchg_acquire(atomic_t *v, int old, int new)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_cmpxchg_acquire(v, old, new);
 }
 #define atomic_cmpxchg_acquire atomic_cmpxchg_acquire
 #endif
 
 #if defined(arch_atomic_cmpxchg_release)
-static inline int
+static __always_inline int
 atomic_cmpxchg_release(atomic_t *v, int old, int new)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_cmpxchg_release(v, old, new);
 }
 #define atomic_cmpxchg_release atomic_cmpxchg_release
 #endif
 
 #if defined(arch_atomic_cmpxchg_relaxed)
-static inline int
+static __always_inline int
 atomic_cmpxchg_relaxed(atomic_t *v, int old, int new)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_cmpxchg_relaxed(v, old, new);
 }
 #define atomic_cmpxchg_relaxed atomic_cmpxchg_relaxed
 #endif
 
 #if defined(arch_atomic_try_cmpxchg)
-static inline bool
+static __always_inline bool
 atomic_try_cmpxchg(atomic_t *v, int *old, int new)
 {
-	kasan_check_write(v, sizeof(*v));
-	kasan_check_write(old, sizeof(*old));
+	instrument_atomic_read_write(v, sizeof(*v));
+	instrument_atomic_read_write(old, sizeof(*old));
 	return arch_atomic_try_cmpxchg(v, old, new);
 }
 #define atomic_try_cmpxchg atomic_try_cmpxchg
 #endif
 
 #if defined(arch_atomic_try_cmpxchg_acquire)
-static inline bool
+static __always_inline bool
 atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new)
 {
-	kasan_check_write(v, sizeof(*v));
-	kasan_check_write(old, sizeof(*old));
+	instrument_atomic_read_write(v, sizeof(*v));
+	instrument_atomic_read_write(old, sizeof(*old));
 	return arch_atomic_try_cmpxchg_acquire(v, old, new);
 }
 #define atomic_try_cmpxchg_acquire atomic_try_cmpxchg_acquire
 #endif
 
 #if defined(arch_atomic_try_cmpxchg_release)
-static inline bool
+static __always_inline bool
 atomic_try_cmpxchg_release(atomic_t *v, int *old, int new)
 {
-	kasan_check_write(v, sizeof(*v));
-	kasan_check_write(old, sizeof(*old));
+	instrument_atomic_read_write(v, sizeof(*v));
+	instrument_atomic_read_write(old, sizeof(*old));
 	return arch_atomic_try_cmpxchg_release(v, old, new);
 }
 #define atomic_try_cmpxchg_release atomic_try_cmpxchg_release
 #endif
 
 #if defined(arch_atomic_try_cmpxchg_relaxed)
-static inline bool
+static __always_inline bool
 atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new)
 {
-	kasan_check_write(v, sizeof(*v));
-	kasan_check_write(old, sizeof(*old));
+	instrument_atomic_read_write(v, sizeof(*v));
+	instrument_atomic_read_write(old, sizeof(*old));
 	return arch_atomic_try_cmpxchg_relaxed(v, old, new);
 }
 #define atomic_try_cmpxchg_relaxed atomic_try_cmpxchg_relaxed
 #endif
 
 #if defined(arch_atomic_sub_and_test)
-static inline bool
+static __always_inline bool
 atomic_sub_and_test(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_sub_and_test(i, v);
 }
 #define atomic_sub_and_test atomic_sub_and_test
 #endif
 
 #if defined(arch_atomic_dec_and_test)
-static inline bool
+static __always_inline bool
 atomic_dec_and_test(atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_dec_and_test(v);
 }
 #define atomic_dec_and_test atomic_dec_and_test
 #endif
 
 #if defined(arch_atomic_inc_and_test)
-static inline bool
+static __always_inline bool
 atomic_inc_and_test(atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_inc_and_test(v);
 }
 #define atomic_inc_and_test atomic_inc_and_test
 #endif
 
 #if defined(arch_atomic_add_negative)
-static inline bool
+static __always_inline bool
 atomic_add_negative(int i, atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_add_negative(i, v);
 }
 #define atomic_add_negative atomic_add_negative
 #endif
 
 #if defined(arch_atomic_fetch_add_unless)
-static inline int
+static __always_inline int
 atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_fetch_add_unless(v, a, u);
 }
 #define atomic_fetch_add_unless atomic_fetch_add_unless
 #endif
 
 #if defined(arch_atomic_add_unless)
-static inline bool
+static __always_inline bool
 atomic_add_unless(atomic_t *v, int a, int u)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_add_unless(v, a, u);
 }
 #define atomic_add_unless atomic_add_unless
 #endif
 
 #if defined(arch_atomic_inc_not_zero)
-static inline bool
+static __always_inline bool
 atomic_inc_not_zero(atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_inc_not_zero(v);
 }
 #define atomic_inc_not_zero atomic_inc_not_zero
 #endif
 
 #if defined(arch_atomic_inc_unless_negative)
-static inline bool
+static __always_inline bool
 atomic_inc_unless_negative(atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_inc_unless_negative(v);
 }
 #define atomic_inc_unless_negative atomic_inc_unless_negative
 #endif
 
 #if defined(arch_atomic_dec_unless_positive)
-static inline bool
+static __always_inline bool
 atomic_dec_unless_positive(atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_dec_unless_positive(v);
 }
 #define atomic_dec_unless_positive atomic_dec_unless_positive
 #endif
 
 #if defined(arch_atomic_dec_if_positive)
-static inline int
+static __always_inline int
 atomic_dec_if_positive(atomic_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic_dec_if_positive(v);
 }
 #define atomic_dec_if_positive atomic_dec_if_positive
 #endif
 
-static inline s64
+static __always_inline s64
 atomic64_read(const atomic64_t *v)
 {
-	kasan_check_read(v, sizeof(*v));
+	instrument_atomic_read(v, sizeof(*v));
 	return arch_atomic64_read(v);
 }
 #define atomic64_read atomic64_read
 
 #if defined(arch_atomic64_read_acquire)
-static inline s64
+static __always_inline s64
 atomic64_read_acquire(const atomic64_t *v)
 {
-	kasan_check_read(v, sizeof(*v));
+	instrument_atomic_read(v, sizeof(*v));
 	return arch_atomic64_read_acquire(v);
 }
 #define atomic64_read_acquire atomic64_read_acquire
 #endif
 
-static inline void
+static __always_inline void
 atomic64_set(atomic64_t *v, s64 i)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_write(v, sizeof(*v));
 	arch_atomic64_set(v, i);
 }
 #define atomic64_set atomic64_set
 
 #if defined(arch_atomic64_set_release)
-static inline void
+static __always_inline void
 atomic64_set_release(atomic64_t *v, s64 i)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_write(v, sizeof(*v));
 	arch_atomic64_set_release(v, i);
 }
 #define atomic64_set_release atomic64_set_release
 #endif
 
-static inline void
+static __always_inline void
 atomic64_add(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic64_add(i, v);
 }
 #define atomic64_add atomic64_add
 
 #if !defined(arch_atomic64_add_return_relaxed) || defined(arch_atomic64_add_return)
-static inline s64
+static __always_inline s64
 atomic64_add_return(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_add_return(i, v);
 }
 #define atomic64_add_return atomic64_add_return
 #endif
 
 #if defined(arch_atomic64_add_return_acquire)
-static inline s64
+static __always_inline s64
 atomic64_add_return_acquire(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_add_return_acquire(i, v);
 }
 #define atomic64_add_return_acquire atomic64_add_return_acquire
 #endif
 
 #if defined(arch_atomic64_add_return_release)
-static inline s64
+static __always_inline s64
 atomic64_add_return_release(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_add_return_release(i, v);
 }
 #define atomic64_add_return_release atomic64_add_return_release
 #endif
 
 #if defined(arch_atomic64_add_return_relaxed)
-static inline s64
+static __always_inline s64
 atomic64_add_return_relaxed(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_add_return_relaxed(i, v);
 }
 #define atomic64_add_return_relaxed atomic64_add_return_relaxed
 #endif
 
 #if !defined(arch_atomic64_fetch_add_relaxed) || defined(arch_atomic64_fetch_add)
-static inline s64
+static __always_inline s64
 atomic64_fetch_add(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_add(i, v);
 }
 #define atomic64_fetch_add atomic64_fetch_add
 #endif
 
 #if defined(arch_atomic64_fetch_add_acquire)
-static inline s64
+static __always_inline s64
 atomic64_fetch_add_acquire(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_add_acquire(i, v);
 }
 #define atomic64_fetch_add_acquire atomic64_fetch_add_acquire
 #endif
 
 #if defined(arch_atomic64_fetch_add_release)
-static inline s64
+static __always_inline s64
 atomic64_fetch_add_release(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_add_release(i, v);
 }
 #define atomic64_fetch_add_release atomic64_fetch_add_release
 #endif
 
 #if defined(arch_atomic64_fetch_add_relaxed)
-static inline s64
+static __always_inline s64
 atomic64_fetch_add_relaxed(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_add_relaxed(i, v);
 }
 #define atomic64_fetch_add_relaxed atomic64_fetch_add_relaxed
 #endif
 
-static inline void
+static __always_inline void
 atomic64_sub(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic64_sub(i, v);
 }
 #define atomic64_sub atomic64_sub
 
 #if !defined(arch_atomic64_sub_return_relaxed) || defined(arch_atomic64_sub_return)
-static inline s64
+static __always_inline s64
 atomic64_sub_return(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_sub_return(i, v);
 }
 #define atomic64_sub_return atomic64_sub_return
 #endif
 
 #if defined(arch_atomic64_sub_return_acquire)
-static inline s64
+static __always_inline s64
 atomic64_sub_return_acquire(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_sub_return_acquire(i, v);
 }
 #define atomic64_sub_return_acquire atomic64_sub_return_acquire
 #endif
 
 #if defined(arch_atomic64_sub_return_release)
-static inline s64
+static __always_inline s64
 atomic64_sub_return_release(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_sub_return_release(i, v);
 }
 #define atomic64_sub_return_release atomic64_sub_return_release
 #endif
 
 #if defined(arch_atomic64_sub_return_relaxed)
-static inline s64
+static __always_inline s64
 atomic64_sub_return_relaxed(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_sub_return_relaxed(i, v);
 }
 #define atomic64_sub_return_relaxed atomic64_sub_return_relaxed
 #endif
 
 #if !defined(arch_atomic64_fetch_sub_relaxed) || defined(arch_atomic64_fetch_sub)
-static inline s64
+static __always_inline s64
 atomic64_fetch_sub(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_sub(i, v);
 }
 #define atomic64_fetch_sub atomic64_fetch_sub
 #endif
 
 #if defined(arch_atomic64_fetch_sub_acquire)
-static inline s64
+static __always_inline s64
 atomic64_fetch_sub_acquire(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_sub_acquire(i, v);
 }
 #define atomic64_fetch_sub_acquire atomic64_fetch_sub_acquire
 #endif
 
 #if defined(arch_atomic64_fetch_sub_release)
-static inline s64
+static __always_inline s64
 atomic64_fetch_sub_release(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_sub_release(i, v);
 }
 #define atomic64_fetch_sub_release atomic64_fetch_sub_release
 #endif
 
 #if defined(arch_atomic64_fetch_sub_relaxed)
-static inline s64
+static __always_inline s64
 atomic64_fetch_sub_relaxed(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_sub_relaxed(i, v);
 }
 #define atomic64_fetch_sub_relaxed atomic64_fetch_sub_relaxed
 #endif
 
 #if defined(arch_atomic64_inc)
-static inline void
+static __always_inline void
 atomic64_inc(atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic64_inc(v);
 }
 #define atomic64_inc atomic64_inc
 #endif
 
 #if defined(arch_atomic64_inc_return)
-static inline s64
+static __always_inline s64
 atomic64_inc_return(atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_inc_return(v);
 }
 #define atomic64_inc_return atomic64_inc_return
 #endif
 
 #if defined(arch_atomic64_inc_return_acquire)
-static inline s64
+static __always_inline s64
 atomic64_inc_return_acquire(atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_inc_return_acquire(v);
 }
 #define atomic64_inc_return_acquire atomic64_inc_return_acquire
 #endif
 
 #if defined(arch_atomic64_inc_return_release)
-static inline s64
+static __always_inline s64
 atomic64_inc_return_release(atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_inc_return_release(v);
 }
 #define atomic64_inc_return_release atomic64_inc_return_release
 #endif
 
 #if defined(arch_atomic64_inc_return_relaxed)
-static inline s64
+static __always_inline s64
 atomic64_inc_return_relaxed(atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_inc_return_relaxed(v);
 }
 #define atomic64_inc_return_relaxed atomic64_inc_return_relaxed
 #endif
 
 #if defined(arch_atomic64_fetch_inc)
-static inline s64
+static __always_inline s64
 atomic64_fetch_inc(atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_inc(v);
 }
 #define atomic64_fetch_inc atomic64_fetch_inc
 #endif
 
 #if defined(arch_atomic64_fetch_inc_acquire)
-static inline s64
+static __always_inline s64
 atomic64_fetch_inc_acquire(atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_inc_acquire(v);
 }
 #define atomic64_fetch_inc_acquire atomic64_fetch_inc_acquire
 #endif
 
 #if defined(arch_atomic64_fetch_inc_release)
-static inline s64
+static __always_inline s64
 atomic64_fetch_inc_release(atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_inc_release(v);
 }
 #define atomic64_fetch_inc_release atomic64_fetch_inc_release
 #endif
 
 #if defined(arch_atomic64_fetch_inc_relaxed)
-static inline s64
+static __always_inline s64
 atomic64_fetch_inc_relaxed(atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_inc_relaxed(v);
 }
 #define atomic64_fetch_inc_relaxed atomic64_fetch_inc_relaxed
 #endif
 
 #if defined(arch_atomic64_dec)
-static inline void
+static __always_inline void
 atomic64_dec(atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic64_dec(v);
 }
 #define atomic64_dec atomic64_dec
 #endif
 
 #if defined(arch_atomic64_dec_return)
-static inline s64
+static __always_inline s64
 atomic64_dec_return(atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_dec_return(v);
 }
 #define atomic64_dec_return atomic64_dec_return
 #endif
 
 #if defined(arch_atomic64_dec_return_acquire)
-static inline s64
+static __always_inline s64
 atomic64_dec_return_acquire(atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_dec_return_acquire(v);
 }
 #define atomic64_dec_return_acquire atomic64_dec_return_acquire
 #endif
 
 #if defined(arch_atomic64_dec_return_release)
-static inline s64
+static __always_inline s64
 atomic64_dec_return_release(atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_dec_return_release(v);
 }
 #define atomic64_dec_return_release atomic64_dec_return_release
 #endif
 
 #if defined(arch_atomic64_dec_return_relaxed)
-static inline s64
+static __always_inline s64
 atomic64_dec_return_relaxed(atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_dec_return_relaxed(v);
 }
 #define atomic64_dec_return_relaxed atomic64_dec_return_relaxed
 #endif
 
 #if defined(arch_atomic64_fetch_dec)
-static inline s64
+static __always_inline s64
 atomic64_fetch_dec(atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_dec(v);
 }
 #define atomic64_fetch_dec atomic64_fetch_dec
 #endif
 
 #if defined(arch_atomic64_fetch_dec_acquire)
-static inline s64
+static __always_inline s64
 atomic64_fetch_dec_acquire(atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_dec_acquire(v);
 }
 #define atomic64_fetch_dec_acquire atomic64_fetch_dec_acquire
 #endif
 
 #if defined(arch_atomic64_fetch_dec_release)
-static inline s64
+static __always_inline s64
 atomic64_fetch_dec_release(atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_dec_release(v);
 }
 #define atomic64_fetch_dec_release atomic64_fetch_dec_release
 #endif
 
 #if defined(arch_atomic64_fetch_dec_relaxed)
-static inline s64
+static __always_inline s64
 atomic64_fetch_dec_relaxed(atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_dec_relaxed(v);
 }
 #define atomic64_fetch_dec_relaxed atomic64_fetch_dec_relaxed
 #endif
 
-static inline void
+static __always_inline void
 atomic64_and(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic64_and(i, v);
 }
 #define atomic64_and atomic64_and
 
 #if !defined(arch_atomic64_fetch_and_relaxed) || defined(arch_atomic64_fetch_and)
-static inline s64
+static __always_inline s64
 atomic64_fetch_and(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_and(i, v);
 }
 #define atomic64_fetch_and atomic64_fetch_and
 #endif
 
 #if defined(arch_atomic64_fetch_and_acquire)
-static inline s64
+static __always_inline s64
 atomic64_fetch_and_acquire(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_and_acquire(i, v);
 }
 #define atomic64_fetch_and_acquire atomic64_fetch_and_acquire
 #endif
 
 #if defined(arch_atomic64_fetch_and_release)
-static inline s64
+static __always_inline s64
 atomic64_fetch_and_release(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_and_release(i, v);
 }
 #define atomic64_fetch_and_release atomic64_fetch_and_release
 #endif
 
 #if defined(arch_atomic64_fetch_and_relaxed)
-static inline s64
+static __always_inline s64
 atomic64_fetch_and_relaxed(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_and_relaxed(i, v);
 }
 #define atomic64_fetch_and_relaxed atomic64_fetch_and_relaxed
 #endif
 
 #if defined(arch_atomic64_andnot)
-static inline void
+static __always_inline void
 atomic64_andnot(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic64_andnot(i, v);
 }
 #define atomic64_andnot atomic64_andnot
 #endif
 
 #if defined(arch_atomic64_fetch_andnot)
-static inline s64
+static __always_inline s64
 atomic64_fetch_andnot(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_andnot(i, v);
 }
 #define atomic64_fetch_andnot atomic64_fetch_andnot
 #endif
 
 #if defined(arch_atomic64_fetch_andnot_acquire)
-static inline s64
+static __always_inline s64
 atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_andnot_acquire(i, v);
 }
 #define atomic64_fetch_andnot_acquire atomic64_fetch_andnot_acquire
 #endif
 
 #if defined(arch_atomic64_fetch_andnot_release)
-static inline s64
+static __always_inline s64
 atomic64_fetch_andnot_release(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_andnot_release(i, v);
 }
 #define atomic64_fetch_andnot_release atomic64_fetch_andnot_release
 #endif
 
 #if defined(arch_atomic64_fetch_andnot_relaxed)
-static inline s64
+static __always_inline s64
 atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_andnot_relaxed(i, v);
 }
 #define atomic64_fetch_andnot_relaxed atomic64_fetch_andnot_relaxed
 #endif
 
-static inline void
+static __always_inline void
 atomic64_or(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic64_or(i, v);
 }
 #define atomic64_or atomic64_or
 
 #if !defined(arch_atomic64_fetch_or_relaxed) || defined(arch_atomic64_fetch_or)
-static inline s64
+static __always_inline s64
 atomic64_fetch_or(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_or(i, v);
 }
 #define atomic64_fetch_or atomic64_fetch_or
 #endif
 
 #if defined(arch_atomic64_fetch_or_acquire)
-static inline s64
+static __always_inline s64
 atomic64_fetch_or_acquire(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_or_acquire(i, v);
 }
 #define atomic64_fetch_or_acquire atomic64_fetch_or_acquire
 #endif
 
 #if defined(arch_atomic64_fetch_or_release)
-static inline s64
+static __always_inline s64
 atomic64_fetch_or_release(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_or_release(i, v);
 }
 #define atomic64_fetch_or_release atomic64_fetch_or_release
 #endif
 
 #if defined(arch_atomic64_fetch_or_relaxed)
-static inline s64
+static __always_inline s64
 atomic64_fetch_or_relaxed(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_or_relaxed(i, v);
 }
 #define atomic64_fetch_or_relaxed atomic64_fetch_or_relaxed
 #endif
 
-static inline void
+static __always_inline void
 atomic64_xor(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	arch_atomic64_xor(i, v);
 }
 #define atomic64_xor atomic64_xor
 
 #if !defined(arch_atomic64_fetch_xor_relaxed) || defined(arch_atomic64_fetch_xor)
-static inline s64
+static __always_inline s64
 atomic64_fetch_xor(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_xor(i, v);
 }
 #define atomic64_fetch_xor atomic64_fetch_xor
 #endif
 
 #if defined(arch_atomic64_fetch_xor_acquire)
-static inline s64
+static __always_inline s64
 atomic64_fetch_xor_acquire(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_xor_acquire(i, v);
 }
 #define atomic64_fetch_xor_acquire atomic64_fetch_xor_acquire
 #endif
 
 #if defined(arch_atomic64_fetch_xor_release)
-static inline s64
+static __always_inline s64
 atomic64_fetch_xor_release(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_xor_release(i, v);
 }
 #define atomic64_fetch_xor_release atomic64_fetch_xor_release
 #endif
 
 #if defined(arch_atomic64_fetch_xor_relaxed)
-static inline s64
+static __always_inline s64
 atomic64_fetch_xor_relaxed(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_xor_relaxed(i, v);
 }
 #define atomic64_fetch_xor_relaxed atomic64_fetch_xor_relaxed
 #endif
 
 #if !defined(arch_atomic64_xchg_relaxed) || defined(arch_atomic64_xchg)
-static inline s64
+static __always_inline s64
 atomic64_xchg(atomic64_t *v, s64 i)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_xchg(v, i);
 }
 #define atomic64_xchg atomic64_xchg
 #endif
 
 #if defined(arch_atomic64_xchg_acquire)
-static inline s64
+static __always_inline s64
 atomic64_xchg_acquire(atomic64_t *v, s64 i)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_xchg_acquire(v, i);
 }
 #define atomic64_xchg_acquire atomic64_xchg_acquire
 #endif
 
 #if defined(arch_atomic64_xchg_release)
-static inline s64
+static __always_inline s64
 atomic64_xchg_release(atomic64_t *v, s64 i)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_xchg_release(v, i);
 }
 #define atomic64_xchg_release atomic64_xchg_release
 #endif
 
 #if defined(arch_atomic64_xchg_relaxed)
-static inline s64
+static __always_inline s64
 atomic64_xchg_relaxed(atomic64_t *v, s64 i)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_xchg_relaxed(v, i);
 }
 #define atomic64_xchg_relaxed atomic64_xchg_relaxed
 #endif
 
 #if !defined(arch_atomic64_cmpxchg_relaxed) || defined(arch_atomic64_cmpxchg)
-static inline s64
+static __always_inline s64
 atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_cmpxchg(v, old, new);
 }
 #define atomic64_cmpxchg atomic64_cmpxchg
 #endif
 
 #if defined(arch_atomic64_cmpxchg_acquire)
-static inline s64
+static __always_inline s64
 atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_cmpxchg_acquire(v, old, new);
 }
 #define atomic64_cmpxchg_acquire atomic64_cmpxchg_acquire
 #endif
 
 #if defined(arch_atomic64_cmpxchg_release)
-static inline s64
+static __always_inline s64
 atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_cmpxchg_release(v, old, new);
 }
 #define atomic64_cmpxchg_release atomic64_cmpxchg_release
 #endif
 
 #if defined(arch_atomic64_cmpxchg_relaxed)
-static inline s64
+static __always_inline s64
 atomic64_cmpxchg_relaxed(atomic64_t *v, s64 old, s64 new)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_cmpxchg_relaxed(v, old, new);
 }
 #define atomic64_cmpxchg_relaxed atomic64_cmpxchg_relaxed
 #endif
 
 #if defined(arch_atomic64_try_cmpxchg)
-static inline bool
+static __always_inline bool
 atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new)
 {
-	kasan_check_write(v, sizeof(*v));
-	kasan_check_write(old, sizeof(*old));
+	instrument_atomic_read_write(v, sizeof(*v));
+	instrument_atomic_read_write(old, sizeof(*old));
 	return arch_atomic64_try_cmpxchg(v, old, new);
 }
 #define atomic64_try_cmpxchg atomic64_try_cmpxchg
 #endif
 
 #if defined(arch_atomic64_try_cmpxchg_acquire)
-static inline bool
+static __always_inline bool
 atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new)
 {
-	kasan_check_write(v, sizeof(*v));
-	kasan_check_write(old, sizeof(*old));
+	instrument_atomic_read_write(v, sizeof(*v));
+	instrument_atomic_read_write(old, sizeof(*old));
 	return arch_atomic64_try_cmpxchg_acquire(v, old, new);
 }
 #define atomic64_try_cmpxchg_acquire atomic64_try_cmpxchg_acquire
 #endif
 
 #if defined(arch_atomic64_try_cmpxchg_release)
-static inline bool
+static __always_inline bool
 atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new)
 {
-	kasan_check_write(v, sizeof(*v));
-	kasan_check_write(old, sizeof(*old));
+	instrument_atomic_read_write(v, sizeof(*v));
+	instrument_atomic_read_write(old, sizeof(*old));
 	return arch_atomic64_try_cmpxchg_release(v, old, new);
 }
 #define atomic64_try_cmpxchg_release atomic64_try_cmpxchg_release
 #endif
 
 #if defined(arch_atomic64_try_cmpxchg_relaxed)
-static inline bool
+static __always_inline bool
 atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new)
 {
-	kasan_check_write(v, sizeof(*v));
-	kasan_check_write(old, sizeof(*old));
+	instrument_atomic_read_write(v, sizeof(*v));
+	instrument_atomic_read_write(old, sizeof(*old));
 	return arch_atomic64_try_cmpxchg_relaxed(v, old, new);
 }
 #define atomic64_try_cmpxchg_relaxed atomic64_try_cmpxchg_relaxed
 #endif
 
 #if defined(arch_atomic64_sub_and_test)
-static inline bool
+static __always_inline bool
 atomic64_sub_and_test(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_sub_and_test(i, v);
 }
 #define atomic64_sub_and_test atomic64_sub_and_test
 #endif
 
 #if defined(arch_atomic64_dec_and_test)
-static inline bool
+static __always_inline bool
 atomic64_dec_and_test(atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_dec_and_test(v);
 }
 #define atomic64_dec_and_test atomic64_dec_and_test
 #endif
 
 #if defined(arch_atomic64_inc_and_test)
-static inline bool
+static __always_inline bool
 atomic64_inc_and_test(atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_inc_and_test(v);
 }
 #define atomic64_inc_and_test atomic64_inc_and_test
 #endif
 
 #if defined(arch_atomic64_add_negative)
-static inline bool
+static __always_inline bool
 atomic64_add_negative(s64 i, atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_add_negative(i, v);
 }
 #define atomic64_add_negative atomic64_add_negative
 #endif
 
 #if defined(arch_atomic64_fetch_add_unless)
-static inline s64
+static __always_inline s64
 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_fetch_add_unless(v, a, u);
 }
 #define atomic64_fetch_add_unless atomic64_fetch_add_unless
 #endif
 
 #if defined(arch_atomic64_add_unless)
-static inline bool
+static __always_inline bool
 atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_add_unless(v, a, u);
 }
 #define atomic64_add_unless atomic64_add_unless
 #endif
 
 #if defined(arch_atomic64_inc_not_zero)
-static inline bool
+static __always_inline bool
 atomic64_inc_not_zero(atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_inc_not_zero(v);
 }
 #define atomic64_inc_not_zero atomic64_inc_not_zero
 #endif
 
 #if defined(arch_atomic64_inc_unless_negative)
-static inline bool
+static __always_inline bool
 atomic64_inc_unless_negative(atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_inc_unless_negative(v);
 }
 #define atomic64_inc_unless_negative atomic64_inc_unless_negative
 #endif
 
 #if defined(arch_atomic64_dec_unless_positive)
-static inline bool
+static __always_inline bool
 atomic64_dec_unless_positive(atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_dec_unless_positive(v);
 }
 #define atomic64_dec_unless_positive atomic64_dec_unless_positive
 #endif
 
 #if defined(arch_atomic64_dec_if_positive)
-static inline s64
+static __always_inline s64
 atomic64_dec_if_positive(atomic64_t *v)
 {
-	kasan_check_write(v, sizeof(*v));
+	instrument_atomic_read_write(v, sizeof(*v));
 	return arch_atomic64_dec_if_positive(v);
 }
 #define atomic64_dec_if_positive atomic64_dec_if_positive
@@ -1644,7 +1645,7 @@
 #define xchg(ptr, ...)						\
 ({									\
 	typeof(ptr) __ai_ptr = (ptr);					\
-	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));		\
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
 	arch_xchg(__ai_ptr, __VA_ARGS__);				\
 })
 #endif
@@ -1653,7 +1654,7 @@
 #define xchg_acquire(ptr, ...)						\
 ({									\
 	typeof(ptr) __ai_ptr = (ptr);					\
-	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));		\
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
 	arch_xchg_acquire(__ai_ptr, __VA_ARGS__);				\
 })
 #endif
@@ -1662,7 +1663,7 @@
 #define xchg_release(ptr, ...)						\
 ({									\
 	typeof(ptr) __ai_ptr = (ptr);					\
-	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));		\
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
 	arch_xchg_release(__ai_ptr, __VA_ARGS__);				\
 })
 #endif
@@ -1671,7 +1672,7 @@
 #define xchg_relaxed(ptr, ...)						\
 ({									\
 	typeof(ptr) __ai_ptr = (ptr);					\
-	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));		\
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
 	arch_xchg_relaxed(__ai_ptr, __VA_ARGS__);				\
 })
 #endif
@@ -1680,7 +1681,7 @@
 #define cmpxchg(ptr, ...)						\
 ({									\
 	typeof(ptr) __ai_ptr = (ptr);					\
-	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));		\
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
 	arch_cmpxchg(__ai_ptr, __VA_ARGS__);				\
 })
 #endif
@@ -1689,7 +1690,7 @@
 #define cmpxchg_acquire(ptr, ...)						\
 ({									\
 	typeof(ptr) __ai_ptr = (ptr);					\
-	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));		\
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
 	arch_cmpxchg_acquire(__ai_ptr, __VA_ARGS__);				\
 })
 #endif
@@ -1698,7 +1699,7 @@
 #define cmpxchg_release(ptr, ...)						\
 ({									\
 	typeof(ptr) __ai_ptr = (ptr);					\
-	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));		\
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
 	arch_cmpxchg_release(__ai_ptr, __VA_ARGS__);				\
 })
 #endif
@@ -1707,7 +1708,7 @@
 #define cmpxchg_relaxed(ptr, ...)						\
 ({									\
 	typeof(ptr) __ai_ptr = (ptr);					\
-	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));		\
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
 	arch_cmpxchg_relaxed(__ai_ptr, __VA_ARGS__);				\
 })
 #endif
@@ -1716,7 +1717,7 @@
 #define cmpxchg64(ptr, ...)						\
 ({									\
 	typeof(ptr) __ai_ptr = (ptr);					\
-	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));		\
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
 	arch_cmpxchg64(__ai_ptr, __VA_ARGS__);				\
 })
 #endif
@@ -1725,7 +1726,7 @@
 #define cmpxchg64_acquire(ptr, ...)						\
 ({									\
 	typeof(ptr) __ai_ptr = (ptr);					\
-	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));		\
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
 	arch_cmpxchg64_acquire(__ai_ptr, __VA_ARGS__);				\
 })
 #endif
@@ -1734,7 +1735,7 @@
 #define cmpxchg64_release(ptr, ...)						\
 ({									\
 	typeof(ptr) __ai_ptr = (ptr);					\
-	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));		\
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
 	arch_cmpxchg64_release(__ai_ptr, __VA_ARGS__);				\
 })
 #endif
@@ -1743,7 +1744,7 @@
 #define cmpxchg64_relaxed(ptr, ...)						\
 ({									\
 	typeof(ptr) __ai_ptr = (ptr);					\
-	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));		\
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
 	arch_cmpxchg64_relaxed(__ai_ptr, __VA_ARGS__);				\
 })
 #endif
@@ -1751,28 +1752,28 @@
 #define cmpxchg_local(ptr, ...)						\
 ({									\
 	typeof(ptr) __ai_ptr = (ptr);					\
-	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));		\
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
 	arch_cmpxchg_local(__ai_ptr, __VA_ARGS__);				\
 })
 
 #define cmpxchg64_local(ptr, ...)						\
 ({									\
 	typeof(ptr) __ai_ptr = (ptr);					\
-	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));		\
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
 	arch_cmpxchg64_local(__ai_ptr, __VA_ARGS__);				\
 })
 
 #define sync_cmpxchg(ptr, ...)						\
 ({									\
 	typeof(ptr) __ai_ptr = (ptr);					\
-	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));		\
+	instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr));		\
 	arch_sync_cmpxchg(__ai_ptr, __VA_ARGS__);				\
 })
 
 #define cmpxchg_double(ptr, ...)						\
 ({									\
 	typeof(ptr) __ai_ptr = (ptr);					\
-	kasan_check_write(__ai_ptr, 2 * sizeof(*__ai_ptr));		\
+	instrument_atomic_write(__ai_ptr, 2 * sizeof(*__ai_ptr));		\
 	arch_cmpxchg_double(__ai_ptr, __VA_ARGS__);				\
 })
 
@@ -1780,9 +1781,9 @@
 #define cmpxchg_double_local(ptr, ...)						\
 ({									\
 	typeof(ptr) __ai_ptr = (ptr);					\
-	kasan_check_write(__ai_ptr, 2 * sizeof(*__ai_ptr));		\
+	instrument_atomic_write(__ai_ptr, 2 * sizeof(*__ai_ptr));		\
 	arch_cmpxchg_double_local(__ai_ptr, __VA_ARGS__);				\
 })
 
 #endif /* _ASM_GENERIC_ATOMIC_INSTRUMENTED_H */
-// b29b625d5de9280f680e42c7be859b55b15e5f6a
+// 9d5e6a315fb1335d02f0ccd3655a91c3dafcc63e
diff --git a/include/asm-generic/atomic-long.h b/include/asm-generic/atomic-long.h
index 881c7e2..073cf40 100644
--- a/include/asm-generic/atomic-long.h
+++ b/include/asm-generic/atomic-long.h
@@ -6,6 +6,7 @@
 #ifndef _ASM_GENERIC_ATOMIC_LONG_H
 #define _ASM_GENERIC_ATOMIC_LONG_H
 
+#include <linux/compiler.h>
 #include <asm/types.h>
 
 #ifdef CONFIG_64BIT
@@ -22,493 +23,493 @@
 
 #ifdef CONFIG_64BIT
 
-static inline long
+static __always_inline long
 atomic_long_read(const atomic_long_t *v)
 {
 	return atomic64_read(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_read_acquire(const atomic_long_t *v)
 {
 	return atomic64_read_acquire(v);
 }
 
-static inline void
+static __always_inline void
 atomic_long_set(atomic_long_t *v, long i)
 {
 	atomic64_set(v, i);
 }
 
-static inline void
+static __always_inline void
 atomic_long_set_release(atomic_long_t *v, long i)
 {
 	atomic64_set_release(v, i);
 }
 
-static inline void
+static __always_inline void
 atomic_long_add(long i, atomic_long_t *v)
 {
 	atomic64_add(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_add_return(long i, atomic_long_t *v)
 {
 	return atomic64_add_return(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_add_return_acquire(long i, atomic_long_t *v)
 {
 	return atomic64_add_return_acquire(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_add_return_release(long i, atomic_long_t *v)
 {
 	return atomic64_add_return_release(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_add_return_relaxed(long i, atomic_long_t *v)
 {
 	return atomic64_add_return_relaxed(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_add(long i, atomic_long_t *v)
 {
 	return atomic64_fetch_add(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_add_acquire(long i, atomic_long_t *v)
 {
 	return atomic64_fetch_add_acquire(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_add_release(long i, atomic_long_t *v)
 {
 	return atomic64_fetch_add_release(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_add_relaxed(long i, atomic_long_t *v)
 {
 	return atomic64_fetch_add_relaxed(i, v);
 }
 
-static inline void
+static __always_inline void
 atomic_long_sub(long i, atomic_long_t *v)
 {
 	atomic64_sub(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_sub_return(long i, atomic_long_t *v)
 {
 	return atomic64_sub_return(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_sub_return_acquire(long i, atomic_long_t *v)
 {
 	return atomic64_sub_return_acquire(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_sub_return_release(long i, atomic_long_t *v)
 {
 	return atomic64_sub_return_release(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_sub_return_relaxed(long i, atomic_long_t *v)
 {
 	return atomic64_sub_return_relaxed(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_sub(long i, atomic_long_t *v)
 {
 	return atomic64_fetch_sub(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_sub_acquire(long i, atomic_long_t *v)
 {
 	return atomic64_fetch_sub_acquire(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_sub_release(long i, atomic_long_t *v)
 {
 	return atomic64_fetch_sub_release(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v)
 {
 	return atomic64_fetch_sub_relaxed(i, v);
 }
 
-static inline void
+static __always_inline void
 atomic_long_inc(atomic_long_t *v)
 {
 	atomic64_inc(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_inc_return(atomic_long_t *v)
 {
 	return atomic64_inc_return(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_inc_return_acquire(atomic_long_t *v)
 {
 	return atomic64_inc_return_acquire(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_inc_return_release(atomic_long_t *v)
 {
 	return atomic64_inc_return_release(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_inc_return_relaxed(atomic_long_t *v)
 {
 	return atomic64_inc_return_relaxed(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_inc(atomic_long_t *v)
 {
 	return atomic64_fetch_inc(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_inc_acquire(atomic_long_t *v)
 {
 	return atomic64_fetch_inc_acquire(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_inc_release(atomic_long_t *v)
 {
 	return atomic64_fetch_inc_release(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_inc_relaxed(atomic_long_t *v)
 {
 	return atomic64_fetch_inc_relaxed(v);
 }
 
-static inline void
+static __always_inline void
 atomic_long_dec(atomic_long_t *v)
 {
 	atomic64_dec(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_dec_return(atomic_long_t *v)
 {
 	return atomic64_dec_return(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_dec_return_acquire(atomic_long_t *v)
 {
 	return atomic64_dec_return_acquire(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_dec_return_release(atomic_long_t *v)
 {
 	return atomic64_dec_return_release(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_dec_return_relaxed(atomic_long_t *v)
 {
 	return atomic64_dec_return_relaxed(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_dec(atomic_long_t *v)
 {
 	return atomic64_fetch_dec(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_dec_acquire(atomic_long_t *v)
 {
 	return atomic64_fetch_dec_acquire(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_dec_release(atomic_long_t *v)
 {
 	return atomic64_fetch_dec_release(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_dec_relaxed(atomic_long_t *v)
 {
 	return atomic64_fetch_dec_relaxed(v);
 }
 
-static inline void
+static __always_inline void
 atomic_long_and(long i, atomic_long_t *v)
 {
 	atomic64_and(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_and(long i, atomic_long_t *v)
 {
 	return atomic64_fetch_and(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_and_acquire(long i, atomic_long_t *v)
 {
 	return atomic64_fetch_and_acquire(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_and_release(long i, atomic_long_t *v)
 {
 	return atomic64_fetch_and_release(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_and_relaxed(long i, atomic_long_t *v)
 {
 	return atomic64_fetch_and_relaxed(i, v);
 }
 
-static inline void
+static __always_inline void
 atomic_long_andnot(long i, atomic_long_t *v)
 {
 	atomic64_andnot(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_andnot(long i, atomic_long_t *v)
 {
 	return atomic64_fetch_andnot(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v)
 {
 	return atomic64_fetch_andnot_acquire(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_andnot_release(long i, atomic_long_t *v)
 {
 	return atomic64_fetch_andnot_release(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v)
 {
 	return atomic64_fetch_andnot_relaxed(i, v);
 }
 
-static inline void
+static __always_inline void
 atomic_long_or(long i, atomic_long_t *v)
 {
 	atomic64_or(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_or(long i, atomic_long_t *v)
 {
 	return atomic64_fetch_or(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_or_acquire(long i, atomic_long_t *v)
 {
 	return atomic64_fetch_or_acquire(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_or_release(long i, atomic_long_t *v)
 {
 	return atomic64_fetch_or_release(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_or_relaxed(long i, atomic_long_t *v)
 {
 	return atomic64_fetch_or_relaxed(i, v);
 }
 
-static inline void
+static __always_inline void
 atomic_long_xor(long i, atomic_long_t *v)
 {
 	atomic64_xor(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_xor(long i, atomic_long_t *v)
 {
 	return atomic64_fetch_xor(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_xor_acquire(long i, atomic_long_t *v)
 {
 	return atomic64_fetch_xor_acquire(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_xor_release(long i, atomic_long_t *v)
 {
 	return atomic64_fetch_xor_release(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v)
 {
 	return atomic64_fetch_xor_relaxed(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_xchg(atomic_long_t *v, long i)
 {
 	return atomic64_xchg(v, i);
 }
 
-static inline long
+static __always_inline long
 atomic_long_xchg_acquire(atomic_long_t *v, long i)
 {
 	return atomic64_xchg_acquire(v, i);
 }
 
-static inline long
+static __always_inline long
 atomic_long_xchg_release(atomic_long_t *v, long i)
 {
 	return atomic64_xchg_release(v, i);
 }
 
-static inline long
+static __always_inline long
 atomic_long_xchg_relaxed(atomic_long_t *v, long i)
 {
 	return atomic64_xchg_relaxed(v, i);
 }
 
-static inline long
+static __always_inline long
 atomic_long_cmpxchg(atomic_long_t *v, long old, long new)
 {
 	return atomic64_cmpxchg(v, old, new);
 }
 
-static inline long
+static __always_inline long
 atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new)
 {
 	return atomic64_cmpxchg_acquire(v, old, new);
 }
 
-static inline long
+static __always_inline long
 atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new)
 {
 	return atomic64_cmpxchg_release(v, old, new);
 }
 
-static inline long
+static __always_inline long
 atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new)
 {
 	return atomic64_cmpxchg_relaxed(v, old, new);
 }
 
-static inline bool
+static __always_inline bool
 atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new)
 {
 	return atomic64_try_cmpxchg(v, (s64 *)old, new);
 }
 
-static inline bool
+static __always_inline bool
 atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new)
 {
 	return atomic64_try_cmpxchg_acquire(v, (s64 *)old, new);
 }
 
-static inline bool
+static __always_inline bool
 atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new)
 {
 	return atomic64_try_cmpxchg_release(v, (s64 *)old, new);
 }
 
-static inline bool
+static __always_inline bool
 atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new)
 {
 	return atomic64_try_cmpxchg_relaxed(v, (s64 *)old, new);
 }
 
-static inline bool
+static __always_inline bool
 atomic_long_sub_and_test(long i, atomic_long_t *v)
 {
 	return atomic64_sub_and_test(i, v);
 }
 
-static inline bool
+static __always_inline bool
 atomic_long_dec_and_test(atomic_long_t *v)
 {
 	return atomic64_dec_and_test(v);
 }
 
-static inline bool
+static __always_inline bool
 atomic_long_inc_and_test(atomic_long_t *v)
 {
 	return atomic64_inc_and_test(v);
 }
 
-static inline bool
+static __always_inline bool
 atomic_long_add_negative(long i, atomic_long_t *v)
 {
 	return atomic64_add_negative(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u)
 {
 	return atomic64_fetch_add_unless(v, a, u);
 }
 
-static inline bool
+static __always_inline bool
 atomic_long_add_unless(atomic_long_t *v, long a, long u)
 {
 	return atomic64_add_unless(v, a, u);
 }
 
-static inline bool
+static __always_inline bool
 atomic_long_inc_not_zero(atomic_long_t *v)
 {
 	return atomic64_inc_not_zero(v);
 }
 
-static inline bool
+static __always_inline bool
 atomic_long_inc_unless_negative(atomic_long_t *v)
 {
 	return atomic64_inc_unless_negative(v);
 }
 
-static inline bool
+static __always_inline bool
 atomic_long_dec_unless_positive(atomic_long_t *v)
 {
 	return atomic64_dec_unless_positive(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_dec_if_positive(atomic_long_t *v)
 {
 	return atomic64_dec_if_positive(v);
@@ -516,493 +517,493 @@
 
 #else /* CONFIG_64BIT */
 
-static inline long
+static __always_inline long
 atomic_long_read(const atomic_long_t *v)
 {
 	return atomic_read(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_read_acquire(const atomic_long_t *v)
 {
 	return atomic_read_acquire(v);
 }
 
-static inline void
+static __always_inline void
 atomic_long_set(atomic_long_t *v, long i)
 {
 	atomic_set(v, i);
 }
 
-static inline void
+static __always_inline void
 atomic_long_set_release(atomic_long_t *v, long i)
 {
 	atomic_set_release(v, i);
 }
 
-static inline void
+static __always_inline void
 atomic_long_add(long i, atomic_long_t *v)
 {
 	atomic_add(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_add_return(long i, atomic_long_t *v)
 {
 	return atomic_add_return(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_add_return_acquire(long i, atomic_long_t *v)
 {
 	return atomic_add_return_acquire(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_add_return_release(long i, atomic_long_t *v)
 {
 	return atomic_add_return_release(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_add_return_relaxed(long i, atomic_long_t *v)
 {
 	return atomic_add_return_relaxed(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_add(long i, atomic_long_t *v)
 {
 	return atomic_fetch_add(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_add_acquire(long i, atomic_long_t *v)
 {
 	return atomic_fetch_add_acquire(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_add_release(long i, atomic_long_t *v)
 {
 	return atomic_fetch_add_release(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_add_relaxed(long i, atomic_long_t *v)
 {
 	return atomic_fetch_add_relaxed(i, v);
 }
 
-static inline void
+static __always_inline void
 atomic_long_sub(long i, atomic_long_t *v)
 {
 	atomic_sub(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_sub_return(long i, atomic_long_t *v)
 {
 	return atomic_sub_return(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_sub_return_acquire(long i, atomic_long_t *v)
 {
 	return atomic_sub_return_acquire(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_sub_return_release(long i, atomic_long_t *v)
 {
 	return atomic_sub_return_release(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_sub_return_relaxed(long i, atomic_long_t *v)
 {
 	return atomic_sub_return_relaxed(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_sub(long i, atomic_long_t *v)
 {
 	return atomic_fetch_sub(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_sub_acquire(long i, atomic_long_t *v)
 {
 	return atomic_fetch_sub_acquire(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_sub_release(long i, atomic_long_t *v)
 {
 	return atomic_fetch_sub_release(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v)
 {
 	return atomic_fetch_sub_relaxed(i, v);
 }
 
-static inline void
+static __always_inline void
 atomic_long_inc(atomic_long_t *v)
 {
 	atomic_inc(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_inc_return(atomic_long_t *v)
 {
 	return atomic_inc_return(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_inc_return_acquire(atomic_long_t *v)
 {
 	return atomic_inc_return_acquire(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_inc_return_release(atomic_long_t *v)
 {
 	return atomic_inc_return_release(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_inc_return_relaxed(atomic_long_t *v)
 {
 	return atomic_inc_return_relaxed(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_inc(atomic_long_t *v)
 {
 	return atomic_fetch_inc(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_inc_acquire(atomic_long_t *v)
 {
 	return atomic_fetch_inc_acquire(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_inc_release(atomic_long_t *v)
 {
 	return atomic_fetch_inc_release(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_inc_relaxed(atomic_long_t *v)
 {
 	return atomic_fetch_inc_relaxed(v);
 }
 
-static inline void
+static __always_inline void
 atomic_long_dec(atomic_long_t *v)
 {
 	atomic_dec(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_dec_return(atomic_long_t *v)
 {
 	return atomic_dec_return(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_dec_return_acquire(atomic_long_t *v)
 {
 	return atomic_dec_return_acquire(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_dec_return_release(atomic_long_t *v)
 {
 	return atomic_dec_return_release(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_dec_return_relaxed(atomic_long_t *v)
 {
 	return atomic_dec_return_relaxed(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_dec(atomic_long_t *v)
 {
 	return atomic_fetch_dec(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_dec_acquire(atomic_long_t *v)
 {
 	return atomic_fetch_dec_acquire(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_dec_release(atomic_long_t *v)
 {
 	return atomic_fetch_dec_release(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_dec_relaxed(atomic_long_t *v)
 {
 	return atomic_fetch_dec_relaxed(v);
 }
 
-static inline void
+static __always_inline void
 atomic_long_and(long i, atomic_long_t *v)
 {
 	atomic_and(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_and(long i, atomic_long_t *v)
 {
 	return atomic_fetch_and(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_and_acquire(long i, atomic_long_t *v)
 {
 	return atomic_fetch_and_acquire(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_and_release(long i, atomic_long_t *v)
 {
 	return atomic_fetch_and_release(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_and_relaxed(long i, atomic_long_t *v)
 {
 	return atomic_fetch_and_relaxed(i, v);
 }
 
-static inline void
+static __always_inline void
 atomic_long_andnot(long i, atomic_long_t *v)
 {
 	atomic_andnot(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_andnot(long i, atomic_long_t *v)
 {
 	return atomic_fetch_andnot(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v)
 {
 	return atomic_fetch_andnot_acquire(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_andnot_release(long i, atomic_long_t *v)
 {
 	return atomic_fetch_andnot_release(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v)
 {
 	return atomic_fetch_andnot_relaxed(i, v);
 }
 
-static inline void
+static __always_inline void
 atomic_long_or(long i, atomic_long_t *v)
 {
 	atomic_or(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_or(long i, atomic_long_t *v)
 {
 	return atomic_fetch_or(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_or_acquire(long i, atomic_long_t *v)
 {
 	return atomic_fetch_or_acquire(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_or_release(long i, atomic_long_t *v)
 {
 	return atomic_fetch_or_release(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_or_relaxed(long i, atomic_long_t *v)
 {
 	return atomic_fetch_or_relaxed(i, v);
 }
 
-static inline void
+static __always_inline void
 atomic_long_xor(long i, atomic_long_t *v)
 {
 	atomic_xor(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_xor(long i, atomic_long_t *v)
 {
 	return atomic_fetch_xor(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_xor_acquire(long i, atomic_long_t *v)
 {
 	return atomic_fetch_xor_acquire(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_xor_release(long i, atomic_long_t *v)
 {
 	return atomic_fetch_xor_release(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v)
 {
 	return atomic_fetch_xor_relaxed(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_xchg(atomic_long_t *v, long i)
 {
 	return atomic_xchg(v, i);
 }
 
-static inline long
+static __always_inline long
 atomic_long_xchg_acquire(atomic_long_t *v, long i)
 {
 	return atomic_xchg_acquire(v, i);
 }
 
-static inline long
+static __always_inline long
 atomic_long_xchg_release(atomic_long_t *v, long i)
 {
 	return atomic_xchg_release(v, i);
 }
 
-static inline long
+static __always_inline long
 atomic_long_xchg_relaxed(atomic_long_t *v, long i)
 {
 	return atomic_xchg_relaxed(v, i);
 }
 
-static inline long
+static __always_inline long
 atomic_long_cmpxchg(atomic_long_t *v, long old, long new)
 {
 	return atomic_cmpxchg(v, old, new);
 }
 
-static inline long
+static __always_inline long
 atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new)
 {
 	return atomic_cmpxchg_acquire(v, old, new);
 }
 
-static inline long
+static __always_inline long
 atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new)
 {
 	return atomic_cmpxchg_release(v, old, new);
 }
 
-static inline long
+static __always_inline long
 atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new)
 {
 	return atomic_cmpxchg_relaxed(v, old, new);
 }
 
-static inline bool
+static __always_inline bool
 atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new)
 {
 	return atomic_try_cmpxchg(v, (int *)old, new);
 }
 
-static inline bool
+static __always_inline bool
 atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new)
 {
 	return atomic_try_cmpxchg_acquire(v, (int *)old, new);
 }
 
-static inline bool
+static __always_inline bool
 atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new)
 {
 	return atomic_try_cmpxchg_release(v, (int *)old, new);
 }
 
-static inline bool
+static __always_inline bool
 atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new)
 {
 	return atomic_try_cmpxchg_relaxed(v, (int *)old, new);
 }
 
-static inline bool
+static __always_inline bool
 atomic_long_sub_and_test(long i, atomic_long_t *v)
 {
 	return atomic_sub_and_test(i, v);
 }
 
-static inline bool
+static __always_inline bool
 atomic_long_dec_and_test(atomic_long_t *v)
 {
 	return atomic_dec_and_test(v);
 }
 
-static inline bool
+static __always_inline bool
 atomic_long_inc_and_test(atomic_long_t *v)
 {
 	return atomic_inc_and_test(v);
 }
 
-static inline bool
+static __always_inline bool
 atomic_long_add_negative(long i, atomic_long_t *v)
 {
 	return atomic_add_negative(i, v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u)
 {
 	return atomic_fetch_add_unless(v, a, u);
 }
 
-static inline bool
+static __always_inline bool
 atomic_long_add_unless(atomic_long_t *v, long a, long u)
 {
 	return atomic_add_unless(v, a, u);
 }
 
-static inline bool
+static __always_inline bool
 atomic_long_inc_not_zero(atomic_long_t *v)
 {
 	return atomic_inc_not_zero(v);
 }
 
-static inline bool
+static __always_inline bool
 atomic_long_inc_unless_negative(atomic_long_t *v)
 {
 	return atomic_inc_unless_negative(v);
 }
 
-static inline bool
+static __always_inline bool
 atomic_long_dec_unless_positive(atomic_long_t *v)
 {
 	return atomic_dec_unless_positive(v);
 }
 
-static inline long
+static __always_inline long
 atomic_long_dec_if_positive(atomic_long_t *v)
 {
 	return atomic_dec_if_positive(v);
@@ -1010,4 +1011,4 @@
 
 #endif /* CONFIG_64BIT */
 #endif /* _ASM_GENERIC_ATOMIC_LONG_H */
-// 77558968132ce4f911ad53f6f52ce423006f6268
+// a624200981f552b2c6be4f32fe44da8289f30d87
diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index 286867f..11f96f4 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -159,8 +159,6 @@
  * resource counting etc..
  */
 
-#define ATOMIC_INIT(i)	{ (i) }
-
 /**
  * atomic_read - read atomic variable
  * @v: pointer of type atomic_t
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 85b28eb..640f094 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -14,6 +14,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/compiler.h>
+#include <asm/rwonce.h>
 
 #ifndef nop
 #define nop()	asm volatile ("nop")
@@ -46,10 +47,6 @@
 #define dma_wmb()	wmb()
 #endif
 
-#ifndef read_barrier_depends
-#define read_barrier_depends()		do { } while (0)
-#endif
-
 #ifndef __smp_mb
 #define __smp_mb()	mb()
 #endif
@@ -62,10 +59,6 @@
 #define __smp_wmb()	wmb()
 #endif
 
-#ifndef __smp_read_barrier_depends
-#define __smp_read_barrier_depends()	read_barrier_depends()
-#endif
-
 #ifdef CONFIG_SMP
 
 #ifndef smp_mb
@@ -80,10 +73,6 @@
 #define smp_wmb()	__smp_wmb()
 #endif
 
-#ifndef smp_read_barrier_depends
-#define smp_read_barrier_depends()	__smp_read_barrier_depends()
-#endif
-
 #else	/* !CONFIG_SMP */
 
 #ifndef smp_mb
@@ -98,10 +87,6 @@
 #define smp_wmb()	barrier()
 #endif
 
-#ifndef smp_read_barrier_depends
-#define smp_read_barrier_depends()	do { } while (0)
-#endif
-
 #endif	/* CONFIG_SMP */
 
 #ifndef __smp_store_mb
@@ -128,10 +113,10 @@
 #ifndef __smp_load_acquire
 #define __smp_load_acquire(p)						\
 ({									\
-	typeof(*p) ___p1 = READ_ONCE(*p);				\
+	__unqual_scalar_typeof(*p) ___p1 = READ_ONCE(*p);		\
 	compiletime_assert_atomic_type(*p);				\
 	__smp_mb();							\
-	___p1;								\
+	(typeof(*p))___p1;						\
 })
 #endif
 
@@ -183,10 +168,10 @@
 #ifndef smp_load_acquire
 #define smp_load_acquire(p)						\
 ({									\
-	typeof(*p) ___p1 = READ_ONCE(*p);				\
+	__unqual_scalar_typeof(*p) ___p1 = READ_ONCE(*p);		\
 	compiletime_assert_atomic_type(*p);				\
 	barrier();							\
-	___p1;								\
+	(typeof(*p))___p1;						\
 })
 #endif
 
@@ -196,7 +181,6 @@
 #define virt_mb() __smp_mb()
 #define virt_rmb() __smp_rmb()
 #define virt_wmb() __smp_wmb()
-#define virt_read_barrier_depends() __smp_read_barrier_depends()
 #define virt_store_mb(var, value) __smp_store_mb(var, value)
 #define virt_mb__before_atomic() __smp_mb__before_atomic()
 #define virt_mb__after_atomic()	__smp_mb__after_atomic()
@@ -229,14 +213,14 @@
 #ifndef smp_cond_load_relaxed
 #define smp_cond_load_relaxed(ptr, cond_expr) ({		\
 	typeof(ptr) __PTR = (ptr);				\
-	typeof(*ptr) VAL;					\
+	__unqual_scalar_typeof(*ptr) VAL;			\
 	for (;;) {						\
 		VAL = READ_ONCE(*__PTR);			\
 		if (cond_expr)					\
 			break;					\
 		cpu_relax();					\
 	}							\
-	VAL;							\
+	(typeof(*ptr))VAL;					\
 })
 #endif
 
@@ -250,12 +234,22 @@
  */
 #ifndef smp_cond_load_acquire
 #define smp_cond_load_acquire(ptr, cond_expr) ({		\
-	typeof(*ptr) _val;					\
+	__unqual_scalar_typeof(*ptr) _val;			\
 	_val = smp_cond_load_relaxed(ptr, cond_expr);		\
 	smp_acquire__after_ctrl_dep();				\
-	_val;							\
+	(typeof(*ptr))_val;					\
 })
 #endif
 
+/*
+ * pmem_wmb() ensures that all stores for which the modification
+ * are written to persistent storage by preceding instructions have
+ * updated persistent storage before any data  access or data transfer
+ * caused by subsequent instructions is initiated.
+ */
+#ifndef pmem_wmb
+#define pmem_wmb()	wmb()
+#endif
+
 #endif /* !__ASSEMBLY__ */
 #endif /* __ASM_GENERIC_BARRIER_H */
diff --git a/include/asm-generic/bitops-instrumented.h b/include/asm-generic/bitops-instrumented.h
deleted file mode 100644
index ddd1c6d..0000000
--- a/include/asm-generic/bitops-instrumented.h
+++ /dev/null
@@ -1,263 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-
-/*
- * This file provides wrappers with sanitizer instrumentation for bit
- * operations.
- *
- * To use this functionality, an arch's bitops.h file needs to define each of
- * the below bit operations with an arch_ prefix (e.g. arch_set_bit(),
- * arch___set_bit(), etc.).
- */
-#ifndef _ASM_GENERIC_BITOPS_INSTRUMENTED_H
-#define _ASM_GENERIC_BITOPS_INSTRUMENTED_H
-
-#include <linux/kasan-checks.h>
-
-/**
- * set_bit - Atomically set a bit in memory
- * @nr: the bit to set
- * @addr: the address to start counting from
- *
- * This is a relaxed atomic operation (no implied memory barriers).
- *
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static inline void set_bit(long nr, volatile unsigned long *addr)
-{
-	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
-	arch_set_bit(nr, addr);
-}
-
-/**
- * __set_bit - Set a bit in memory
- * @nr: the bit to set
- * @addr: the address to start counting from
- *
- * Unlike set_bit(), this function is non-atomic. If it is called on the same
- * region of memory concurrently, the effect may be that only one operation
- * succeeds.
- */
-static inline void __set_bit(long nr, volatile unsigned long *addr)
-{
-	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
-	arch___set_bit(nr, addr);
-}
-
-/**
- * clear_bit - Clears a bit in memory
- * @nr: Bit to clear
- * @addr: Address to start counting from
- *
- * This is a relaxed atomic operation (no implied memory barriers).
- */
-static inline void clear_bit(long nr, volatile unsigned long *addr)
-{
-	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
-	arch_clear_bit(nr, addr);
-}
-
-/**
- * __clear_bit - Clears a bit in memory
- * @nr: the bit to clear
- * @addr: the address to start counting from
- *
- * Unlike clear_bit(), this function is non-atomic. If it is called on the same
- * region of memory concurrently, the effect may be that only one operation
- * succeeds.
- */
-static inline void __clear_bit(long nr, volatile unsigned long *addr)
-{
-	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
-	arch___clear_bit(nr, addr);
-}
-
-/**
- * clear_bit_unlock - Clear a bit in memory, for unlock
- * @nr: the bit to set
- * @addr: the address to start counting from
- *
- * This operation is atomic and provides release barrier semantics.
- */
-static inline void clear_bit_unlock(long nr, volatile unsigned long *addr)
-{
-	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
-	arch_clear_bit_unlock(nr, addr);
-}
-
-/**
- * __clear_bit_unlock - Clears a bit in memory
- * @nr: Bit to clear
- * @addr: Address to start counting from
- *
- * This is a non-atomic operation but implies a release barrier before the
- * memory operation. It can be used for an unlock if no other CPUs can
- * concurrently modify other bits in the word.
- */
-static inline void __clear_bit_unlock(long nr, volatile unsigned long *addr)
-{
-	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
-	arch___clear_bit_unlock(nr, addr);
-}
-
-/**
- * change_bit - Toggle a bit in memory
- * @nr: Bit to change
- * @addr: Address to start counting from
- *
- * This is a relaxed atomic operation (no implied memory barriers).
- *
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static inline void change_bit(long nr, volatile unsigned long *addr)
-{
-	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
-	arch_change_bit(nr, addr);
-}
-
-/**
- * __change_bit - Toggle a bit in memory
- * @nr: the bit to change
- * @addr: the address to start counting from
- *
- * Unlike change_bit(), this function is non-atomic. If it is called on the same
- * region of memory concurrently, the effect may be that only one operation
- * succeeds.
- */
-static inline void __change_bit(long nr, volatile unsigned long *addr)
-{
-	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
-	arch___change_bit(nr, addr);
-}
-
-/**
- * test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This is an atomic fully-ordered operation (implied full memory barrier).
- */
-static inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
-{
-	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
-	return arch_test_and_set_bit(nr, addr);
-}
-
-/**
- * __test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is non-atomic. If two instances of this operation race, one
- * can appear to succeed but actually fail.
- */
-static inline bool __test_and_set_bit(long nr, volatile unsigned long *addr)
-{
-	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
-	return arch___test_and_set_bit(nr, addr);
-}
-
-/**
- * test_and_set_bit_lock - Set a bit and return its old value, for lock
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is atomic and provides acquire barrier semantics if
- * the returned value is 0.
- * It can be used to implement bit locks.
- */
-static inline bool test_and_set_bit_lock(long nr, volatile unsigned long *addr)
-{
-	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
-	return arch_test_and_set_bit_lock(nr, addr);
-}
-
-/**
- * test_and_clear_bit - Clear a bit and return its old value
- * @nr: Bit to clear
- * @addr: Address to count from
- *
- * This is an atomic fully-ordered operation (implied full memory barrier).
- */
-static inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
-{
-	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
-	return arch_test_and_clear_bit(nr, addr);
-}
-
-/**
- * __test_and_clear_bit - Clear a bit and return its old value
- * @nr: Bit to clear
- * @addr: Address to count from
- *
- * This operation is non-atomic. If two instances of this operation race, one
- * can appear to succeed but actually fail.
- */
-static inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr)
-{
-	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
-	return arch___test_and_clear_bit(nr, addr);
-}
-
-/**
- * test_and_change_bit - Change a bit and return its old value
- * @nr: Bit to change
- * @addr: Address to count from
- *
- * This is an atomic fully-ordered operation (implied full memory barrier).
- */
-static inline bool test_and_change_bit(long nr, volatile unsigned long *addr)
-{
-	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
-	return arch_test_and_change_bit(nr, addr);
-}
-
-/**
- * __test_and_change_bit - Change a bit and return its old value
- * @nr: Bit to change
- * @addr: Address to count from
- *
- * This operation is non-atomic. If two instances of this operation race, one
- * can appear to succeed but actually fail.
- */
-static inline bool __test_and_change_bit(long nr, volatile unsigned long *addr)
-{
-	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
-	return arch___test_and_change_bit(nr, addr);
-}
-
-/**
- * test_bit - Determine whether a bit is set
- * @nr: bit number to test
- * @addr: Address to start counting from
- */
-static inline bool test_bit(long nr, const volatile unsigned long *addr)
-{
-	kasan_check_read(addr + BIT_WORD(nr), sizeof(long));
-	return arch_test_bit(nr, addr);
-}
-
-#if defined(arch_clear_bit_unlock_is_negative_byte)
-/**
- * clear_bit_unlock_is_negative_byte - Clear a bit in memory and test if bottom
- *                                     byte is negative, for unlock.
- * @nr: the bit to clear
- * @addr: the address to start counting from
- *
- * This operation is atomic and provides release barrier semantics.
- *
- * This is a bit of a one-trick-pony for the filemap code, which clears
- * PG_locked and tests PG_waiters,
- */
-static inline bool
-clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr)
-{
-	kasan_check_write(addr + BIT_WORD(nr), sizeof(long));
-	return arch_clear_bit_unlock_is_negative_byte(nr, addr);
-}
-/* Let everybody know we have it. */
-#define clear_bit_unlock_is_negative_byte clear_bit_unlock_is_negative_byte
-#endif
-
-#endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_H */
diff --git a/include/asm-generic/bitops.h b/include/asm-generic/bitops.h
index bfc96bf..df9b5bc 100644
--- a/include/asm-generic/bitops.h
+++ b/include/asm-generic/bitops.h
@@ -4,8 +4,9 @@
 
 /*
  * For the benefit of those who are trying to port Linux to another
- * architecture, here are some C-language equivalents.  You should
- * recode these in the native assembly language, if at all possible.
+ * architecture, here are some C-language equivalents.  They should
+ * generate reasonable code, so take a look at what your compiler spits
+ * out before rolling your own buggy implementation in assembly language.
  *
  * C language equivalents written by Theodore Ts'o, 9/26/92
  */
diff --git a/include/asm-generic/bitops/find.h b/include/asm-generic/bitops/find.h
index 8a1ee10..9fdf213 100644
--- a/include/asm-generic/bitops/find.h
+++ b/include/asm-generic/bitops/find.h
@@ -80,4 +80,21 @@
 
 #endif /* CONFIG_GENERIC_FIND_FIRST_BIT */
 
+/**
+ * find_next_clump8 - find next 8-bit clump with set bits in a memory region
+ * @clump: location to store copy of found clump
+ * @addr: address to base the search on
+ * @size: bitmap size in number of bits
+ * @offset: bit offset at which to start searching
+ *
+ * Returns the bit offset for the next set clump; the found clump value is
+ * copied to the location pointed by @clump. If no bits are set, returns @size.
+ */
+extern unsigned long find_next_clump8(unsigned long *clump,
+				      const unsigned long *addr,
+				      unsigned long size, unsigned long offset);
+
+#define find_first_clump8(clump, bits, size) \
+	find_next_clump8((clump), (bits), (size), 0)
+
 #endif /*_ASM_GENERIC_BITOPS_FIND_H_ */
diff --git a/include/asm-generic/bitops/instrumented-atomic.h b/include/asm-generic/bitops/instrumented-atomic.h
new file mode 100644
index 0000000..81915dc
--- /dev/null
+++ b/include/asm-generic/bitops/instrumented-atomic.h
@@ -0,0 +1,100 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * This file provides wrappers with sanitizer instrumentation for atomic bit
+ * operations.
+ *
+ * To use this functionality, an arch's bitops.h file needs to define each of
+ * the below bit operations with an arch_ prefix (e.g. arch_set_bit(),
+ * arch___set_bit(), etc.).
+ */
+#ifndef _ASM_GENERIC_BITOPS_INSTRUMENTED_ATOMIC_H
+#define _ASM_GENERIC_BITOPS_INSTRUMENTED_ATOMIC_H
+
+#include <linux/instrumented.h>
+
+/**
+ * set_bit - Atomically set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This is a relaxed atomic operation (no implied memory barriers).
+ *
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static inline void set_bit(long nr, volatile unsigned long *addr)
+{
+	instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
+	arch_set_bit(nr, addr);
+}
+
+/**
+ * clear_bit - Clears a bit in memory
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ *
+ * This is a relaxed atomic operation (no implied memory barriers).
+ */
+static inline void clear_bit(long nr, volatile unsigned long *addr)
+{
+	instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
+	arch_clear_bit(nr, addr);
+}
+
+/**
+ * change_bit - Toggle a bit in memory
+ * @nr: Bit to change
+ * @addr: Address to start counting from
+ *
+ * This is a relaxed atomic operation (no implied memory barriers).
+ *
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static inline void change_bit(long nr, volatile unsigned long *addr)
+{
+	instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
+	arch_change_bit(nr, addr);
+}
+
+/**
+ * test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This is an atomic fully-ordered operation (implied full memory barrier).
+ */
+static inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
+{
+	instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long));
+	return arch_test_and_set_bit(nr, addr);
+}
+
+/**
+ * test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This is an atomic fully-ordered operation (implied full memory barrier).
+ */
+static inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
+{
+	instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long));
+	return arch_test_and_clear_bit(nr, addr);
+}
+
+/**
+ * test_and_change_bit - Change a bit and return its old value
+ * @nr: Bit to change
+ * @addr: Address to count from
+ *
+ * This is an atomic fully-ordered operation (implied full memory barrier).
+ */
+static inline bool test_and_change_bit(long nr, volatile unsigned long *addr)
+{
+	instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long));
+	return arch_test_and_change_bit(nr, addr);
+}
+
+#endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */
diff --git a/include/asm-generic/bitops/instrumented-lock.h b/include/asm-generic/bitops/instrumented-lock.h
new file mode 100644
index 0000000..75ef606
--- /dev/null
+++ b/include/asm-generic/bitops/instrumented-lock.h
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * This file provides wrappers with sanitizer instrumentation for bit
+ * locking operations.
+ *
+ * To use this functionality, an arch's bitops.h file needs to define each of
+ * the below bit operations with an arch_ prefix (e.g. arch_set_bit(),
+ * arch___set_bit(), etc.).
+ */
+#ifndef _ASM_GENERIC_BITOPS_INSTRUMENTED_LOCK_H
+#define _ASM_GENERIC_BITOPS_INSTRUMENTED_LOCK_H
+
+#include <linux/instrumented.h>
+
+/**
+ * clear_bit_unlock - Clear a bit in memory, for unlock
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This operation is atomic and provides release barrier semantics.
+ */
+static inline void clear_bit_unlock(long nr, volatile unsigned long *addr)
+{
+	instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
+	arch_clear_bit_unlock(nr, addr);
+}
+
+/**
+ * __clear_bit_unlock - Clears a bit in memory
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ *
+ * This is a non-atomic operation but implies a release barrier before the
+ * memory operation. It can be used for an unlock if no other CPUs can
+ * concurrently modify other bits in the word.
+ */
+static inline void __clear_bit_unlock(long nr, volatile unsigned long *addr)
+{
+	instrument_write(addr + BIT_WORD(nr), sizeof(long));
+	arch___clear_bit_unlock(nr, addr);
+}
+
+/**
+ * test_and_set_bit_lock - Set a bit and return its old value, for lock
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is atomic and provides acquire barrier semantics if
+ * the returned value is 0.
+ * It can be used to implement bit locks.
+ */
+static inline bool test_and_set_bit_lock(long nr, volatile unsigned long *addr)
+{
+	instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long));
+	return arch_test_and_set_bit_lock(nr, addr);
+}
+
+#if defined(arch_clear_bit_unlock_is_negative_byte)
+/**
+ * clear_bit_unlock_is_negative_byte - Clear a bit in memory and test if bottom
+ *                                     byte is negative, for unlock.
+ * @nr: the bit to clear
+ * @addr: the address to start counting from
+ *
+ * This operation is atomic and provides release barrier semantics.
+ *
+ * This is a bit of a one-trick-pony for the filemap code, which clears
+ * PG_locked and tests PG_waiters,
+ */
+static inline bool
+clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr)
+{
+	instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
+	return arch_clear_bit_unlock_is_negative_byte(nr, addr);
+}
+/* Let everybody know we have it. */
+#define clear_bit_unlock_is_negative_byte clear_bit_unlock_is_negative_byte
+#endif
+
+#endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_LOCK_H */
diff --git a/include/asm-generic/bitops/instrumented-non-atomic.h b/include/asm-generic/bitops/instrumented-non-atomic.h
new file mode 100644
index 0000000..37363d5
--- /dev/null
+++ b/include/asm-generic/bitops/instrumented-non-atomic.h
@@ -0,0 +1,138 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * This file provides wrappers with sanitizer instrumentation for non-atomic
+ * bit operations.
+ *
+ * To use this functionality, an arch's bitops.h file needs to define each of
+ * the below bit operations with an arch_ prefix (e.g. arch_set_bit(),
+ * arch___set_bit(), etc.).
+ */
+#ifndef _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H
+#define _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H
+
+#include <linux/instrumented.h>
+
+/**
+ * __set_bit - Set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * Unlike set_bit(), this function is non-atomic. If it is called on the same
+ * region of memory concurrently, the effect may be that only one operation
+ * succeeds.
+ */
+static inline void __set_bit(long nr, volatile unsigned long *addr)
+{
+	instrument_write(addr + BIT_WORD(nr), sizeof(long));
+	arch___set_bit(nr, addr);
+}
+
+/**
+ * __clear_bit - Clears a bit in memory
+ * @nr: the bit to clear
+ * @addr: the address to start counting from
+ *
+ * Unlike clear_bit(), this function is non-atomic. If it is called on the same
+ * region of memory concurrently, the effect may be that only one operation
+ * succeeds.
+ */
+static inline void __clear_bit(long nr, volatile unsigned long *addr)
+{
+	instrument_write(addr + BIT_WORD(nr), sizeof(long));
+	arch___clear_bit(nr, addr);
+}
+
+/**
+ * __change_bit - Toggle a bit in memory
+ * @nr: the bit to change
+ * @addr: the address to start counting from
+ *
+ * Unlike change_bit(), this function is non-atomic. If it is called on the same
+ * region of memory concurrently, the effect may be that only one operation
+ * succeeds.
+ */
+static inline void __change_bit(long nr, volatile unsigned long *addr)
+{
+	instrument_write(addr + BIT_WORD(nr), sizeof(long));
+	arch___change_bit(nr, addr);
+}
+
+static inline void __instrument_read_write_bitop(long nr, volatile unsigned long *addr)
+{
+	if (IS_ENABLED(CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC)) {
+		/*
+		 * We treat non-atomic read-write bitops a little more special.
+		 * Given the operations here only modify a single bit, assuming
+		 * non-atomicity of the writer is sufficient may be reasonable
+		 * for certain usage (and follows the permissible nature of the
+		 * assume-plain-writes-atomic rule):
+		 * 1. report read-modify-write races -> check read;
+		 * 2. do not report races with marked readers, but do report
+		 *    races with unmarked readers -> check "atomic" write.
+		 */
+		kcsan_check_read(addr + BIT_WORD(nr), sizeof(long));
+		/*
+		 * Use generic write instrumentation, in case other sanitizers
+		 * or tools are enabled alongside KCSAN.
+		 */
+		instrument_write(addr + BIT_WORD(nr), sizeof(long));
+	} else {
+		instrument_read_write(addr + BIT_WORD(nr), sizeof(long));
+	}
+}
+
+/**
+ * __test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic. If two instances of this operation race, one
+ * can appear to succeed but actually fail.
+ */
+static inline bool __test_and_set_bit(long nr, volatile unsigned long *addr)
+{
+	__instrument_read_write_bitop(nr, addr);
+	return arch___test_and_set_bit(nr, addr);
+}
+
+/**
+ * __test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic. If two instances of this operation race, one
+ * can appear to succeed but actually fail.
+ */
+static inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr)
+{
+	__instrument_read_write_bitop(nr, addr);
+	return arch___test_and_clear_bit(nr, addr);
+}
+
+/**
+ * __test_and_change_bit - Change a bit and return its old value
+ * @nr: Bit to change
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic. If two instances of this operation race, one
+ * can appear to succeed but actually fail.
+ */
+static inline bool __test_and_change_bit(long nr, volatile unsigned long *addr)
+{
+	__instrument_read_write_bitop(nr, addr);
+	return arch___test_and_change_bit(nr, addr);
+}
+
+/**
+ * test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static inline bool test_bit(long nr, const volatile unsigned long *addr)
+{
+	instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long));
+	return arch_test_bit(nr, addr);
+}
+
+#endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */
diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index 384b5c8..76a10e0 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -3,6 +3,7 @@
 #define _ASM_GENERIC_BUG_H
 
 #include <linux/compiler.h>
+#include <linux/instrumentation.h>
 
 #define CUT_HERE		"------------[ cut here ]------------\n"
 
@@ -83,14 +84,19 @@
 void warn_slowpath_fmt(const char *file, const int line, unsigned taint,
 		       const char *fmt, ...);
 #define __WARN()		__WARN_printf(TAINT_WARN, NULL)
-#define __WARN_printf(taint, arg...)					\
-	warn_slowpath_fmt(__FILE__, __LINE__, taint, arg)
+#define __WARN_printf(taint, arg...) do {				\
+		instrumentation_begin();				\
+		warn_slowpath_fmt(__FILE__, __LINE__, taint, arg);	\
+		instrumentation_end();					\
+	} while (0)
 #else
 extern __printf(1, 2) void __warn_printk(const char *fmt, ...);
 #define __WARN()		__WARN_FLAGS(BUGFLAG_TAINT(TAINT_WARN))
 #define __WARN_printf(taint, arg...) do {				\
+		instrumentation_begin();				\
 		__warn_printk(arg);					\
 		__WARN_FLAGS(BUGFLAG_NO_CUT_HERE | BUGFLAG_TAINT(taint));\
+		instrumentation_end();					\
 	} while (0)
 #define WARN_ON_ONCE(condition) ({				\
 	int __ret_warn_on = !!(condition);			\
@@ -135,7 +141,7 @@
 
 #ifndef WARN_ON_ONCE
 #define WARN_ON_ONCE(condition)	({				\
-	static bool __section(.data.once) __warned;		\
+	static bool __section(".data.once") __warned;		\
 	int __ret_warn_once = !!(condition);			\
 								\
 	if (unlikely(__ret_warn_once && !__warned)) {		\
@@ -147,7 +153,7 @@
 #endif
 
 #define WARN_ONCE(condition, format...)	({			\
-	static bool __section(.data.once) __warned;		\
+	static bool __section(".data.once") __warned;		\
 	int __ret_warn_once = !!(condition);			\
 								\
 	if (unlikely(__ret_warn_once && !__warned)) {		\
@@ -158,7 +164,7 @@
 })
 
 #define WARN_TAINT_ONCE(condition, taint, format...)	({	\
-	static bool __section(.data.once) __warned;		\
+	static bool __section(".data.once") __warned;		\
 	int __ret_warn_once = !!(condition);			\
 								\
 	if (unlikely(__ret_warn_once && !__warned)) {		\
diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h
index cac7404..4a674db 100644
--- a/include/asm-generic/cacheflush.h
+++ b/include/asm-generic/cacheflush.h
@@ -1,11 +1,11 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __ASM_CACHEFLUSH_H
-#define __ASM_CACHEFLUSH_H
+#ifndef _ASM_GENERIC_CACHEFLUSH_H
+#define _ASM_GENERIC_CACHEFLUSH_H
 
-/* Keep includes the same across arches.  */
-#include <linux/mm.h>
-
-#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
+struct mm_struct;
+struct vm_area_struct;
+struct page;
+struct address_space;
 
 /*
  * The cache doesn't need to be flushed when TLB entries change when
@@ -45,12 +45,14 @@
 }
 #endif
 
-#ifndef flush_dcache_page
+#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
 static inline void flush_dcache_page(struct page *page)
 {
 }
+#define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 0
 #endif
 
+
 #ifndef flush_dcache_mmap_lock
 static inline void flush_dcache_mmap_lock(struct address_space *mapping)
 {
@@ -69,6 +71,10 @@
 }
 #endif
 
+#ifndef flush_icache_user_range
+#define flush_icache_user_range flush_icache_range
+#endif
+
 #ifndef flush_icache_page
 static inline void flush_icache_page(struct vm_area_struct *vma,
 				     struct page *page)
@@ -76,8 +82,8 @@
 }
 #endif
 
-#ifndef flush_icache_user_range
-static inline void flush_icache_user_range(struct vm_area_struct *vma,
+#ifndef flush_icache_user_page
+static inline void flush_icache_user_page(struct vm_area_struct *vma,
 					   struct page *page,
 					   unsigned long addr, int len)
 {
@@ -100,7 +106,7 @@
 #define copy_to_user_page(vma, page, vaddr, dst, src, len)	\
 	do { \
 		memcpy(dst, src, len); \
-		flush_icache_user_range(vma, page, vaddr, len); \
+		flush_icache_user_page(vma, page, vaddr, len); \
 	} while (0)
 #endif
 
@@ -109,4 +115,4 @@
 	memcpy(dst, src, len)
 #endif
 
-#endif /* __ASM_CACHEFLUSH_H */
+#endif /* _ASM_GENERIC_CACHEFLUSH_H */
diff --git a/include/asm-generic/checksum.h b/include/asm-generic/checksum.h
index 34785c0..43e18db 100644
--- a/include/asm-generic/checksum.h
+++ b/include/asm-generic/checksum.h
@@ -16,29 +16,6 @@
  */
 extern __wsum csum_partial(const void *buff, int len, __wsum sum);
 
-/*
- * the same as csum_partial, but copies from src while it
- * checksums
- *
- * here even more important to align src and dst on a 32-bit (or even
- * better 64-bit) boundary
- */
-extern __wsum csum_partial_copy(const void *src, void *dst, int len, __wsum sum);
-
-/*
- * the same as csum_partial_copy, but copies from user space.
- *
- * here even more important to align src and dst on a 32-bit (or even
- * better 64-bit) boundary
- */
-extern __wsum csum_partial_copy_from_user(const void __user *src, void *dst,
-					int len, __wsum sum, int *csum_err);
-
-#ifndef csum_partial_copy_nocheck
-#define csum_partial_copy_nocheck(src, dst, len, sum)	\
-	csum_partial_copy((src), (dst), (len), (sum))
-#endif
-
 #ifndef ip_fast_csum
 /*
  * This is a version of ip_compute_csum() optimized for IP headers,
diff --git a/include/asm-generic/compat.h b/include/asm-generic/compat.h
index a86f65b..30f7b18 100644
--- a/include/asm-generic/compat.h
+++ b/include/asm-generic/compat.h
@@ -22,4 +22,12 @@
 typedef u32 compat_uptr_t;
 typedef u32 compat_aio_context_t;
 
+#ifdef CONFIG_COMPAT_FOR_U64_ALIGNMENT
+typedef s64 __attribute__((aligned(4))) compat_s64;
+typedef u64 __attribute__((aligned(4))) compat_u64;
+#else
+typedef s64 compat_s64;
+typedef u64 compat_u64;
+#endif
+
 #endif
diff --git a/include/asm-generic/dma-contiguous.h b/include/asm-generic/dma-contiguous.h
deleted file mode 100644
index f24b0f9..0000000
--- a/include/asm-generic/dma-contiguous.h
+++ /dev/null
@@ -1,10 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_GENERIC_DMA_CONTIGUOUS_H
-#define _ASM_GENERIC_DMA_CONTIGUOUS_H
-
-#include <linux/types.h>
-
-static inline void
-dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { }
-
-#endif
diff --git a/include/asm-generic/error-injection.h b/include/asm-generic/error-injection.h
index 80ca610..7ddd9dc 100644
--- a/include/asm-generic/error-injection.h
+++ b/include/asm-generic/error-injection.h
@@ -25,7 +25,7 @@
  */
 #define ALLOW_ERROR_INJECTION(fname, _etype)				\
 static struct error_injection_entry __used				\
-	__attribute__((__section__("_error_injection_whitelist")))	\
+	__section("_error_injection_whitelist")				\
 	_eil_addr_##fname = {						\
 		.addr = (unsigned long)fname,				\
 		.etype = EI_ETYPE_##_etype,				\
diff --git a/include/asm-generic/export.h b/include/asm-generic/export.h
index fa57797..365345f 100644
--- a/include/asm-generic/export.h
+++ b/include/asm-generic/export.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
 #ifndef __ASM_GENERIC_EXPORT_H
 #define __ASM_GENERIC_EXPORT_H
 
@@ -26,25 +27,25 @@
 .endm
 
 /*
- * note on .section use: @progbits vs %progbits nastiness doesn't matter,
- * since we immediately emit into those sections anyway.
+ * note on .section use: we specify progbits since usage of the "M" (SHF_MERGE)
+ * section flag requires it. Use '%progbits' instead of '@progbits' since the
+ * former apparently works on all arches according to the binutils source.
  */
+
 .macro ___EXPORT_SYMBOL name,val,sec
 #ifdef CONFIG_MODULES
-	.globl __ksymtab_\name
 	.section ___ksymtab\sec+\name,"a"
 	.balign KSYM_ALIGN
 __ksymtab_\name:
 	__put \val, __kstrtab_\name
 	.previous
-	.section __ksymtab_strings,"a"
+	.section __ksymtab_strings,"aMS",%progbits,1
 __kstrtab_\name:
 	.asciz "\name"
 	.previous
 #ifdef CONFIG_MODVERSIONS
 	.section ___kcrctab\sec+\name,"a"
 	.balign KCRC_ALIGN
-__kcrctab_\name:
 #if defined(CONFIG_MODULE_REL_CRCS)
 	.long __crc_\name - .
 #else
diff --git a/include/asm-generic/futex.h b/include/asm-generic/futex.h
index 02970b1..f4c3470 100644
--- a/include/asm-generic/futex.h
+++ b/include/asm-generic/futex.h
@@ -34,7 +34,6 @@
 	u32 tmp;
 
 	preempt_disable();
-	pagefault_disable();
 
 	ret = -EFAULT;
 	if (unlikely(get_user(oldval, uaddr) != 0))
@@ -67,7 +66,6 @@
 		ret = -EFAULT;
 
 out_pagefault_enable:
-	pagefault_enable();
 	preempt_enable();
 
 	if (ret == 0)
diff --git a/include/asm-generic/gpio.h b/include/asm-generic/gpio.h
index 19eadac..aea9aee 100644
--- a/include/asm-generic/gpio.h
+++ b/include/asm-generic/gpio.h
@@ -2,10 +2,8 @@
 #ifndef _ASM_GENERIC_GPIO_H
 #define _ASM_GENERIC_GPIO_H
 
-#include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/errno.h>
-#include <linux/of.h>
 
 #ifdef CONFIG_GPIOLIB
 
@@ -140,6 +138,8 @@
 
 #else	/* !CONFIG_GPIOLIB */
 
+#include <linux/kernel.h>
+
 static inline bool gpio_is_valid(int number)
 {
 	/* only non-negative numbers are valid */
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index 822f433..8e1e624 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -122,7 +122,7 @@
 #ifndef __HAVE_ARCH_HUGE_PTEP_GET
 static inline pte_t huge_ptep_get(pte_t *ptep)
 {
-	return *ptep;
+	return ptep_get(ptep);
 }
 #endif
 
diff --git a/include/asm-generic/hyperv-tlfs.h b/include/asm-generic/hyperv-tlfs.h
new file mode 100644
index 0000000..e73a118
--- /dev/null
+++ b/include/asm-generic/hyperv-tlfs.h
@@ -0,0 +1,497 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * This file contains definitions from Hyper-V Hypervisor Top-Level Functional
+ * Specification (TLFS):
+ * https://docs.microsoft.com/en-us/virtualization/hyper-v-on-windows/reference/tlfs
+ */
+
+#ifndef _ASM_GENERIC_HYPERV_TLFS_H
+#define _ASM_GENERIC_HYPERV_TLFS_H
+
+#include <linux/types.h>
+#include <linux/bits.h>
+#include <linux/time64.h>
+
+/*
+ * While not explicitly listed in the TLFS, Hyper-V always runs with a page size
+ * of 4096. These definitions are used when communicating with Hyper-V using
+ * guest physical pages and guest physical page addresses, since the guest page
+ * size may not be 4096 on all architectures.
+ */
+#define HV_HYP_PAGE_SHIFT      12
+#define HV_HYP_PAGE_SIZE       BIT(HV_HYP_PAGE_SHIFT)
+#define HV_HYP_PAGE_MASK       (~(HV_HYP_PAGE_SIZE - 1))
+
+/*
+ * Hyper-V provides two categories of flags relevant to guest VMs.  The
+ * "Features" category indicates specific functionality that is available
+ * to guests on this particular instance of Hyper-V. The "Features"
+ * are presented in four groups, each of which is 32 bits. The group A
+ * and B definitions are common across architectures and are listed here.
+ * However, not all flags are relevant on all architectures.
+ *
+ * Groups C and D vary across architectures and are listed in the
+ * architecture specific portion of hyperv-tlfs.h. Some of these flags exist
+ * on multiple architectures, but the bit positions are different so they
+ * cannot appear in the generic portion of hyperv-tlfs.h.
+ *
+ * The "Enlightenments" category provides recommendations on whether to use
+ * specific enlightenments that are available. The Enlighenments are a single
+ * group of 32 bits, but they vary across architectures and are listed in
+ * the architecture specific portion of hyperv-tlfs.h.
+ */
+
+/*
+ * Group A Features.
+ */
+
+/* VP Runtime register available */
+#define HV_MSR_VP_RUNTIME_AVAILABLE		BIT(0)
+/* Partition Reference Counter available*/
+#define HV_MSR_TIME_REF_COUNT_AVAILABLE		BIT(1)
+/* Basic SynIC register available */
+#define HV_MSR_SYNIC_AVAILABLE			BIT(2)
+/* Synthetic Timer registers available */
+#define HV_MSR_SYNTIMER_AVAILABLE		BIT(3)
+/* Virtual APIC assist and VP assist page registers available */
+#define HV_MSR_APIC_ACCESS_AVAILABLE		BIT(4)
+/* Hypercall and Guest OS ID registers available*/
+#define HV_MSR_HYPERCALL_AVAILABLE		BIT(5)
+/* Access virtual processor index register available*/
+#define HV_MSR_VP_INDEX_AVAILABLE		BIT(6)
+/* Virtual system reset register available*/
+#define HV_MSR_RESET_AVAILABLE			BIT(7)
+/* Access statistics page registers available */
+#define HV_MSR_STAT_PAGES_AVAILABLE		BIT(8)
+/* Partition reference TSC register is available */
+#define HV_MSR_REFERENCE_TSC_AVAILABLE		BIT(9)
+/* Partition Guest IDLE register is available */
+#define HV_MSR_GUEST_IDLE_AVAILABLE		BIT(10)
+/* Partition local APIC and TSC frequency registers available */
+#define HV_ACCESS_FREQUENCY_MSRS		BIT(11)
+/* AccessReenlightenmentControls privilege */
+#define HV_ACCESS_REENLIGHTENMENT		BIT(13)
+/* AccessTscInvariantControls privilege */
+#define HV_ACCESS_TSC_INVARIANT			BIT(15)
+
+/*
+ * Group B features.
+ */
+#define HV_CREATE_PARTITIONS			BIT(0)
+#define HV_ACCESS_PARTITION_ID			BIT(1)
+#define HV_ACCESS_MEMORY_POOL			BIT(2)
+#define HV_ADJUST_MESSAGE_BUFFERS		BIT(3)
+#define HV_POST_MESSAGES			BIT(4)
+#define HV_SIGNAL_EVENTS			BIT(5)
+#define HV_CREATE_PORT				BIT(6)
+#define HV_CONNECT_PORT				BIT(7)
+#define HV_ACCESS_STATS				BIT(8)
+#define HV_DEBUGGING				BIT(11)
+#define HV_CPU_POWER_MANAGEMENT			BIT(12)
+
+
+/*
+ * TSC page layout.
+ */
+struct ms_hyperv_tsc_page {
+	volatile u32 tsc_sequence;
+	u32 reserved1;
+	volatile u64 tsc_scale;
+	volatile s64 tsc_offset;
+} __packed;
+
+/*
+ * The guest OS needs to register the guest ID with the hypervisor.
+ * The guest ID is a 64 bit entity and the structure of this ID is
+ * specified in the Hyper-V specification:
+ *
+ * msdn.microsoft.com/en-us/library/windows/hardware/ff542653%28v=vs.85%29.aspx
+ *
+ * While the current guideline does not specify how Linux guest ID(s)
+ * need to be generated, our plan is to publish the guidelines for
+ * Linux and other guest operating systems that currently are hosted
+ * on Hyper-V. The implementation here conforms to this yet
+ * unpublished guidelines.
+ *
+ *
+ * Bit(s)
+ * 63 - Indicates if the OS is Open Source or not; 1 is Open Source
+ * 62:56 - Os Type; Linux is 0x100
+ * 55:48 - Distro specific identification
+ * 47:16 - Linux kernel version number
+ * 15:0  - Distro specific identification
+ *
+ *
+ */
+
+#define HV_LINUX_VENDOR_ID              0x8100
+
+/*
+ * Crash notification flags.
+ */
+#define HV_CRASH_CTL_CRASH_NOTIFY_MSG		BIT_ULL(62)
+#define HV_CRASH_CTL_CRASH_NOTIFY		BIT_ULL(63)
+
+/* Declare the various hypercall operations. */
+#define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE	0x0002
+#define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST	0x0003
+#define HVCALL_NOTIFY_LONG_SPIN_WAIT		0x0008
+#define HVCALL_SEND_IPI				0x000b
+#define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX	0x0013
+#define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX	0x0014
+#define HVCALL_SEND_IPI_EX			0x0015
+#define HVCALL_GET_VP_REGISTERS			0x0050
+#define HVCALL_SET_VP_REGISTERS			0x0051
+#define HVCALL_POST_MESSAGE			0x005c
+#define HVCALL_SIGNAL_EVENT			0x005d
+#define HVCALL_POST_DEBUG_DATA			0x0069
+#define HVCALL_RETRIEVE_DEBUG_DATA		0x006a
+#define HVCALL_RESET_DEBUG_SESSION		0x006b
+#define HVCALL_RETARGET_INTERRUPT		0x007e
+#define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af
+#define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST 0x00b0
+
+#define HV_FLUSH_ALL_PROCESSORS			BIT(0)
+#define HV_FLUSH_ALL_VIRTUAL_ADDRESS_SPACES	BIT(1)
+#define HV_FLUSH_NON_GLOBAL_MAPPINGS_ONLY	BIT(2)
+#define HV_FLUSH_USE_EXTENDED_RANGE_FORMAT	BIT(3)
+
+enum HV_GENERIC_SET_FORMAT {
+	HV_GENERIC_SET_SPARSE_4K,
+	HV_GENERIC_SET_ALL,
+};
+
+#define HV_PARTITION_ID_SELF		((u64)-1)
+#define HV_VP_INDEX_SELF		((u32)-2)
+
+#define HV_HYPERCALL_RESULT_MASK	GENMASK_ULL(15, 0)
+#define HV_HYPERCALL_FAST_BIT		BIT(16)
+#define HV_HYPERCALL_VARHEAD_OFFSET	17
+#define HV_HYPERCALL_REP_COMP_OFFSET	32
+#define HV_HYPERCALL_REP_COMP_1		BIT_ULL(32)
+#define HV_HYPERCALL_REP_COMP_MASK	GENMASK_ULL(43, 32)
+#define HV_HYPERCALL_REP_START_OFFSET	48
+#define HV_HYPERCALL_REP_START_MASK	GENMASK_ULL(59, 48)
+
+/* hypercall status code */
+#define HV_STATUS_SUCCESS			0
+#define HV_STATUS_INVALID_HYPERCALL_CODE	2
+#define HV_STATUS_INVALID_HYPERCALL_INPUT	3
+#define HV_STATUS_INVALID_ALIGNMENT		4
+#define HV_STATUS_INVALID_PARAMETER		5
+#define HV_STATUS_OPERATION_DENIED		8
+#define HV_STATUS_INSUFFICIENT_MEMORY		11
+#define HV_STATUS_INVALID_PORT_ID		17
+#define HV_STATUS_INVALID_CONNECTION_ID		18
+#define HV_STATUS_INSUFFICIENT_BUFFERS		19
+
+/*
+ * The Hyper-V TimeRefCount register and the TSC
+ * page provide a guest VM clock with 100ns tick rate
+ */
+#define HV_CLOCK_HZ (NSEC_PER_SEC/100)
+
+/* Define the number of synthetic interrupt sources. */
+#define HV_SYNIC_SINT_COUNT		(16)
+/* Define the expected SynIC version. */
+#define HV_SYNIC_VERSION_1		(0x1)
+/* Valid SynIC vectors are 16-255. */
+#define HV_SYNIC_FIRST_VALID_VECTOR	(16)
+
+#define HV_SYNIC_CONTROL_ENABLE		(1ULL << 0)
+#define HV_SYNIC_SIMP_ENABLE		(1ULL << 0)
+#define HV_SYNIC_SIEFP_ENABLE		(1ULL << 0)
+#define HV_SYNIC_SINT_MASKED		(1ULL << 16)
+#define HV_SYNIC_SINT_AUTO_EOI		(1ULL << 17)
+#define HV_SYNIC_SINT_VECTOR_MASK	(0xFF)
+
+#define HV_SYNIC_STIMER_COUNT		(4)
+
+/* Define synthetic interrupt controller message constants. */
+#define HV_MESSAGE_SIZE			(256)
+#define HV_MESSAGE_PAYLOAD_BYTE_COUNT	(240)
+#define HV_MESSAGE_PAYLOAD_QWORD_COUNT	(30)
+
+/* Define synthetic interrupt controller message flags. */
+union hv_message_flags {
+	__u8 asu8;
+	struct {
+		__u8 msg_pending:1;
+		__u8 reserved:7;
+	} __packed;
+};
+
+/* Define port identifier type. */
+union hv_port_id {
+	__u32 asu32;
+	struct {
+		__u32 id:24;
+		__u32 reserved:8;
+	} __packed u;
+};
+
+/* Define synthetic interrupt controller message header. */
+struct hv_message_header {
+	__u32 message_type;
+	__u8 payload_size;
+	union hv_message_flags message_flags;
+	__u8 reserved[2];
+	union {
+		__u64 sender;
+		union hv_port_id port;
+	};
+} __packed;
+
+/* Define synthetic interrupt controller message format. */
+struct hv_message {
+	struct hv_message_header header;
+	union {
+		__u64 payload[HV_MESSAGE_PAYLOAD_QWORD_COUNT];
+	} u;
+} __packed;
+
+/* Define the synthetic interrupt message page layout. */
+struct hv_message_page {
+	struct hv_message sint_message[HV_SYNIC_SINT_COUNT];
+} __packed;
+
+/* Define timer message payload structure. */
+struct hv_timer_message_payload {
+	__u32 timer_index;
+	__u32 reserved;
+	__u64 expiration_time;	/* When the timer expired */
+	__u64 delivery_time;	/* When the message was delivered */
+} __packed;
+
+
+/* Define synthetic interrupt controller flag constants. */
+#define HV_EVENT_FLAGS_COUNT		(256 * 8)
+#define HV_EVENT_FLAGS_LONG_COUNT	(256 / sizeof(unsigned long))
+
+/*
+ * Synthetic timer configuration.
+ */
+union hv_stimer_config {
+	u64 as_uint64;
+	struct {
+		u64 enable:1;
+		u64 periodic:1;
+		u64 lazy:1;
+		u64 auto_enable:1;
+		u64 apic_vector:8;
+		u64 direct_mode:1;
+		u64 reserved_z0:3;
+		u64 sintx:4;
+		u64 reserved_z1:44;
+	} __packed;
+};
+
+
+/* Define the synthetic interrupt controller event flags format. */
+union hv_synic_event_flags {
+	unsigned long flags[HV_EVENT_FLAGS_LONG_COUNT];
+};
+
+/* Define SynIC control register. */
+union hv_synic_scontrol {
+	u64 as_uint64;
+	struct {
+		u64 enable:1;
+		u64 reserved:63;
+	} __packed;
+};
+
+/* Define synthetic interrupt source. */
+union hv_synic_sint {
+	u64 as_uint64;
+	struct {
+		u64 vector:8;
+		u64 reserved1:8;
+		u64 masked:1;
+		u64 auto_eoi:1;
+		u64 polling:1;
+		u64 reserved2:45;
+	} __packed;
+};
+
+/* Define the format of the SIMP register */
+union hv_synic_simp {
+	u64 as_uint64;
+	struct {
+		u64 simp_enabled:1;
+		u64 preserved:11;
+		u64 base_simp_gpa:52;
+	} __packed;
+};
+
+/* Define the format of the SIEFP register */
+union hv_synic_siefp {
+	u64 as_uint64;
+	struct {
+		u64 siefp_enabled:1;
+		u64 preserved:11;
+		u64 base_siefp_gpa:52;
+	} __packed;
+};
+
+struct hv_vpset {
+	u64 format;
+	u64 valid_bank_mask;
+	u64 bank_contents[];
+} __packed;
+
+/* HvCallSendSyntheticClusterIpi hypercall */
+struct hv_send_ipi {
+	u32 vector;
+	u32 reserved;
+	u64 cpu_mask;
+} __packed;
+
+/* HvCallSendSyntheticClusterIpiEx hypercall */
+struct hv_send_ipi_ex {
+	u32 vector;
+	u32 reserved;
+	struct hv_vpset vp_set;
+} __packed;
+
+/* HvFlushGuestPhysicalAddressSpace hypercalls */
+struct hv_guest_mapping_flush {
+	u64 address_space;
+	u64 flags;
+} __packed;
+
+/*
+ *  HV_MAX_FLUSH_PAGES = "additional_pages" + 1. It's limited
+ *  by the bitwidth of "additional_pages" in union hv_gpa_page_range.
+ */
+#define HV_MAX_FLUSH_PAGES (2048)
+
+/* HvFlushGuestPhysicalAddressList hypercall */
+union hv_gpa_page_range {
+	u64 address_space;
+	struct {
+		u64 additional_pages:11;
+		u64 largepage:1;
+		u64 basepfn:52;
+	} page;
+};
+
+/*
+ * All input flush parameters should be in single page. The max flush
+ * count is equal with how many entries of union hv_gpa_page_range can
+ * be populated into the input parameter page.
+ */
+#define HV_MAX_FLUSH_REP_COUNT ((HV_HYP_PAGE_SIZE - 2 * sizeof(u64)) /	\
+				sizeof(union hv_gpa_page_range))
+
+struct hv_guest_mapping_flush_list {
+	u64 address_space;
+	u64 flags;
+	union hv_gpa_page_range gpa_list[HV_MAX_FLUSH_REP_COUNT];
+};
+
+/* HvFlushVirtualAddressSpace, HvFlushVirtualAddressList hypercalls */
+struct hv_tlb_flush {
+	u64 address_space;
+	u64 flags;
+	u64 processor_mask;
+	u64 gva_list[];
+} __packed;
+
+/* HvFlushVirtualAddressSpaceEx, HvFlushVirtualAddressListEx hypercalls */
+struct hv_tlb_flush_ex {
+	u64 address_space;
+	u64 flags;
+	struct hv_vpset hv_vp_set;
+	u64 gva_list[];
+} __packed;
+
+/* HvRetargetDeviceInterrupt hypercall */
+union hv_msi_entry {
+	u64 as_uint64;
+	struct {
+		u32 address;
+		u32 data;
+	} __packed;
+};
+
+struct hv_interrupt_entry {
+	u32 source;			/* 1 for MSI(-X) */
+	u32 reserved1;
+	union hv_msi_entry msi_entry;
+} __packed;
+
+/*
+ * flags for hv_device_interrupt_target.flags
+ */
+#define HV_DEVICE_INTERRUPT_TARGET_MULTICAST		1
+#define HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET	2
+
+struct hv_device_interrupt_target {
+	u32 vector;
+	u32 flags;
+	union {
+		u64 vp_mask;
+		struct hv_vpset vp_set;
+	};
+} __packed;
+
+struct hv_retarget_device_interrupt {
+	u64 partition_id;		/* use "self" */
+	u64 device_id;
+	struct hv_interrupt_entry int_entry;
+	u64 reserved2;
+	struct hv_device_interrupt_target int_target;
+} __packed __aligned(8);
+
+
+/* HvGetVpRegisters hypercall input with variable size reg name list*/
+struct hv_get_vp_registers_input {
+	struct {
+		u64 partitionid;
+		u32 vpindex;
+		u8  inputvtl;
+		u8  padding[3];
+	} header;
+	struct input {
+		u32 name0;
+		u32 name1;
+	} element[];
+} __packed;
+
+
+/* HvGetVpRegisters returns an array of these output elements */
+struct hv_get_vp_registers_output {
+	union {
+		struct {
+			u32 a;
+			u32 b;
+			u32 c;
+			u32 d;
+		} as32 __packed;
+		struct {
+			u64 low;
+			u64 high;
+		} as64 __packed;
+	};
+};
+
+/* HvSetVpRegisters hypercall with variable size reg name/value list*/
+struct hv_set_vp_registers_input {
+	struct {
+		u64 partitionid;
+		u32 vpindex;
+		u8  inputvtl;
+		u8  padding[3];
+	} header;
+	struct {
+		u32 name;
+		u32 padding1;
+		u64 padding2;
+		u64 valuelow;
+		u64 valuehigh;
+	} element[];
+} __packed;
+
+#endif
diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index d028065..9ea83d8 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -163,7 +163,7 @@
 	u16 val;
 
 	__io_br();
-	val = __le16_to_cpu(__raw_readw(addr));
+	val = __le16_to_cpu((__le16 __force)__raw_readw(addr));
 	__io_ar(val);
 	return val;
 }
@@ -176,7 +176,7 @@
 	u32 val;
 
 	__io_br();
-	val = __le32_to_cpu(__raw_readl(addr));
+	val = __le32_to_cpu((__le32 __force)__raw_readl(addr));
 	__io_ar(val);
 	return val;
 }
@@ -212,7 +212,7 @@
 static inline void writew(u16 value, volatile void __iomem *addr)
 {
 	__io_bw();
-	__raw_writew(cpu_to_le16(value), addr);
+	__raw_writew((u16 __force)cpu_to_le16(value), addr);
 	__io_aw();
 }
 #endif
@@ -222,7 +222,7 @@
 static inline void writel(u32 value, volatile void __iomem *addr)
 {
 	__io_bw();
-	__raw_writel(__cpu_to_le32(value), addr);
+	__raw_writel((u32 __force)__cpu_to_le32(value), addr);
 	__io_aw();
 }
 #endif
@@ -448,17 +448,15 @@
 #define IO_SPACE_LIMIT 0xffff
 #endif
 
-#include <linux/logic_pio.h>
-
 /*
  * {in,out}{b,w,l}() access little endian I/O. {in,out}{b,w,l}_p() can be
  * implemented on hardware that needs an additional delay for I/O accesses to
  * take effect.
  */
 
-#ifndef inb
-#define inb inb
-static inline u8 inb(unsigned long addr)
+#if !defined(inb) && !defined(_inb)
+#define _inb _inb
+static inline u8 _inb(unsigned long addr)
 {
 	u8 val;
 
@@ -469,35 +467,35 @@
 }
 #endif
 
-#ifndef inw
-#define inw inw
-static inline u16 inw(unsigned long addr)
+#if !defined(inw) && !defined(_inw)
+#define _inw _inw
+static inline u16 _inw(unsigned long addr)
 {
 	u16 val;
 
 	__io_pbr();
-	val = __le16_to_cpu(__raw_readw(PCI_IOBASE + addr));
+	val = __le16_to_cpu((__le16 __force)__raw_readw(PCI_IOBASE + addr));
 	__io_par(val);
 	return val;
 }
 #endif
 
-#ifndef inl
-#define inl inl
-static inline u32 inl(unsigned long addr)
+#if !defined(inl) && !defined(_inl)
+#define _inl _inl
+static inline u32 _inl(unsigned long addr)
 {
 	u32 val;
 
 	__io_pbr();
-	val = __le32_to_cpu(__raw_readl(PCI_IOBASE + addr));
+	val = __le32_to_cpu((__le32 __force)__raw_readl(PCI_IOBASE + addr));
 	__io_par(val);
 	return val;
 }
 #endif
 
-#ifndef outb
-#define outb outb
-static inline void outb(u8 value, unsigned long addr)
+#if !defined(outb) && !defined(_outb)
+#define _outb _outb
+static inline void _outb(u8 value, unsigned long addr)
 {
 	__io_pbw();
 	__raw_writeb(value, PCI_IOBASE + addr);
@@ -505,26 +503,52 @@
 }
 #endif
 
-#ifndef outw
-#define outw outw
-static inline void outw(u16 value, unsigned long addr)
+#if !defined(outw) && !defined(_outw)
+#define _outw _outw
+static inline void _outw(u16 value, unsigned long addr)
 {
 	__io_pbw();
-	__raw_writew(cpu_to_le16(value), PCI_IOBASE + addr);
+	__raw_writew((u16 __force)cpu_to_le16(value), PCI_IOBASE + addr);
 	__io_paw();
 }
 #endif
 
-#ifndef outl
-#define outl outl
-static inline void outl(u32 value, unsigned long addr)
+#if !defined(outl) && !defined(_outl)
+#define _outl _outl
+static inline void _outl(u32 value, unsigned long addr)
 {
 	__io_pbw();
-	__raw_writel(cpu_to_le32(value), PCI_IOBASE + addr);
+	__raw_writel((u32 __force)cpu_to_le32(value), PCI_IOBASE + addr);
 	__io_paw();
 }
 #endif
 
+#include <linux/logic_pio.h>
+
+#ifndef inb
+#define inb _inb
+#endif
+
+#ifndef inw
+#define inw _inw
+#endif
+
+#ifndef inl
+#define inl _inl
+#endif
+
+#ifndef outb
+#define outb _outb
+#endif
+
+#ifndef outw
+#define outw _outw
+#endif
+
+#ifndef outl
+#define outl _outl
+#endif
+
 #ifndef inb_p
 #define inb_p inb_p
 static inline u8 inb_p(unsigned long addr)
@@ -887,18 +911,6 @@
 #include <linux/vmalloc.h>
 #define __io_virt(x) ((void __force *)(x))
 
-#ifndef CONFIG_GENERIC_IOMAP
-struct pci_dev;
-extern void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max);
-
-#ifndef pci_iounmap
-#define pci_iounmap pci_iounmap
-static inline void pci_iounmap(struct pci_dev *dev, void __iomem *p)
-{
-}
-#endif
-#endif /* CONFIG_GENERIC_IOMAP */
-
 /*
  * Change virtual addresses to physical addresses and vv.
  * These are pretty trivial
@@ -922,39 +934,17 @@
 /**
  * DOC: ioremap() and ioremap_*() variants
  *
- * If you have an IOMMU your architecture is expected to have both ioremap()
- * and iounmap() implemented otherwise the asm-generic helpers will provide a
- * direct mapping.
+ * Architectures with an MMU are expected to provide ioremap() and iounmap()
+ * themselves or rely on GENERIC_IOREMAP.  For NOMMU architectures we provide
+ * a default nop-op implementation that expect that the physical address used
+ * for MMIO are already marked as uncached, and can be used as kernel virtual
+ * addresses.
  *
- * There are ioremap_*() call variants, if you have no IOMMU we naturally will
- * default to direct mapping for all of them, you can override these defaults.
- * If you have an IOMMU you are highly encouraged to provide your own
- * ioremap variant implementation as there currently is no safe architecture
- * agnostic default. To avoid possible improper behaviour default asm-generic
- * ioremap_*() variants all return NULL when an IOMMU is available. If you've
- * defined your own ioremap_*() variant you must then declare your own
- * ioremap_*() variant as defined to itself to avoid the default NULL return.
+ * ioremap_wc() and ioremap_wt() can provide more relaxed caching attributes
+ * for specific drivers if the architecture choses to implement them.  If they
+ * are not implemented we fall back to plain ioremap.
  */
-
-#ifdef CONFIG_MMU
-
-#ifndef ioremap_uc
-#define ioremap_uc ioremap_uc
-static inline void __iomem *ioremap_uc(phys_addr_t offset, size_t size)
-{
-	return NULL;
-}
-#endif
-
-#else /* !CONFIG_MMU */
-
-/*
- * Change "struct page" to physical address.
- *
- * This implementation is for the no-MMU case only... if you have an MMU
- * you'll need to provide your own definitions.
- */
-
+#ifndef CONFIG_MMU
 #ifndef ioremap
 #define ioremap ioremap
 static inline void __iomem *ioremap(phys_addr_t offset, size_t size)
@@ -965,42 +955,43 @@
 
 #ifndef iounmap
 #define iounmap iounmap
-
 static inline void iounmap(void __iomem *addr)
 {
 }
 #endif
-#endif /* CONFIG_MMU */
-#ifndef ioremap_nocache
-void __iomem *ioremap(phys_addr_t phys_addr, size_t size);
-#define ioremap_nocache ioremap_nocache
-static inline void __iomem *ioremap_nocache(phys_addr_t offset, size_t size)
+#elif defined(CONFIG_GENERIC_IOREMAP)
+#include <linux/pgtable.h>
+
+void __iomem *ioremap_prot(phys_addr_t addr, size_t size, unsigned long prot);
+void iounmap(volatile void __iomem *addr);
+
+static inline void __iomem *ioremap(phys_addr_t addr, size_t size)
 {
-	return ioremap(offset, size);
+	/* _PAGE_IOREMAP needs to be supplied by the architecture */
+	return ioremap_prot(addr, size, _PAGE_IOREMAP);
 }
+#endif /* !CONFIG_MMU || CONFIG_GENERIC_IOREMAP */
+
+#ifndef ioremap_wc
+#define ioremap_wc ioremap
 #endif
 
+#ifndef ioremap_wt
+#define ioremap_wt ioremap
+#endif
+
+/*
+ * ioremap_uc is special in that we do require an explicit architecture
+ * implementation.  In general you do not want to use this function in a
+ * driver and use plain ioremap, which is uncached by default.  Similarly
+ * architectures should not implement it unless they have a very good
+ * reason.
+ */
 #ifndef ioremap_uc
 #define ioremap_uc ioremap_uc
 static inline void __iomem *ioremap_uc(phys_addr_t offset, size_t size)
 {
-	return ioremap_nocache(offset, size);
-}
-#endif
-
-#ifndef ioremap_wc
-#define ioremap_wc ioremap_wc
-static inline void __iomem *ioremap_wc(phys_addr_t offset, size_t size)
-{
-	return ioremap_nocache(offset, size);
-}
-#endif
-
-#ifndef ioremap_wt
-#define ioremap_wt ioremap_wt
-static inline void __iomem *ioremap_wt(phys_addr_t offset, size_t size)
-{
-	return ioremap_nocache(offset, size);
+	return NULL;
 }
 #endif
 
@@ -1013,6 +1004,16 @@
 	port &= IO_SPACE_LIMIT;
 	return (port > MMIO_UPPER_LIMIT) ? NULL : PCI_IOBASE + port;
 }
+#define __pci_ioport_unmap __pci_ioport_unmap
+static inline void __pci_ioport_unmap(void __iomem *p)
+{
+	uintptr_t start = (uintptr_t) PCI_IOBASE;
+	uintptr_t addr = (uintptr_t) p;
+
+	if (addr >= start && addr < start + IO_SPACE_LIMIT)
+		return;
+	iounmap(p);
+}
 #endif
 
 #ifndef ioport_unmap
@@ -1027,6 +1028,23 @@
 #endif /* CONFIG_GENERIC_IOMAP */
 #endif /* CONFIG_HAS_IOPORT_MAP */
 
+#ifndef CONFIG_GENERIC_IOMAP
+struct pci_dev;
+extern void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max);
+
+#ifndef __pci_ioport_unmap
+static inline void __pci_ioport_unmap(void __iomem *p) {}
+#endif
+
+#ifndef pci_iounmap
+#define pci_iounmap pci_iounmap
+static inline void pci_iounmap(struct pci_dev *dev, void __iomem *p)
+{
+	__pci_ioport_unmap(p);
+}
+#endif
+#endif /* CONFIG_GENERIC_IOMAP */
+
 /*
  * Convert a virtual cached pointer to an uncached pointer
  */
diff --git a/include/asm-generic/iomap.h b/include/asm-generic/iomap.h
index a008f50..6492246 100644
--- a/include/asm-generic/iomap.h
+++ b/include/asm-generic/iomap.h
@@ -26,14 +26,14 @@
  * in the low address range. Architectures for which this is not
  * true can't use this generic implementation.
  */
-extern unsigned int ioread8(void __iomem *);
-extern unsigned int ioread16(void __iomem *);
-extern unsigned int ioread16be(void __iomem *);
-extern unsigned int ioread32(void __iomem *);
-extern unsigned int ioread32be(void __iomem *);
+extern unsigned int ioread8(const void __iomem *);
+extern unsigned int ioread16(const void __iomem *);
+extern unsigned int ioread16be(const void __iomem *);
+extern unsigned int ioread32(const void __iomem *);
+extern unsigned int ioread32be(const void __iomem *);
 #ifdef CONFIG_64BIT
-extern u64 ioread64(void __iomem *);
-extern u64 ioread64be(void __iomem *);
+extern u64 ioread64(const void __iomem *);
+extern u64 ioread64be(const void __iomem *);
 #endif
 
 #ifdef readq
@@ -41,10 +41,10 @@
 #define ioread64_hi_lo ioread64_hi_lo
 #define ioread64be_lo_hi ioread64be_lo_hi
 #define ioread64be_hi_lo ioread64be_hi_lo
-extern u64 ioread64_lo_hi(void __iomem *addr);
-extern u64 ioread64_hi_lo(void __iomem *addr);
-extern u64 ioread64be_lo_hi(void __iomem *addr);
-extern u64 ioread64be_hi_lo(void __iomem *addr);
+extern u64 ioread64_lo_hi(const void __iomem *addr);
+extern u64 ioread64_hi_lo(const void __iomem *addr);
+extern u64 ioread64be_lo_hi(const void __iomem *addr);
+extern u64 ioread64be_hi_lo(const void __iomem *addr);
 #endif
 
 extern void iowrite8(u8, void __iomem *);
@@ -79,9 +79,9 @@
  * memory across multiple ports, use "memcpy_toio()"
  * and friends.
  */
-extern void ioread8_rep(void __iomem *port, void *buf, unsigned long count);
-extern void ioread16_rep(void __iomem *port, void *buf, unsigned long count);
-extern void ioread32_rep(void __iomem *port, void *buf, unsigned long count);
+extern void ioread8_rep(const void __iomem *port, void *buf, unsigned long count);
+extern void ioread16_rep(const void __iomem *port, void *buf, unsigned long count);
+extern void ioread32_rep(const void __iomem *port, void *buf, unsigned long count);
 
 extern void iowrite8_rep(void __iomem *port, const void *buf, unsigned long count);
 extern void iowrite16_rep(void __iomem *port, const void *buf, unsigned long count);
@@ -94,11 +94,11 @@
 #endif
 
 #ifndef ARCH_HAS_IOREMAP_WC
-#define ioremap_wc ioremap_nocache
+#define ioremap_wc ioremap
 #endif
 
 #ifndef ARCH_HAS_IOREMAP_WT
-#define ioremap_wt ioremap_nocache
+#define ioremap_wt ioremap
 #endif
 
 #ifdef CONFIG_PCI
diff --git a/include/asm-generic/kprobes.h b/include/asm-generic/kprobes.h
index 4a98208..060eab0 100644
--- a/include/asm-generic/kprobes.h
+++ b/include/asm-generic/kprobes.h
@@ -10,11 +10,11 @@
  */
 # define __NOKPROBE_SYMBOL(fname)				\
 static unsigned long __used					\
-	__attribute__((__section__("_kprobe_blacklist")))	\
+	__section("_kprobe_blacklist")				\
 	_kbl_addr_##fname = (unsigned long)fname;
 # define NOKPROBE_SYMBOL(fname)	__NOKPROBE_SYMBOL(fname)
 /* Use this to forbid a kprobes attach on very low level functions */
-# define __kprobes	__attribute__((__section__(".kprobes.text")))
+# define __kprobes	__section(".kprobes.text")
 # define nokprobe_inline	__always_inline
 #else
 # define NOKPROBE_SYMBOL(fname)
diff --git a/include/asm-generic/kvm_types.h b/include/asm-generic/kvm_types.h
new file mode 100644
index 0000000..2a82daf
--- /dev/null
+++ b/include/asm-generic/kvm_types.h
@@ -0,0 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_KVM_TYPES_H
+#define _ASM_GENERIC_KVM_TYPES_H
+
+#endif
diff --git a/include/asm-generic/mm_hooks.h b/include/asm-generic/mm_hooks.h
index 6736ed2..4dbb177 100644
--- a/include/asm-generic/mm_hooks.h
+++ b/include/asm-generic/mm_hooks.h
@@ -22,11 +22,6 @@
 {
 }
 
-static inline void arch_bprm_mm_init(struct mm_struct *mm,
-				     struct vm_area_struct *vma)
-{
-}
-
 static inline bool arch_vma_access_permitted(struct vm_area_struct *vma,
 		bool write, bool execute, bool foreign)
 {
diff --git a/include/asm-generic/module.lds.h b/include/asm-generic/module.lds.h
new file mode 100644
index 0000000..f210d5c
--- /dev/null
+++ b/include/asm-generic/module.lds.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __ASM_GENERIC_MODULE_LDS_H
+#define __ASM_GENERIC_MODULE_LDS_H
+
+/*
+ * <asm/module.lds.h> can specify arch-specific sections for linking modules.
+ * Empty for the asm-generic header.
+ */
+
+#endif /* __ASM_GENERIC_MODULE_LDS_H */
diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h
index 53759d2..c577996 100644
--- a/include/asm-generic/mshyperv.h
+++ b/include/asm-generic/mshyperv.h
@@ -89,7 +89,7 @@
 	}
 }
 
-void hv_setup_vmbus_irq(void (*handler)(void));
+int hv_setup_vmbus_irq(int irq, void (*handler)(void));
 void hv_remove_vmbus_irq(void);
 void hv_enable_vmbus_irq(void);
 void hv_disable_vmbus_irq(void);
@@ -99,6 +99,8 @@
 void hv_setup_crash_handler(void (*handler)(struct pt_regs *regs));
 void hv_remove_crash_handler(void);
 
+extern int vmbus_interrupt;
+
 #if IS_ENABLED(CONFIG_HYPERV)
 /*
  * Hypervisor's notion of virtual processor ID is different from
@@ -166,10 +168,11 @@
 void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die);
 void hyperv_report_panic_msg(phys_addr_t pa, size_t size);
 bool hv_is_hyperv_initialized(void);
+bool hv_is_hibernation_supported(void);
 void hyperv_cleanup(void);
-void hv_setup_sched_clock(void *sched_clock);
 #else /* CONFIG_HYPERV */
 static inline bool hv_is_hyperv_initialized(void) { return false; }
+static inline bool hv_is_hibernation_supported(void) { return false; }
 static inline void hyperv_cleanup(void) {}
 #endif /* CONFIG_HYPERV */
 
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index c2de013..6432a7f 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -74,7 +74,7 @@
 
 #define raw_cpu_generic_add_return(pcp, val)				\
 ({									\
-	typeof(&(pcp)) __p = raw_cpu_ptr(&(pcp));			\
+	typeof(pcp) *__p = raw_cpu_ptr(&(pcp));				\
 									\
 	*__p += val;							\
 	*__p;								\
@@ -82,7 +82,7 @@
 
 #define raw_cpu_generic_xchg(pcp, nval)					\
 ({									\
-	typeof(&(pcp)) __p = raw_cpu_ptr(&(pcp));			\
+	typeof(pcp) *__p = raw_cpu_ptr(&(pcp));				\
 	typeof(pcp) __ret;						\
 	__ret = *__p;							\
 	*__p = nval;							\
@@ -91,7 +91,7 @@
 
 #define raw_cpu_generic_cmpxchg(pcp, oval, nval)			\
 ({									\
-	typeof(&(pcp)) __p = raw_cpu_ptr(&(pcp));			\
+	typeof(pcp) *__p = raw_cpu_ptr(&(pcp));				\
 	typeof(pcp) __ret;						\
 	__ret = *__p;							\
 	if (__ret == (oval))						\
@@ -101,8 +101,8 @@
 
 #define raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \
 ({									\
-	typeof(&(pcp1)) __p1 = raw_cpu_ptr(&(pcp1));			\
-	typeof(&(pcp2)) __p2 = raw_cpu_ptr(&(pcp2));			\
+	typeof(pcp1) *__p1 = raw_cpu_ptr(&(pcp1));			\
+	typeof(pcp2) *__p2 = raw_cpu_ptr(&(pcp2));			\
 	int __ret = 0;							\
 	if (*__p1 == (oval1) && *__p2  == (oval2)) {			\
 		*__p1 = nval1;						\
@@ -114,21 +114,21 @@
 
 #define __this_cpu_generic_read_nopreempt(pcp)				\
 ({									\
-	typeof(pcp) __ret;						\
+	typeof(pcp) ___ret;						\
 	preempt_disable_notrace();					\
-	__ret = READ_ONCE(*raw_cpu_ptr(&(pcp)));			\
+	___ret = READ_ONCE(*raw_cpu_ptr(&(pcp)));			\
 	preempt_enable_notrace();					\
-	__ret;								\
+	___ret;								\
 })
 
 #define __this_cpu_generic_read_noirq(pcp)				\
 ({									\
-	typeof(pcp) __ret;						\
-	unsigned long __flags;						\
-	raw_local_irq_save(__flags);					\
-	__ret = raw_cpu_generic_read(pcp);				\
-	raw_local_irq_restore(__flags);					\
-	__ret;								\
+	typeof(pcp) ___ret;						\
+	unsigned long ___flags;						\
+	raw_local_irq_save(___flags);					\
+	___ret = raw_cpu_generic_read(pcp);				\
+	raw_local_irq_restore(___flags);				\
+	___ret;								\
 })
 
 #define this_cpu_generic_read(pcp)					\
diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h
index 73f7421..02932ef 100644
--- a/include/asm-generic/pgalloc.h
+++ b/include/asm-generic/pgalloc.h
@@ -102,6 +102,86 @@
 	__free_page(pte_page);
 }
 
+
+#if CONFIG_PGTABLE_LEVELS > 2
+
+#ifndef __HAVE_ARCH_PMD_ALLOC_ONE
+/**
+ * pmd_alloc_one - allocate a page for PMD-level page table
+ * @mm: the mm_struct of the current context
+ *
+ * Allocates a page and runs the pgtable_pmd_page_ctor().
+ * Allocations use %GFP_PGTABLE_USER in user context and
+ * %GFP_PGTABLE_KERNEL in kernel context.
+ *
+ * Return: pointer to the allocated memory or %NULL on error
+ */
+static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	struct page *page;
+	gfp_t gfp = GFP_PGTABLE_USER;
+
+	if (mm == &init_mm)
+		gfp = GFP_PGTABLE_KERNEL;
+	page = alloc_pages(gfp, 0);
+	if (!page)
+		return NULL;
+	if (!pgtable_pmd_page_ctor(page)) {
+		__free_pages(page, 0);
+		return NULL;
+	}
+	return (pmd_t *)page_address(page);
+}
+#endif
+
+#ifndef __HAVE_ARCH_PMD_FREE
+static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
+{
+	BUG_ON((unsigned long)pmd & (PAGE_SIZE-1));
+	pgtable_pmd_page_dtor(virt_to_page(pmd));
+	free_page((unsigned long)pmd);
+}
+#endif
+
+#endif /* CONFIG_PGTABLE_LEVELS > 2 */
+
+#if CONFIG_PGTABLE_LEVELS > 3
+
+#ifndef __HAVE_ARCH_PUD_ALLOC_ONE
+/**
+ * pud_alloc_one - allocate a page for PUD-level page table
+ * @mm: the mm_struct of the current context
+ *
+ * Allocates a page using %GFP_PGTABLE_USER for user context and
+ * %GFP_PGTABLE_KERNEL for kernel context.
+ *
+ * Return: pointer to the allocated memory or %NULL on error
+ */
+static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	gfp_t gfp = GFP_PGTABLE_USER;
+
+	if (mm == &init_mm)
+		gfp = GFP_PGTABLE_KERNEL;
+	return (pud_t *)get_zeroed_page(gfp);
+}
+#endif
+
+static inline void pud_free(struct mm_struct *mm, pud_t *pud)
+{
+	BUG_ON((unsigned long)pud & (PAGE_SIZE-1));
+	free_page((unsigned long)pud);
+}
+
+#endif /* CONFIG_PGTABLE_LEVELS > 3 */
+
+#ifndef __HAVE_ARCH_PGD_FREE
+static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+	free_page((unsigned long)pgd);
+}
+#endif
+
 #endif /* CONFIG_MMU */
 
 #endif /* __ASM_GENERIC_PGALLOC_H */
diff --git a/include/asm-generic/pgtable-nop4d-hack.h b/include/asm-generic/pgtable-nop4d-hack.h
deleted file mode 100644
index 829bdb0..0000000
--- a/include/asm-generic/pgtable-nop4d-hack.h
+++ /dev/null
@@ -1,64 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _PGTABLE_NOP4D_HACK_H
-#define _PGTABLE_NOP4D_HACK_H
-
-#ifndef __ASSEMBLY__
-#include <asm-generic/5level-fixup.h>
-
-#define __PAGETABLE_PUD_FOLDED 1
-
-/*
- * Having the pud type consist of a pgd gets the size right, and allows
- * us to conceptually access the pgd entry that this pud is folded into
- * without casting.
- */
-typedef struct { pgd_t pgd; } pud_t;
-
-#define PUD_SHIFT	PGDIR_SHIFT
-#define PTRS_PER_PUD	1
-#define PUD_SIZE	(1UL << PUD_SHIFT)
-#define PUD_MASK	(~(PUD_SIZE-1))
-
-/*
- * The "pgd_xxx()" functions here are trivial for a folded two-level
- * setup: the pud is never bad, and a pud always exists (as it's folded
- * into the pgd entry)
- */
-static inline int pgd_none(pgd_t pgd)		{ return 0; }
-static inline int pgd_bad(pgd_t pgd)		{ return 0; }
-static inline int pgd_present(pgd_t pgd)	{ return 1; }
-static inline void pgd_clear(pgd_t *pgd)	{ }
-#define pud_ERROR(pud)				(pgd_ERROR((pud).pgd))
-
-#define pgd_populate(mm, pgd, pud)		do { } while (0)
-#define pgd_populate_safe(mm, pgd, pud)		do { } while (0)
-/*
- * (puds are folded into pgds so this doesn't get actually called,
- * but the define is needed for a generic inline function.)
- */
-#define set_pgd(pgdptr, pgdval)	set_pud((pud_t *)(pgdptr), (pud_t) { pgdval })
-
-static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address)
-{
-	return (pud_t *)pgd;
-}
-
-#define pud_val(x)				(pgd_val((x).pgd))
-#define __pud(x)				((pud_t) { __pgd(x) })
-
-#define pgd_page(pgd)				(pud_page((pud_t){ pgd }))
-#define pgd_page_vaddr(pgd)			(pud_page_vaddr((pud_t){ pgd }))
-
-/*
- * allocating and freeing a pud is trivial: the 1-entry pud is
- * inside the pgd, so has no extra memory associated with it.
- */
-#define pud_alloc_one(mm, address)		NULL
-#define pud_free(mm, x)				do { } while (0)
-#define __pud_free_tlb(tlb, x, a)		do { } while (0)
-
-#undef  pud_addr_end
-#define pud_addr_end(addr, end)			(end)
-
-#endif /* __ASSEMBLY__ */
-#endif /* _PGTABLE_NOP4D_HACK_H */
diff --git a/include/asm-generic/pgtable-nop4d.h b/include/asm-generic/pgtable-nop4d.h
index aebab90..ce2cbb3 100644
--- a/include/asm-generic/pgtable-nop4d.h
+++ b/include/asm-generic/pgtable-nop4d.h
@@ -50,7 +50,7 @@
  */
 #define p4d_alloc_one(mm, address)		NULL
 #define p4d_free(mm, x)				do { } while (0)
-#define __p4d_free_tlb(tlb, x, a)		do { } while (0)
+#define p4d_free_tlb(tlb, x, a)			do { } while (0)
 
 #undef  p4d_addr_end
 #define p4d_addr_end(addr, end)			(end)
diff --git a/include/asm-generic/pgtable-nopmd.h b/include/asm-generic/pgtable-nopmd.h
index b85b827..3e13acd 100644
--- a/include/asm-generic/pgtable-nopmd.h
+++ b/include/asm-generic/pgtable-nopmd.h
@@ -45,6 +45,7 @@
 {
 	return (pmd_t *)pud;
 }
+#define pmd_offset pmd_offset
 
 #define pmd_val(x)				(pud_val((x).pud))
 #define __pmd(x)				((pmd_t) { __pud(x) } )
@@ -60,7 +61,7 @@
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
 }
-#define __pmd_free_tlb(tlb, x, a)		do { } while (0)
+#define pmd_free_tlb(tlb, x, a)		do { } while (0)
 
 #undef  pmd_addr_end
 #define pmd_addr_end(addr, end)			(end)
diff --git a/include/asm-generic/pgtable-nopud.h b/include/asm-generic/pgtable-nopud.h
index c77a1d3..a9d751f 100644
--- a/include/asm-generic/pgtable-nopud.h
+++ b/include/asm-generic/pgtable-nopud.h
@@ -4,9 +4,6 @@
 
 #ifndef __ASSEMBLY__
 
-#ifdef __ARCH_USE_5LEVEL_HACK
-#include <asm-generic/pgtable-nop4d-hack.h>
-#else
 #include <asm-generic/pgtable-nop4d.h>
 
 #define __PAGETABLE_PUD_FOLDED 1
@@ -46,6 +43,7 @@
 {
 	return (pud_t *)p4d;
 }
+#define pud_offset pud_offset
 
 #define pud_val(x)				(p4d_val((x).p4d))
 #define __pud(x)				((pud_t) { __p4d(x) })
@@ -59,11 +57,10 @@
  */
 #define pud_alloc_one(mm, address)		NULL
 #define pud_free(mm, x)				do { } while (0)
-#define __pud_free_tlb(tlb, x, a)		do { } while (0)
+#define pud_free_tlb(tlb, x, a)		        do { } while (0)
 
 #undef  pud_addr_end
 #define pud_addr_end(addr, end)			(end)
 
 #endif /* __ASSEMBLY__ */
-#endif /* !__ARCH_USE_5LEVEL_HACK */
 #endif /* _PGTABLE_NOPUD_H */
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
deleted file mode 100644
index 15f7736..0000000
--- a/include/asm-generic/pgtable.h
+++ /dev/null
@@ -1,1209 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_GENERIC_PGTABLE_H
-#define _ASM_GENERIC_PGTABLE_H
-
-#include <linux/pfn.h>
-
-#ifndef __ASSEMBLY__
-#ifdef CONFIG_MMU
-
-#include <linux/mm_types.h>
-#include <linux/bug.h>
-#include <linux/errno.h>
-
-#if 5 - defined(__PAGETABLE_P4D_FOLDED) - defined(__PAGETABLE_PUD_FOLDED) - \
-	defined(__PAGETABLE_PMD_FOLDED) != CONFIG_PGTABLE_LEVELS
-#error CONFIG_PGTABLE_LEVELS is not consistent with __PAGETABLE_{P4D,PUD,PMD}_FOLDED
-#endif
-
-/*
- * On almost all architectures and configurations, 0 can be used as the
- * upper ceiling to free_pgtables(): on many architectures it has the same
- * effect as using TASK_SIZE.  However, there is one configuration which
- * must impose a more careful limit, to avoid freeing kernel pgtables.
- */
-#ifndef USER_PGTABLES_CEILING
-#define USER_PGTABLES_CEILING	0UL
-#endif
-
-#ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
-extern int ptep_set_access_flags(struct vm_area_struct *vma,
-				 unsigned long address, pte_t *ptep,
-				 pte_t entry, int dirty);
-#endif
-
-#ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-extern int pmdp_set_access_flags(struct vm_area_struct *vma,
-				 unsigned long address, pmd_t *pmdp,
-				 pmd_t entry, int dirty);
-extern int pudp_set_access_flags(struct vm_area_struct *vma,
-				 unsigned long address, pud_t *pudp,
-				 pud_t entry, int dirty);
-#else
-static inline int pmdp_set_access_flags(struct vm_area_struct *vma,
-					unsigned long address, pmd_t *pmdp,
-					pmd_t entry, int dirty)
-{
-	BUILD_BUG();
-	return 0;
-}
-static inline int pudp_set_access_flags(struct vm_area_struct *vma,
-					unsigned long address, pud_t *pudp,
-					pud_t entry, int dirty)
-{
-	BUILD_BUG();
-	return 0;
-}
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-#endif
-
-#ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
-static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
-					    unsigned long address,
-					    pte_t *ptep)
-{
-	pte_t pte = *ptep;
-	int r = 1;
-	if (!pte_young(pte))
-		r = 0;
-	else
-		set_pte_at(vma->vm_mm, address, ptep, pte_mkold(pte));
-	return r;
-}
-#endif
-
-#ifndef __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
-					    unsigned long address,
-					    pmd_t *pmdp)
-{
-	pmd_t pmd = *pmdp;
-	int r = 1;
-	if (!pmd_young(pmd))
-		r = 0;
-	else
-		set_pmd_at(vma->vm_mm, address, pmdp, pmd_mkold(pmd));
-	return r;
-}
-#else
-static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
-					    unsigned long address,
-					    pmd_t *pmdp)
-{
-	BUILD_BUG();
-	return 0;
-}
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-#endif
-
-#ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
-int ptep_clear_flush_young(struct vm_area_struct *vma,
-			   unsigned long address, pte_t *ptep);
-#endif
-
-#ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
-				  unsigned long address, pmd_t *pmdp);
-#else
-/*
- * Despite relevant to THP only, this API is called from generic rmap code
- * under PageTransHuge(), hence needs a dummy implementation for !THP
- */
-static inline int pmdp_clear_flush_young(struct vm_area_struct *vma,
-					 unsigned long address, pmd_t *pmdp)
-{
-	BUILD_BUG();
-	return 0;
-}
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-#endif
-
-#ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR
-static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
-				       unsigned long address,
-				       pte_t *ptep)
-{
-	pte_t pte = *ptep;
-	pte_clear(mm, address, ptep);
-	return pte;
-}
-#endif
-
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
-static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
-					    unsigned long address,
-					    pmd_t *pmdp)
-{
-	pmd_t pmd = *pmdp;
-	pmd_clear(pmdp);
-	return pmd;
-}
-#endif /* __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR */
-#ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR
-static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm,
-					    unsigned long address,
-					    pud_t *pudp)
-{
-	pud_t pud = *pudp;
-
-	pud_clear(pudp);
-	return pud;
-}
-#endif /* __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR */
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#ifndef __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR_FULL
-static inline pmd_t pmdp_huge_get_and_clear_full(struct mm_struct *mm,
-					    unsigned long address, pmd_t *pmdp,
-					    int full)
-{
-	return pmdp_huge_get_and_clear(mm, address, pmdp);
-}
-#endif
-
-#ifndef __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR_FULL
-static inline pud_t pudp_huge_get_and_clear_full(struct mm_struct *mm,
-					    unsigned long address, pud_t *pudp,
-					    int full)
-{
-	return pudp_huge_get_and_clear(mm, address, pudp);
-}
-#endif
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-
-#ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
-static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
-					    unsigned long address, pte_t *ptep,
-					    int full)
-{
-	pte_t pte;
-	pte = ptep_get_and_clear(mm, address, ptep);
-	return pte;
-}
-#endif
-
-/*
- * Some architectures may be able to avoid expensive synchronization
- * primitives when modifications are made to PTE's which are already
- * not present, or in the process of an address space destruction.
- */
-#ifndef __HAVE_ARCH_PTE_CLEAR_NOT_PRESENT_FULL
-static inline void pte_clear_not_present_full(struct mm_struct *mm,
-					      unsigned long address,
-					      pte_t *ptep,
-					      int full)
-{
-	pte_clear(mm, address, ptep);
-}
-#endif
-
-#ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH
-extern pte_t ptep_clear_flush(struct vm_area_struct *vma,
-			      unsigned long address,
-			      pte_t *ptep);
-#endif
-
-#ifndef __HAVE_ARCH_PMDP_HUGE_CLEAR_FLUSH
-extern pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma,
-			      unsigned long address,
-			      pmd_t *pmdp);
-extern pud_t pudp_huge_clear_flush(struct vm_area_struct *vma,
-			      unsigned long address,
-			      pud_t *pudp);
-#endif
-
-#ifndef __HAVE_ARCH_PTEP_SET_WRPROTECT
-struct mm_struct;
-static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep)
-{
-	pte_t old_pte = *ptep;
-	set_pte_at(mm, address, ptep, pte_wrprotect(old_pte));
-}
-#endif
-
-#ifndef pte_savedwrite
-#define pte_savedwrite pte_write
-#endif
-
-#ifndef pte_mk_savedwrite
-#define pte_mk_savedwrite pte_mkwrite
-#endif
-
-#ifndef pte_clear_savedwrite
-#define pte_clear_savedwrite pte_wrprotect
-#endif
-
-#ifndef pmd_savedwrite
-#define pmd_savedwrite pmd_write
-#endif
-
-#ifndef pmd_mk_savedwrite
-#define pmd_mk_savedwrite pmd_mkwrite
-#endif
-
-#ifndef pmd_clear_savedwrite
-#define pmd_clear_savedwrite pmd_wrprotect
-#endif
-
-#ifndef __HAVE_ARCH_PMDP_SET_WRPROTECT
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline void pmdp_set_wrprotect(struct mm_struct *mm,
-				      unsigned long address, pmd_t *pmdp)
-{
-	pmd_t old_pmd = *pmdp;
-	set_pmd_at(mm, address, pmdp, pmd_wrprotect(old_pmd));
-}
-#else
-static inline void pmdp_set_wrprotect(struct mm_struct *mm,
-				      unsigned long address, pmd_t *pmdp)
-{
-	BUILD_BUG();
-}
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-#endif
-#ifndef __HAVE_ARCH_PUDP_SET_WRPROTECT
-#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
-static inline void pudp_set_wrprotect(struct mm_struct *mm,
-				      unsigned long address, pud_t *pudp)
-{
-	pud_t old_pud = *pudp;
-
-	set_pud_at(mm, address, pudp, pud_wrprotect(old_pud));
-}
-#else
-static inline void pudp_set_wrprotect(struct mm_struct *mm,
-				      unsigned long address, pud_t *pudp)
-{
-	BUILD_BUG();
-}
-#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
-#endif
-
-#ifndef pmdp_collapse_flush
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-extern pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
-				 unsigned long address, pmd_t *pmdp);
-#else
-static inline pmd_t pmdp_collapse_flush(struct vm_area_struct *vma,
-					unsigned long address,
-					pmd_t *pmdp)
-{
-	BUILD_BUG();
-	return *pmdp;
-}
-#define pmdp_collapse_flush pmdp_collapse_flush
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-#endif
-
-#ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
-extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
-				       pgtable_t pgtable);
-#endif
-
-#ifndef __HAVE_ARCH_PGTABLE_WITHDRAW
-extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp);
-#endif
-
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-/*
- * This is an implementation of pmdp_establish() that is only suitable for an
- * architecture that doesn't have hardware dirty/accessed bits. In this case we
- * can't race with CPU which sets these bits and non-atomic aproach is fine.
- */
-static inline pmd_t generic_pmdp_establish(struct vm_area_struct *vma,
-		unsigned long address, pmd_t *pmdp, pmd_t pmd)
-{
-	pmd_t old_pmd = *pmdp;
-	set_pmd_at(vma->vm_mm, address, pmdp, pmd);
-	return old_pmd;
-}
-#endif
-
-#ifndef __HAVE_ARCH_PMDP_INVALIDATE
-extern pmd_t pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
-			    pmd_t *pmdp);
-#endif
-
-#ifndef __HAVE_ARCH_PTE_SAME
-static inline int pte_same(pte_t pte_a, pte_t pte_b)
-{
-	return pte_val(pte_a) == pte_val(pte_b);
-}
-#endif
-
-#ifndef __HAVE_ARCH_PTE_UNUSED
-/*
- * Some architectures provide facilities to virtualization guests
- * so that they can flag allocated pages as unused. This allows the
- * host to transparently reclaim unused pages. This function returns
- * whether the pte's page is unused.
- */
-static inline int pte_unused(pte_t pte)
-{
-	return 0;
-}
-#endif
-
-#ifndef pte_access_permitted
-#define pte_access_permitted(pte, write) \
-	(pte_present(pte) && (!(write) || pte_write(pte)))
-#endif
-
-#ifndef pmd_access_permitted
-#define pmd_access_permitted(pmd, write) \
-	(pmd_present(pmd) && (!(write) || pmd_write(pmd)))
-#endif
-
-#ifndef pud_access_permitted
-#define pud_access_permitted(pud, write) \
-	(pud_present(pud) && (!(write) || pud_write(pud)))
-#endif
-
-#ifndef p4d_access_permitted
-#define p4d_access_permitted(p4d, write) \
-	(p4d_present(p4d) && (!(write) || p4d_write(p4d)))
-#endif
-
-#ifndef pgd_access_permitted
-#define pgd_access_permitted(pgd, write) \
-	(pgd_present(pgd) && (!(write) || pgd_write(pgd)))
-#endif
-
-#ifndef __HAVE_ARCH_PMD_SAME
-static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
-{
-	return pmd_val(pmd_a) == pmd_val(pmd_b);
-}
-
-static inline int pud_same(pud_t pud_a, pud_t pud_b)
-{
-	return pud_val(pud_a) == pud_val(pud_b);
-}
-#endif
-
-#ifndef __HAVE_ARCH_P4D_SAME
-static inline int p4d_same(p4d_t p4d_a, p4d_t p4d_b)
-{
-	return p4d_val(p4d_a) == p4d_val(p4d_b);
-}
-#endif
-
-#ifndef __HAVE_ARCH_PGD_SAME
-static inline int pgd_same(pgd_t pgd_a, pgd_t pgd_b)
-{
-	return pgd_val(pgd_a) == pgd_val(pgd_b);
-}
-#endif
-
-/*
- * Use set_p*_safe(), and elide TLB flushing, when confident that *no*
- * TLB flush will be required as a result of the "set". For example, use
- * in scenarios where it is known ahead of time that the routine is
- * setting non-present entries, or re-setting an existing entry to the
- * same value. Otherwise, use the typical "set" helpers and flush the
- * TLB.
- */
-#define set_pte_safe(ptep, pte) \
-({ \
-	WARN_ON_ONCE(pte_present(*ptep) && !pte_same(*ptep, pte)); \
-	set_pte(ptep, pte); \
-})
-
-#define set_pmd_safe(pmdp, pmd) \
-({ \
-	WARN_ON_ONCE(pmd_present(*pmdp) && !pmd_same(*pmdp, pmd)); \
-	set_pmd(pmdp, pmd); \
-})
-
-#define set_pud_safe(pudp, pud) \
-({ \
-	WARN_ON_ONCE(pud_present(*pudp) && !pud_same(*pudp, pud)); \
-	set_pud(pudp, pud); \
-})
-
-#define set_p4d_safe(p4dp, p4d) \
-({ \
-	WARN_ON_ONCE(p4d_present(*p4dp) && !p4d_same(*p4dp, p4d)); \
-	set_p4d(p4dp, p4d); \
-})
-
-#define set_pgd_safe(pgdp, pgd) \
-({ \
-	WARN_ON_ONCE(pgd_present(*pgdp) && !pgd_same(*pgdp, pgd)); \
-	set_pgd(pgdp, pgd); \
-})
-
-#ifndef __HAVE_ARCH_DO_SWAP_PAGE
-/*
- * Some architectures support metadata associated with a page. When a
- * page is being swapped out, this metadata must be saved so it can be
- * restored when the page is swapped back in. SPARC M7 and newer
- * processors support an ADI (Application Data Integrity) tag for the
- * page as metadata for the page. arch_do_swap_page() can restore this
- * metadata when a page is swapped back in.
- */
-static inline void arch_do_swap_page(struct mm_struct *mm,
-				     struct vm_area_struct *vma,
-				     unsigned long addr,
-				     pte_t pte, pte_t oldpte)
-{
-
-}
-#endif
-
-#ifndef __HAVE_ARCH_UNMAP_ONE
-/*
- * Some architectures support metadata associated with a page. When a
- * page is being swapped out, this metadata must be saved so it can be
- * restored when the page is swapped back in. SPARC M7 and newer
- * processors support an ADI (Application Data Integrity) tag for the
- * page as metadata for the page. arch_unmap_one() can save this
- * metadata on a swap-out of a page.
- */
-static inline int arch_unmap_one(struct mm_struct *mm,
-				  struct vm_area_struct *vma,
-				  unsigned long addr,
-				  pte_t orig_pte)
-{
-	return 0;
-}
-#endif
-
-#ifndef __HAVE_ARCH_PGD_OFFSET_GATE
-#define pgd_offset_gate(mm, addr)	pgd_offset(mm, addr)
-#endif
-
-#ifndef __HAVE_ARCH_MOVE_PTE
-#define move_pte(pte, prot, old_addr, new_addr)	(pte)
-#endif
-
-#ifndef pte_accessible
-# define pte_accessible(mm, pte)	((void)(pte), 1)
-#endif
-
-#ifndef flush_tlb_fix_spurious_fault
-#define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address)
-#endif
-
-#ifndef pgprot_noncached
-#define pgprot_noncached(prot)	(prot)
-#endif
-
-#ifndef pgprot_writecombine
-#define pgprot_writecombine pgprot_noncached
-#endif
-
-#ifndef pgprot_writethrough
-#define pgprot_writethrough pgprot_noncached
-#endif
-
-#ifndef pgprot_device
-#define pgprot_device pgprot_noncached
-#endif
-
-#ifndef pgprot_modify
-#define pgprot_modify pgprot_modify
-static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
-{
-	if (pgprot_val(oldprot) == pgprot_val(pgprot_noncached(oldprot)))
-		newprot = pgprot_noncached(newprot);
-	if (pgprot_val(oldprot) == pgprot_val(pgprot_writecombine(oldprot)))
-		newprot = pgprot_writecombine(newprot);
-	if (pgprot_val(oldprot) == pgprot_val(pgprot_device(oldprot)))
-		newprot = pgprot_device(newprot);
-	return newprot;
-}
-#endif
-
-/*
- * When walking page tables, get the address of the next boundary,
- * or the end address of the range if that comes earlier.  Although no
- * vma end wraps to 0, rounded up __boundary may wrap to 0 throughout.
- */
-
-#define pgd_addr_end(addr, end)						\
-({	unsigned long __boundary = ((addr) + PGDIR_SIZE) & PGDIR_MASK;	\
-	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
-})
-
-#ifndef p4d_addr_end
-#define p4d_addr_end(addr, end)						\
-({	unsigned long __boundary = ((addr) + P4D_SIZE) & P4D_MASK;	\
-	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
-})
-#endif
-
-#ifndef pud_addr_end
-#define pud_addr_end(addr, end)						\
-({	unsigned long __boundary = ((addr) + PUD_SIZE) & PUD_MASK;	\
-	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
-})
-#endif
-
-#ifndef pmd_addr_end
-#define pmd_addr_end(addr, end)						\
-({	unsigned long __boundary = ((addr) + PMD_SIZE) & PMD_MASK;	\
-	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
-})
-#endif
-
-/*
- * When walking page tables, we usually want to skip any p?d_none entries;
- * and any p?d_bad entries - reporting the error before resetting to none.
- * Do the tests inline, but report and clear the bad entry in mm/memory.c.
- */
-void pgd_clear_bad(pgd_t *);
-void p4d_clear_bad(p4d_t *);
-void pud_clear_bad(pud_t *);
-void pmd_clear_bad(pmd_t *);
-
-static inline int pgd_none_or_clear_bad(pgd_t *pgd)
-{
-	if (pgd_none(*pgd))
-		return 1;
-	if (unlikely(pgd_bad(*pgd))) {
-		pgd_clear_bad(pgd);
-		return 1;
-	}
-	return 0;
-}
-
-static inline int p4d_none_or_clear_bad(p4d_t *p4d)
-{
-	if (p4d_none(*p4d))
-		return 1;
-	if (unlikely(p4d_bad(*p4d))) {
-		p4d_clear_bad(p4d);
-		return 1;
-	}
-	return 0;
-}
-
-static inline int pud_none_or_clear_bad(pud_t *pud)
-{
-	if (pud_none(*pud))
-		return 1;
-	if (unlikely(pud_bad(*pud))) {
-		pud_clear_bad(pud);
-		return 1;
-	}
-	return 0;
-}
-
-static inline int pmd_none_or_clear_bad(pmd_t *pmd)
-{
-	if (pmd_none(*pmd))
-		return 1;
-	if (unlikely(pmd_bad(*pmd))) {
-		pmd_clear_bad(pmd);
-		return 1;
-	}
-	return 0;
-}
-
-static inline pte_t __ptep_modify_prot_start(struct vm_area_struct *vma,
-					     unsigned long addr,
-					     pte_t *ptep)
-{
-	/*
-	 * Get the current pte state, but zero it out to make it
-	 * non-present, preventing the hardware from asynchronously
-	 * updating it.
-	 */
-	return ptep_get_and_clear(vma->vm_mm, addr, ptep);
-}
-
-static inline void __ptep_modify_prot_commit(struct vm_area_struct *vma,
-					     unsigned long addr,
-					     pte_t *ptep, pte_t pte)
-{
-	/*
-	 * The pte is non-present, so there's no hardware state to
-	 * preserve.
-	 */
-	set_pte_at(vma->vm_mm, addr, ptep, pte);
-}
-
-#ifndef __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
-/*
- * Start a pte protection read-modify-write transaction, which
- * protects against asynchronous hardware modifications to the pte.
- * The intention is not to prevent the hardware from making pte
- * updates, but to prevent any updates it may make from being lost.
- *
- * This does not protect against other software modifications of the
- * pte; the appropriate pte lock must be held over the transation.
- *
- * Note that this interface is intended to be batchable, meaning that
- * ptep_modify_prot_commit may not actually update the pte, but merely
- * queue the update to be done at some later time.  The update must be
- * actually committed before the pte lock is released, however.
- */
-static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma,
-					   unsigned long addr,
-					   pte_t *ptep)
-{
-	return __ptep_modify_prot_start(vma, addr, ptep);
-}
-
-/*
- * Commit an update to a pte, leaving any hardware-controlled bits in
- * the PTE unmodified.
- */
-static inline void ptep_modify_prot_commit(struct vm_area_struct *vma,
-					   unsigned long addr,
-					   pte_t *ptep, pte_t old_pte, pte_t pte)
-{
-	__ptep_modify_prot_commit(vma, addr, ptep, pte);
-}
-#endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */
-#endif /* CONFIG_MMU */
-
-/*
- * No-op macros that just return the current protection value. Defined here
- * because these macros can be used used even if CONFIG_MMU is not defined.
- */
-#ifndef pgprot_encrypted
-#define pgprot_encrypted(prot)	(prot)
-#endif
-
-#ifndef pgprot_decrypted
-#define pgprot_decrypted(prot)	(prot)
-#endif
-
-/*
- * A facility to provide lazy MMU batching.  This allows PTE updates and
- * page invalidations to be delayed until a call to leave lazy MMU mode
- * is issued.  Some architectures may benefit from doing this, and it is
- * beneficial for both shadow and direct mode hypervisors, which may batch
- * the PTE updates which happen during this window.  Note that using this
- * interface requires that read hazards be removed from the code.  A read
- * hazard could result in the direct mode hypervisor case, since the actual
- * write to the page tables may not yet have taken place, so reads though
- * a raw PTE pointer after it has been modified are not guaranteed to be
- * up to date.  This mode can only be entered and left under the protection of
- * the page table locks for all page tables which may be modified.  In the UP
- * case, this is required so that preemption is disabled, and in the SMP case,
- * it must synchronize the delayed page table writes properly on other CPUs.
- */
-#ifndef __HAVE_ARCH_ENTER_LAZY_MMU_MODE
-#define arch_enter_lazy_mmu_mode()	do {} while (0)
-#define arch_leave_lazy_mmu_mode()	do {} while (0)
-#define arch_flush_lazy_mmu_mode()	do {} while (0)
-#endif
-
-/*
- * A facility to provide batching of the reload of page tables and
- * other process state with the actual context switch code for
- * paravirtualized guests.  By convention, only one of the batched
- * update (lazy) modes (CPU, MMU) should be active at any given time,
- * entry should never be nested, and entry and exits should always be
- * paired.  This is for sanity of maintaining and reasoning about the
- * kernel code.  In this case, the exit (end of the context switch) is
- * in architecture-specific code, and so doesn't need a generic
- * definition.
- */
-#ifndef __HAVE_ARCH_START_CONTEXT_SWITCH
-#define arch_start_context_switch(prev)	do {} while (0)
-#endif
-
-#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
-#ifndef CONFIG_ARCH_ENABLE_THP_MIGRATION
-static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd)
-{
-	return pmd;
-}
-
-static inline int pmd_swp_soft_dirty(pmd_t pmd)
-{
-	return 0;
-}
-
-static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd)
-{
-	return pmd;
-}
-#endif
-#else /* !CONFIG_HAVE_ARCH_SOFT_DIRTY */
-static inline int pte_soft_dirty(pte_t pte)
-{
-	return 0;
-}
-
-static inline int pmd_soft_dirty(pmd_t pmd)
-{
-	return 0;
-}
-
-static inline pte_t pte_mksoft_dirty(pte_t pte)
-{
-	return pte;
-}
-
-static inline pmd_t pmd_mksoft_dirty(pmd_t pmd)
-{
-	return pmd;
-}
-
-static inline pte_t pte_clear_soft_dirty(pte_t pte)
-{
-	return pte;
-}
-
-static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd)
-{
-	return pmd;
-}
-
-static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
-{
-	return pte;
-}
-
-static inline int pte_swp_soft_dirty(pte_t pte)
-{
-	return 0;
-}
-
-static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
-{
-	return pte;
-}
-
-static inline pmd_t pmd_swp_mksoft_dirty(pmd_t pmd)
-{
-	return pmd;
-}
-
-static inline int pmd_swp_soft_dirty(pmd_t pmd)
-{
-	return 0;
-}
-
-static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd)
-{
-	return pmd;
-}
-#endif
-
-#ifndef __HAVE_PFNMAP_TRACKING
-/*
- * Interfaces that can be used by architecture code to keep track of
- * memory type of pfn mappings specified by the remap_pfn_range,
- * vmf_insert_pfn.
- */
-
-/*
- * track_pfn_remap is called when a _new_ pfn mapping is being established
- * by remap_pfn_range() for physical range indicated by pfn and size.
- */
-static inline int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
-				  unsigned long pfn, unsigned long addr,
-				  unsigned long size)
-{
-	return 0;
-}
-
-/*
- * track_pfn_insert is called when a _new_ single pfn is established
- * by vmf_insert_pfn().
- */
-static inline void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
-				    pfn_t pfn)
-{
-}
-
-/*
- * track_pfn_copy is called when vma that is covering the pfnmap gets
- * copied through copy_page_range().
- */
-static inline int track_pfn_copy(struct vm_area_struct *vma)
-{
-	return 0;
-}
-
-/*
- * untrack_pfn is called while unmapping a pfnmap for a region.
- * untrack can be called for a specific region indicated by pfn and size or
- * can be for the entire vma (in which case pfn, size are zero).
- */
-static inline void untrack_pfn(struct vm_area_struct *vma,
-			       unsigned long pfn, unsigned long size)
-{
-}
-
-/*
- * untrack_pfn_moved is called while mremapping a pfnmap for a new region.
- */
-static inline void untrack_pfn_moved(struct vm_area_struct *vma)
-{
-}
-#else
-extern int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
-			   unsigned long pfn, unsigned long addr,
-			   unsigned long size);
-extern void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
-			     pfn_t pfn);
-extern int track_pfn_copy(struct vm_area_struct *vma);
-extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
-			unsigned long size);
-extern void untrack_pfn_moved(struct vm_area_struct *vma);
-#endif
-
-#ifdef __HAVE_COLOR_ZERO_PAGE
-static inline int is_zero_pfn(unsigned long pfn)
-{
-	extern unsigned long zero_pfn;
-	unsigned long offset_from_zero_pfn = pfn - zero_pfn;
-	return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT);
-}
-
-#define my_zero_pfn(addr)	page_to_pfn(ZERO_PAGE(addr))
-
-#else
-static inline int is_zero_pfn(unsigned long pfn)
-{
-	extern unsigned long zero_pfn;
-	return pfn == zero_pfn;
-}
-
-static inline unsigned long my_zero_pfn(unsigned long addr)
-{
-	extern unsigned long zero_pfn;
-	return zero_pfn;
-}
-#endif
-
-#ifdef CONFIG_MMU
-
-#ifndef CONFIG_TRANSPARENT_HUGEPAGE
-static inline int pmd_trans_huge(pmd_t pmd)
-{
-	return 0;
-}
-#ifndef pmd_write
-static inline int pmd_write(pmd_t pmd)
-{
-	BUG();
-	return 0;
-}
-#endif /* pmd_write */
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-
-#ifndef pud_write
-static inline int pud_write(pud_t pud)
-{
-	BUG();
-	return 0;
-}
-#endif /* pud_write */
-
-#if !defined(CONFIG_TRANSPARENT_HUGEPAGE) || \
-	(defined(CONFIG_TRANSPARENT_HUGEPAGE) && \
-	 !defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD))
-static inline int pud_trans_huge(pud_t pud)
-{
-	return 0;
-}
-#endif
-
-#ifndef pmd_read_atomic
-static inline pmd_t pmd_read_atomic(pmd_t *pmdp)
-{
-	/*
-	 * Depend on compiler for an atomic pmd read. NOTE: this is
-	 * only going to work, if the pmdval_t isn't larger than
-	 * an unsigned long.
-	 */
-	return *pmdp;
-}
-#endif
-
-#ifndef arch_needs_pgtable_deposit
-#define arch_needs_pgtable_deposit() (false)
-#endif
-/*
- * This function is meant to be used by sites walking pagetables with
- * the mmap_sem hold in read mode to protect against MADV_DONTNEED and
- * transhuge page faults. MADV_DONTNEED can convert a transhuge pmd
- * into a null pmd and the transhuge page fault can convert a null pmd
- * into an hugepmd or into a regular pmd (if the hugepage allocation
- * fails). While holding the mmap_sem in read mode the pmd becomes
- * stable and stops changing under us only if it's not null and not a
- * transhuge pmd. When those races occurs and this function makes a
- * difference vs the standard pmd_none_or_clear_bad, the result is
- * undefined so behaving like if the pmd was none is safe (because it
- * can return none anyway). The compiler level barrier() is critically
- * important to compute the two checks atomically on the same pmdval.
- *
- * For 32bit kernels with a 64bit large pmd_t this automatically takes
- * care of reading the pmd atomically to avoid SMP race conditions
- * against pmd_populate() when the mmap_sem is hold for reading by the
- * caller (a special atomic read not done by "gcc" as in the generic
- * version above, is also needed when THP is disabled because the page
- * fault can populate the pmd from under us).
- */
-static inline int pmd_none_or_trans_huge_or_clear_bad(pmd_t *pmd)
-{
-	pmd_t pmdval = pmd_read_atomic(pmd);
-	/*
-	 * The barrier will stabilize the pmdval in a register or on
-	 * the stack so that it will stop changing under the code.
-	 *
-	 * When CONFIG_TRANSPARENT_HUGEPAGE=y on x86 32bit PAE,
-	 * pmd_read_atomic is allowed to return a not atomic pmdval
-	 * (for example pointing to an hugepage that has never been
-	 * mapped in the pmd). The below checks will only care about
-	 * the low part of the pmd with 32bit PAE x86 anyway, with the
-	 * exception of pmd_none(). So the important thing is that if
-	 * the low part of the pmd is found null, the high part will
-	 * be also null or the pmd_none() check below would be
-	 * confused.
-	 */
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	barrier();
-#endif
-	/*
-	 * !pmd_present() checks for pmd migration entries
-	 *
-	 * The complete check uses is_pmd_migration_entry() in linux/swapops.h
-	 * But using that requires moving current function and pmd_trans_unstable()
-	 * to linux/swapops.h to resovle dependency, which is too much code move.
-	 *
-	 * !pmd_present() is equivalent to is_pmd_migration_entry() currently,
-	 * because !pmd_present() pages can only be under migration not swapped
-	 * out.
-	 *
-	 * pmd_none() is preseved for future condition checks on pmd migration
-	 * entries and not confusing with this function name, although it is
-	 * redundant with !pmd_present().
-	 */
-	if (pmd_none(pmdval) || pmd_trans_huge(pmdval) ||
-		(IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION) && !pmd_present(pmdval)))
-		return 1;
-	if (unlikely(pmd_bad(pmdval))) {
-		pmd_clear_bad(pmd);
-		return 1;
-	}
-	return 0;
-}
-
-/*
- * This is a noop if Transparent Hugepage Support is not built into
- * the kernel. Otherwise it is equivalent to
- * pmd_none_or_trans_huge_or_clear_bad(), and shall only be called in
- * places that already verified the pmd is not none and they want to
- * walk ptes while holding the mmap sem in read mode (write mode don't
- * need this). If THP is not enabled, the pmd can't go away under the
- * code even if MADV_DONTNEED runs, but if THP is enabled we need to
- * run a pmd_trans_unstable before walking the ptes after
- * split_huge_pmd returns (because it may have run when the pmd become
- * null, but then a page fault can map in a THP and not a regular page).
- */
-static inline int pmd_trans_unstable(pmd_t *pmd)
-{
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	return pmd_none_or_trans_huge_or_clear_bad(pmd);
-#else
-	return 0;
-#endif
-}
-
-#ifndef CONFIG_NUMA_BALANCING
-/*
- * Technically a PTE can be PROTNONE even when not doing NUMA balancing but
- * the only case the kernel cares is for NUMA balancing and is only ever set
- * when the VMA is accessible. For PROT_NONE VMAs, the PTEs are not marked
- * _PAGE_PROTNONE so by by default, implement the helper as "always no". It
- * is the responsibility of the caller to distinguish between PROT_NONE
- * protections and NUMA hinting fault protections.
- */
-static inline int pte_protnone(pte_t pte)
-{
-	return 0;
-}
-
-static inline int pmd_protnone(pmd_t pmd)
-{
-	return 0;
-}
-#endif /* CONFIG_NUMA_BALANCING */
-
-#endif /* CONFIG_MMU */
-
-#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
-
-#ifndef __PAGETABLE_P4D_FOLDED
-int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot);
-int p4d_clear_huge(p4d_t *p4d);
-#else
-static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
-{
-	return 0;
-}
-static inline int p4d_clear_huge(p4d_t *p4d)
-{
-	return 0;
-}
-#endif /* !__PAGETABLE_P4D_FOLDED */
-
-int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot);
-int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot);
-int pud_clear_huge(pud_t *pud);
-int pmd_clear_huge(pmd_t *pmd);
-int p4d_free_pud_page(p4d_t *p4d, unsigned long addr);
-int pud_free_pmd_page(pud_t *pud, unsigned long addr);
-int pmd_free_pte_page(pmd_t *pmd, unsigned long addr);
-#else	/* !CONFIG_HAVE_ARCH_HUGE_VMAP */
-static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
-{
-	return 0;
-}
-static inline int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
-{
-	return 0;
-}
-static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
-{
-	return 0;
-}
-static inline int p4d_clear_huge(p4d_t *p4d)
-{
-	return 0;
-}
-static inline int pud_clear_huge(pud_t *pud)
-{
-	return 0;
-}
-static inline int pmd_clear_huge(pmd_t *pmd)
-{
-	return 0;
-}
-static inline int p4d_free_pud_page(p4d_t *p4d, unsigned long addr)
-{
-	return 0;
-}
-static inline int pud_free_pmd_page(pud_t *pud, unsigned long addr)
-{
-	return 0;
-}
-static inline int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
-{
-	return 0;
-}
-#endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP */
-
-#ifndef __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-/*
- * ARCHes with special requirements for evicting THP backing TLB entries can
- * implement this. Otherwise also, it can help optimize normal TLB flush in
- * THP regime. stock flush_tlb_range() typically has optimization to nuke the
- * entire TLB TLB if flush span is greater than a threshold, which will
- * likely be true for a single huge page. Thus a single thp flush will
- * invalidate the entire TLB which is not desitable.
- * e.g. see arch/arc: flush_pmd_tlb_range
- */
-#define flush_pmd_tlb_range(vma, addr, end)	flush_tlb_range(vma, addr, end)
-#define flush_pud_tlb_range(vma, addr, end)	flush_tlb_range(vma, addr, end)
-#else
-#define flush_pmd_tlb_range(vma, addr, end)	BUILD_BUG()
-#define flush_pud_tlb_range(vma, addr, end)	BUILD_BUG()
-#endif
-#endif
-
-struct file;
-int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
-			unsigned long size, pgprot_t *vma_prot);
-
-#ifndef CONFIG_X86_ESPFIX64
-static inline void init_espfix_bsp(void) { }
-#endif
-
-extern void __init pgtable_cache_init(void);
-
-#ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED
-static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot)
-{
-	return true;
-}
-
-static inline bool arch_has_pfn_modify_check(void)
-{
-	return false;
-}
-#endif /* !_HAVE_ARCH_PFN_MODIFY_ALLOWED */
-
-/*
- * Architecture PAGE_KERNEL_* fallbacks
- *
- * Some architectures don't define certain PAGE_KERNEL_* flags. This is either
- * because they really don't support them, or the port needs to be updated to
- * reflect the required functionality. Below are a set of relatively safe
- * fallbacks, as best effort, which we can count on in lieu of the architectures
- * not defining them on their own yet.
- */
-
-#ifndef PAGE_KERNEL_RO
-# define PAGE_KERNEL_RO PAGE_KERNEL
-#endif
-
-#ifndef PAGE_KERNEL_EXEC
-# define PAGE_KERNEL_EXEC PAGE_KERNEL
-#endif
-
-#endif /* !__ASSEMBLY__ */
-
-#if !defined(MAX_POSSIBLE_PHYSMEM_BITS) && !defined(CONFIG_64BIT)
-#ifdef CONFIG_PHYS_ADDR_T_64BIT
-/*
- * ZSMALLOC needs to know the highest PFN on 32-bit architectures
- * with physical address space extension, but falls back to
- * BITS_PER_LONG otherwise.
- */
-#error Missing MAX_POSSIBLE_PHYSMEM_BITS definition
-#else
-#define MAX_POSSIBLE_PHYSMEM_BITS 32
-#endif
-#endif
-
-#ifndef has_transparent_hugepage
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#define has_transparent_hugepage() 1
-#else
-#define has_transparent_hugepage() 0
-#endif
-#endif
-
-#ifndef p4d_offset_lockless
-#define p4d_offset_lockless(pgdp, pgd, address) p4d_offset(&(pgd), address)
-#endif
-#ifndef pud_offset_lockless
-#define pud_offset_lockless(p4dp, p4d, address) pud_offset(&(p4d), address)
-#endif
-#ifndef pmd_offset_lockless
-#define pmd_offset_lockless(pudp, pud, address) pmd_offset(&(pud), address)
-#endif
-
-/*
- * On some architectures it depends on the mm if the p4d/pud or pmd
- * layer of the page table hierarchy is folded or not.
- */
-#ifndef mm_p4d_folded
-#define mm_p4d_folded(mm)	__is_defined(__PAGETABLE_P4D_FOLDED)
-#endif
-
-#ifndef mm_pud_folded
-#define mm_pud_folded(mm)	__is_defined(__PAGETABLE_PUD_FOLDED)
-#endif
-
-#ifndef mm_pmd_folded
-#define mm_pmd_folded(mm)	__is_defined(__PAGETABLE_PMD_FOLDED)
-#endif
-
-#endif /* _ASM_GENERIC_PGTABLE_H */
diff --git a/include/asm-generic/pgtable_uffd.h b/include/asm-generic/pgtable_uffd.h
new file mode 100644
index 0000000..828966d
--- /dev/null
+++ b/include/asm-generic/pgtable_uffd.h
@@ -0,0 +1,66 @@
+#ifndef _ASM_GENERIC_PGTABLE_UFFD_H
+#define _ASM_GENERIC_PGTABLE_UFFD_H
+
+#ifndef CONFIG_HAVE_ARCH_USERFAULTFD_WP
+static __always_inline int pte_uffd_wp(pte_t pte)
+{
+	return 0;
+}
+
+static __always_inline int pmd_uffd_wp(pmd_t pmd)
+{
+	return 0;
+}
+
+static __always_inline pte_t pte_mkuffd_wp(pte_t pte)
+{
+	return pte;
+}
+
+static __always_inline pmd_t pmd_mkuffd_wp(pmd_t pmd)
+{
+	return pmd;
+}
+
+static __always_inline pte_t pte_clear_uffd_wp(pte_t pte)
+{
+	return pte;
+}
+
+static __always_inline pmd_t pmd_clear_uffd_wp(pmd_t pmd)
+{
+	return pmd;
+}
+
+static __always_inline pte_t pte_swp_mkuffd_wp(pte_t pte)
+{
+	return pte;
+}
+
+static __always_inline int pte_swp_uffd_wp(pte_t pte)
+{
+	return 0;
+}
+
+static __always_inline pte_t pte_swp_clear_uffd_wp(pte_t pte)
+{
+	return pte;
+}
+
+static inline pmd_t pmd_swp_mkuffd_wp(pmd_t pmd)
+{
+	return pmd;
+}
+
+static inline int pmd_swp_uffd_wp(pmd_t pmd)
+{
+	return 0;
+}
+
+static inline pmd_t pmd_swp_clear_uffd_wp(pmd_t pmd)
+{
+	return pmd;
+}
+#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */
+
+#endif /* _ASM_GENERIC_PGTABLE_UFFD_H */
diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
index d683f5e..b4d43a4 100644
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -29,7 +29,7 @@
 } while (0)
 
 #define init_idle_preempt_count(p, cpu) do { \
-	task_thread_info(p)->preempt_count = PREEMPT_ENABLED; \
+	task_thread_info(p)->preempt_count = PREEMPT_DISABLED; \
 } while (0)
 
 static __always_inline void set_preempt_need_resched(void)
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index fde943d..4fe7fd0 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -11,7 +11,9 @@
 #define __ASM_GENERIC_QSPINLOCK_H
 
 #include <asm-generic/qspinlock_types.h>
+#include <linux/atomic.h>
 
+#ifndef queued_spin_is_locked
 /**
  * queued_spin_is_locked - is the spinlock locked?
  * @lock: Pointer to queued spinlock structure
@@ -25,6 +27,7 @@
 	 */
 	return atomic_read(&lock->val);
 }
+#endif
 
 /**
  * queued_spin_value_unlocked - is the spinlock structure unlocked?
@@ -67,6 +70,7 @@
 
 extern void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
 
+#ifndef queued_spin_lock
 /**
  * queued_spin_lock - acquire a queued spinlock
  * @lock: Pointer to queued spinlock structure
@@ -80,6 +84,7 @@
 
 	queued_spin_lock_slowpath(lock, val);
 }
+#endif
 
 #ifndef queued_spin_unlock
 /**
diff --git a/include/asm-generic/qspinlock_types.h b/include/asm-generic/qspinlock_types.h
index 56d1309..2fd1fb8 100644
--- a/include/asm-generic/qspinlock_types.h
+++ b/include/asm-generic/qspinlock_types.h
@@ -9,15 +9,7 @@
 #ifndef __ASM_GENERIC_QSPINLOCK_TYPES_H
 #define __ASM_GENERIC_QSPINLOCK_TYPES_H
 
-/*
- * Including atomic.h with PARAVIRT on will cause compilation errors because
- * of recursive header file incluson via paravirt_types.h. So don't include
- * it if PARAVIRT is on.
- */
-#ifndef CONFIG_PARAVIRT
 #include <linux/types.h>
-#include <linux/atomic.h>
-#endif
 
 typedef struct qspinlock {
 	union {
diff --git a/include/asm-generic/rwonce.h b/include/asm-generic/rwonce.h
new file mode 100644
index 0000000..8d0a628
--- /dev/null
+++ b/include/asm-generic/rwonce.h
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Prevent the compiler from merging or refetching reads or writes. The
+ * compiler is also forbidden from reordering successive instances of
+ * READ_ONCE and WRITE_ONCE, but only when the compiler is aware of some
+ * particular ordering. One way to make the compiler aware of ordering is to
+ * put the two invocations of READ_ONCE or WRITE_ONCE in different C
+ * statements.
+ *
+ * These two macros will also work on aggregate data types like structs or
+ * unions.
+ *
+ * Their two major use cases are: (1) Mediating communication between
+ * process-level code and irq/NMI handlers, all running on the same CPU,
+ * and (2) Ensuring that the compiler does not fold, spindle, or otherwise
+ * mutilate accesses that either do not require ordering or that interact
+ * with an explicit memory barrier or atomic instruction that provides the
+ * required ordering.
+ */
+#ifndef __ASM_GENERIC_RWONCE_H
+#define __ASM_GENERIC_RWONCE_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/compiler_types.h>
+#include <linux/kasan-checks.h>
+#include <linux/kcsan-checks.h>
+
+/*
+ * Yes, this permits 64-bit accesses on 32-bit architectures. These will
+ * actually be atomic in some cases (namely Armv7 + LPAE), but for others we
+ * rely on the access being split into 2x32-bit accesses for a 32-bit quantity
+ * (e.g. a virtual address) and a strong prevailing wind.
+ */
+#define compiletime_assert_rwonce_type(t)					\
+	compiletime_assert(__native_word(t) || sizeof(t) == sizeof(long long),	\
+		"Unsupported access size for {READ,WRITE}_ONCE().")
+
+/*
+ * Use __READ_ONCE() instead of READ_ONCE() if you do not require any
+ * atomicity. Note that this may result in tears!
+ */
+#ifndef __READ_ONCE
+#define __READ_ONCE(x)	(*(const volatile __unqual_scalar_typeof(x) *)&(x))
+#endif
+
+#define READ_ONCE(x)							\
+({									\
+	compiletime_assert_rwonce_type(x);				\
+	__READ_ONCE(x);							\
+})
+
+#define __WRITE_ONCE(x, val)						\
+do {									\
+	*(volatile typeof(x) *)&(x) = (val);				\
+} while (0)
+
+#define WRITE_ONCE(x, val)						\
+do {									\
+	compiletime_assert_rwonce_type(x);				\
+	__WRITE_ONCE(x, val);						\
+} while (0)
+
+static __no_sanitize_or_inline
+unsigned long __read_once_word_nocheck(const void *addr)
+{
+	return __READ_ONCE(*(unsigned long *)addr);
+}
+
+/*
+ * Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need to load a
+ * word from memory atomically but without telling KASAN/KCSAN. This is
+ * usually used by unwinding code when walking the stack of a running process.
+ */
+#define READ_ONCE_NOCHECK(x)						\
+({									\
+	compiletime_assert(sizeof(x) == sizeof(unsigned long),		\
+		"Unsupported access size for READ_ONCE_NOCHECK().");	\
+	(typeof(x))__read_once_word_nocheck(&(x));			\
+})
+
+static __no_kasan_or_inline
+unsigned long read_word_at_a_time(const void *addr)
+{
+	kasan_check_read(addr, 1);
+	return *(unsigned long *)addr;
+}
+
+#endif /* __ASSEMBLY__ */
+#endif	/* __ASM_GENERIC_RWONCE_H */
diff --git a/include/asm-generic/seccomp.h b/include/asm-generic/seccomp.h
index 1321ac7..6b6f42b 100644
--- a/include/asm-generic/seccomp.h
+++ b/include/asm-generic/seccomp.h
@@ -33,7 +33,7 @@
 	static const int mode1_syscalls_32[] = {
 		__NR_seccomp_read_32, __NR_seccomp_write_32,
 		__NR_seccomp_exit_32, __NR_seccomp_sigreturn_32,
-		0, /* null terminated */
+		-1, /* negative terminated */
 	};
 	return mode1_syscalls_32;
 }
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index 66397ed..d16302d 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -60,8 +60,8 @@
 
 /* Function descriptor handling (if any).  Override in asm/sections.h */
 #ifndef dereference_function_descriptor
-#define dereference_function_descriptor(p) (p)
-#define dereference_kernel_function_descriptor(p) (p)
+#define dereference_function_descriptor(p) ((void *)(p))
+#define dereference_kernel_function_descriptor(p) ((void *)(p))
 #endif
 
 /* random extra sections (if any).  Override
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index c716ea8..6661ee1 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -13,7 +13,7 @@
 
 #include <linux/mmu_notifier.h>
 #include <linux/swap.h>
-#include <asm/pgalloc.h>
+#include <linux/hugetlb_inline.h>
 #include <asm/tlbflush.h>
 #include <asm/cacheflush.h>
 
@@ -56,6 +56,15 @@
  *    Defaults to flushing at tlb_end_vma() to reset the range; helps when
  *    there's large holes between the VMAs.
  *
+ *  - tlb_remove_table()
+ *
+ *    tlb_remove_table() is the basic primitive to free page-table directories
+ *    (__p*_free_tlb()).  In it's most primitive form it is an alias for
+ *    tlb_remove_page() below, for when page directories are pages and have no
+ *    additional constraints.
+ *
+ *    See also MMU_GATHER_TABLE_FREE and MMU_GATHER_RCU_TABLE_FREE.
+ *
  *  - tlb_remove_page() / __tlb_remove_page()
  *  - tlb_remove_page_size() / __tlb_remove_page_size()
  *
@@ -121,58 +130,53 @@
  *
  * Additionally there are a few opt-in features:
  *
- *  HAVE_MMU_GATHER_PAGE_SIZE
+ *  MMU_GATHER_PAGE_SIZE
  *
  *  This ensures we call tlb_flush() every time tlb_change_page_size() actually
  *  changes the size and provides mmu_gather::page_size to tlb_flush().
  *
- *  HAVE_RCU_TABLE_FREE
+ *  This might be useful if your architecture has size specific TLB
+ *  invalidation instructions.
+ *
+ *  MMU_GATHER_TABLE_FREE
  *
  *  This provides tlb_remove_table(), to be used instead of tlb_remove_page()
- *  for page directores (__p*_free_tlb()). This provides separate freeing of
- *  the page-table pages themselves in a semi-RCU fashion (see comment below).
- *  Useful if your architecture doesn't use IPIs for remote TLB invalidates
- *  and therefore doesn't naturally serialize with software page-table walkers.
+ *  for page directores (__p*_free_tlb()).
+ *
+ *  Useful if your architecture has non-page page directories.
  *
  *  When used, an architecture is expected to provide __tlb_remove_table()
  *  which does the actual freeing of these pages.
  *
+ *  MMU_GATHER_RCU_TABLE_FREE
+ *
+ *  Like MMU_GATHER_TABLE_FREE, and adds semi-RCU semantics to the free (see
+ *  comment below).
+ *
+ *  Useful if your architecture doesn't use IPIs for remote TLB invalidates
+ *  and therefore doesn't naturally serialize with software page-table walkers.
+ *
  *  MMU_GATHER_NO_RANGE
  *
  *  Use this if your architecture lacks an efficient flush_tlb_range().
+ *
+ *  MMU_GATHER_NO_GATHER
+ *
+ *  If the option is set the mmu_gather will not track individual pages for
+ *  delayed page free anymore. A platform that enables the option needs to
+ *  provide its own implementation of the __tlb_remove_page_size() function to
+ *  free pages.
+ *
+ *  This is useful if your architecture already flushes TLB entries in the
+ *  various ptep_get_and_clear() functions.
  */
 
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
-/*
- * Semi RCU freeing of the page directories.
- *
- * This is needed by some architectures to implement software pagetable walkers.
- *
- * gup_fast() and other software pagetable walkers do a lockless page-table
- * walk and therefore needs some synchronization with the freeing of the page
- * directories. The chosen means to accomplish that is by disabling IRQs over
- * the walk.
- *
- * Architectures that use IPIs to flush TLBs will then automagically DTRT,
- * since we unlink the page, flush TLBs, free the page. Since the disabling of
- * IRQs delays the completion of the TLB flush we can never observe an already
- * freed page.
- *
- * Architectures that do not have this (PPC) need to delay the freeing by some
- * other means, this is that means.
- *
- * What we do is batch the freed directory pages (tables) and RCU free them.
- * We use the sched RCU variant, as that guarantees that IRQ/preempt disabling
- * holds off grace periods.
- *
- * However, in order to batch these pages we need to allocate storage, this
- * allocation is deep inside the MM code and can thus easily fail on memory
- * pressure. To guarantee progress we fall back to single table freeing, see
- * the implementation of tlb_remove_table_one().
- *
- */
+#ifdef CONFIG_MMU_GATHER_TABLE_FREE
+
 struct mmu_table_batch {
+#ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE
 	struct rcu_head		rcu;
+#endif
 	unsigned int		nr;
 	void			*tables[0];
 };
@@ -182,6 +186,17 @@
 
 extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
 
+#else /* !CONFIG_MMU_GATHER_HAVE_TABLE_FREE */
+
+/*
+ * Without MMU_GATHER_TABLE_FREE the architecture is assumed to have page based
+ * page directories and we can use the normal page batching to free them.
+ */
+#define tlb_remove_table(tlb, page) tlb_remove_page((tlb), (page))
+
+#endif /* CONFIG_MMU_GATHER_TABLE_FREE */
+
+#ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE
 /*
  * This allows an architecture that does not use the linux page-tables for
  * hardware to skip the TLBI when freeing page tables.
@@ -193,13 +208,13 @@
 #else
 
 #ifdef tlb_needs_table_invalidate
-#error tlb_needs_table_invalidate() requires HAVE_RCU_TABLE_FREE
+#error tlb_needs_table_invalidate() requires MMU_GATHER_RCU_TABLE_FREE
 #endif
 
-#endif /* CONFIG_HAVE_RCU_TABLE_FREE */
+#endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */
 
 
-#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+#ifndef CONFIG_MMU_GATHER_NO_GATHER
 /*
  * If we can't allocate a page to make a big batch of page pointers
  * to work on, then just handle a few from the on-stack structure.
@@ -235,7 +250,7 @@
 struct mmu_gather {
 	struct mm_struct	*mm;
 
-#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+#ifdef CONFIG_MMU_GATHER_TABLE_FREE
 	struct mmu_table_batch	*batch;
 #endif
 
@@ -274,22 +289,18 @@
 
 	unsigned int		batch_count;
 
-#ifndef CONFIG_HAVE_MMU_GATHER_NO_GATHER
+#ifndef CONFIG_MMU_GATHER_NO_GATHER
 	struct mmu_gather_batch *active;
 	struct mmu_gather_batch	local;
 	struct page		*__pages[MMU_GATHER_BUNDLE];
 
-#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
+#ifdef CONFIG_MMU_GATHER_PAGE_SIZE
 	unsigned int page_size;
 #endif
 #endif
 };
 
-void arch_tlb_gather_mmu(struct mmu_gather *tlb,
-	struct mm_struct *mm, unsigned long start, unsigned long end);
 void tlb_flush_mmu(struct mmu_gather *tlb);
-void arch_tlb_finish_mmu(struct mmu_gather *tlb,
-			 unsigned long start, unsigned long end, bool force);
 
 static inline void __tlb_adjust_range(struct mmu_gather *tlb,
 				      unsigned long address,
@@ -387,7 +398,7 @@
 	 * We rely on tlb_end_vma() to issue a flush, such that when we reset
 	 * these values the batch is empty.
 	 */
-	tlb->vma_huge = !!(vma->vm_flags & VM_HUGETLB);
+	tlb->vma_huge = is_vm_hugetlb_page(vma);
 	tlb->vma_exec = !!(vma->vm_flags & VM_EXEC);
 }
 
@@ -402,7 +413,12 @@
 
 static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
 {
-	if (!tlb->end)
+	/*
+	 * Anything calling __tlb_adjust_range() also sets at least one of
+	 * these bits.
+	 */
+	if (!(tlb->freed_tables || tlb->cleared_ptes || tlb->cleared_pmds ||
+	      tlb->cleared_puds || tlb->cleared_p4ds))
 		return;
 
 	tlb_flush(tlb);
@@ -434,9 +450,9 @@
 static inline void tlb_change_page_size(struct mmu_gather *tlb,
 						     unsigned int page_size)
 {
-#ifdef CONFIG_HAVE_MMU_GATHER_PAGE_SIZE
+#ifdef CONFIG_MMU_GATHER_PAGE_SIZE
 	if (tlb->page_size && tlb->page_size != page_size) {
-		if (!tlb->fullmm)
+		if (!tlb->fullmm && !tlb->need_flush_all)
 			tlb_flush_mmu(tlb);
 	}
 
@@ -495,6 +511,38 @@
 }
 #endif
 
+/*
+ * tlb_flush_{pte|pmd|pud|p4d}_range() adjust the tlb->start and tlb->end,
+ * and set corresponding cleared_*.
+ */
+static inline void tlb_flush_pte_range(struct mmu_gather *tlb,
+				     unsigned long address, unsigned long size)
+{
+	__tlb_adjust_range(tlb, address, size);
+	tlb->cleared_ptes = 1;
+}
+
+static inline void tlb_flush_pmd_range(struct mmu_gather *tlb,
+				     unsigned long address, unsigned long size)
+{
+	__tlb_adjust_range(tlb, address, size);
+	tlb->cleared_pmds = 1;
+}
+
+static inline void tlb_flush_pud_range(struct mmu_gather *tlb,
+				     unsigned long address, unsigned long size)
+{
+	__tlb_adjust_range(tlb, address, size);
+	tlb->cleared_puds = 1;
+}
+
+static inline void tlb_flush_p4d_range(struct mmu_gather *tlb,
+				     unsigned long address, unsigned long size)
+{
+	__tlb_adjust_range(tlb, address, size);
+	tlb->cleared_p4ds = 1;
+}
+
 #ifndef __tlb_remove_tlb_entry
 #define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
 #endif
@@ -508,19 +556,17 @@
  */
 #define tlb_remove_tlb_entry(tlb, ptep, address)		\
 	do {							\
-		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
-		tlb->cleared_ptes = 1;				\
+		tlb_flush_pte_range(tlb, address, PAGE_SIZE);	\
 		__tlb_remove_tlb_entry(tlb, ptep, address);	\
 	} while (0)
 
 #define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
 	do {							\
 		unsigned long _sz = huge_page_size(h);		\
-		__tlb_adjust_range(tlb, address, _sz);		\
 		if (_sz == PMD_SIZE)				\
-			tlb->cleared_pmds = 1;			\
+			tlb_flush_pmd_range(tlb, address, _sz);	\
 		else if (_sz == PUD_SIZE)			\
-			tlb->cleared_puds = 1;			\
+			tlb_flush_pud_range(tlb, address, _sz);	\
 		__tlb_remove_tlb_entry(tlb, ptep, address);	\
 	} while (0)
 
@@ -534,8 +580,7 @@
 
 #define tlb_remove_pmd_tlb_entry(tlb, pmdp, address)			\
 	do {								\
-		__tlb_adjust_range(tlb, address, HPAGE_PMD_SIZE);	\
-		tlb->cleared_pmds = 1;					\
+		tlb_flush_pmd_range(tlb, address, HPAGE_PMD_SIZE);	\
 		__tlb_remove_pmd_tlb_entry(tlb, pmdp, address);		\
 	} while (0)
 
@@ -549,8 +594,7 @@
 
 #define tlb_remove_pud_tlb_entry(tlb, pudp, address)			\
 	do {								\
-		__tlb_adjust_range(tlb, address, HPAGE_PUD_SIZE);	\
-		tlb->cleared_puds = 1;					\
+		tlb_flush_pud_range(tlb, address, HPAGE_PUD_SIZE);	\
 		__tlb_remove_pud_tlb_entry(tlb, pudp, address);		\
 	} while (0)
 
@@ -575,9 +619,8 @@
 #ifndef pte_free_tlb
 #define pte_free_tlb(tlb, ptep, address)			\
 	do {							\
-		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
+		tlb_flush_pmd_range(tlb, address, PAGE_SIZE);	\
 		tlb->freed_tables = 1;				\
-		tlb->cleared_pmds = 1;				\
 		__pte_free_tlb(tlb, ptep, address);		\
 	} while (0)
 #endif
@@ -585,26 +628,21 @@
 #ifndef pmd_free_tlb
 #define pmd_free_tlb(tlb, pmdp, address)			\
 	do {							\
-		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
+		tlb_flush_pud_range(tlb, address, PAGE_SIZE);	\
 		tlb->freed_tables = 1;				\
-		tlb->cleared_puds = 1;				\
 		__pmd_free_tlb(tlb, pmdp, address);		\
 	} while (0)
 #endif
 
-#ifndef __ARCH_HAS_4LEVEL_HACK
 #ifndef pud_free_tlb
 #define pud_free_tlb(tlb, pudp, address)			\
 	do {							\
-		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
+		tlb_flush_p4d_range(tlb, address, PAGE_SIZE);	\
 		tlb->freed_tables = 1;				\
-		tlb->cleared_p4ds = 1;				\
 		__pud_free_tlb(tlb, pudp, address);		\
 	} while (0)
 #endif
-#endif
 
-#ifndef __ARCH_HAS_5LEVEL_HACK
 #ifndef p4d_free_tlb
 #define p4d_free_tlb(tlb, pudp, address)			\
 	do {							\
@@ -613,7 +651,6 @@
 		__p4d_free_tlb(tlb, pudp, address);		\
 	} while (0)
 #endif
-#endif
 
 #endif /* CONFIG_MMU */
 
diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h
index e935318..4973328 100644
--- a/include/asm-generic/uaccess.h
+++ b/include/asm-generic/uaccess.h
@@ -10,28 +10,78 @@
 #include <linux/string.h>
 
 #ifdef CONFIG_UACCESS_MEMCPY
+#include <asm/unaligned.h>
+
+static __always_inline int
+__get_user_fn(size_t size, const void __user *from, void *to)
+{
+	BUILD_BUG_ON(!__builtin_constant_p(size));
+
+	switch (size) {
+	case 1:
+		*(u8 *)to = get_unaligned((u8 __force *)from);
+		return 0;
+	case 2:
+		*(u16 *)to = get_unaligned((u16 __force *)from);
+		return 0;
+	case 4:
+		*(u32 *)to = get_unaligned((u32 __force *)from);
+		return 0;
+	case 8:
+		*(u64 *)to = get_unaligned((u64 __force *)from);
+		return 0;
+	default:
+		BUILD_BUG();
+		return 0;
+	}
+
+}
+#define __get_user_fn(sz, u, k)	__get_user_fn(sz, u, k)
+
+static __always_inline int
+__put_user_fn(size_t size, void __user *to, void *from)
+{
+	BUILD_BUG_ON(!__builtin_constant_p(size));
+
+	switch (size) {
+	case 1:
+		put_unaligned(*(u8 *)from, (u8 __force *)to);
+		return 0;
+	case 2:
+		put_unaligned(*(u16 *)from, (u16 __force *)to);
+		return 0;
+	case 4:
+		put_unaligned(*(u32 *)from, (u32 __force *)to);
+		return 0;
+	case 8:
+		put_unaligned(*(u64 *)from, (u64 __force *)to);
+		return 0;
+	default:
+		BUILD_BUG();
+		return 0;
+	}
+}
+#define __put_user_fn(sz, u, k)	__put_user_fn(sz, u, k)
+
+#define __get_kernel_nofault(dst, src, type, err_label)			\
+do {									\
+	*((type *)dst) = get_unaligned((type *)(src));			\
+	if (0) /* make sure the label looks used to the compiler */	\
+		goto err_label;						\
+} while (0)
+
+#define __put_kernel_nofault(dst, src, type, err_label)			\
+do {									\
+	put_unaligned(*((type *)src), (type *)(dst));			\
+	if (0) /* make sure the label looks used to the compiler */	\
+		goto err_label;						\
+} while (0)
+
+#define HAVE_GET_KERNEL_NOFAULT 1
+
 static inline __must_check unsigned long
 raw_copy_from_user(void *to, const void __user * from, unsigned long n)
 {
-	if (__builtin_constant_p(n)) {
-		switch(n) {
-		case 1:
-			*(u8 *)to = *(u8 __force *)from;
-			return 0;
-		case 2:
-			*(u16 *)to = *(u16 __force *)from;
-			return 0;
-		case 4:
-			*(u32 *)to = *(u32 __force *)from;
-			return 0;
-#ifdef CONFIG_64BIT
-		case 8:
-			*(u64 *)to = *(u64 __force *)from;
-			return 0;
-#endif
-		}
-	}
-
 	memcpy(to, (const void __force *)from, n);
 	return 0;
 }
@@ -39,27 +89,6 @@
 static inline __must_check unsigned long
 raw_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-	if (__builtin_constant_p(n)) {
-		switch(n) {
-		case 1:
-			*(u8 __force *)to = *(u8 *)from;
-			return 0;
-		case 2:
-			*(u16 __force *)to = *(u16 *)from;
-			return 0;
-		case 4:
-			*(u32 __force *)to = *(u32 *)from;
-			return 0;
-#ifdef CONFIG_64BIT
-		case 8:
-			*(u64 __force *)to = *(u64 *)from;
-			return 0;
-#endif
-		default:
-			break;
-		}
-	}
-
 	memcpy((void __force *)to, from, n);
 	return 0;
 }
@@ -67,6 +96,7 @@
 #define INLINE_COPY_TO_USER
 #endif /* CONFIG_UACCESS_MEMCPY */
 
+#ifdef CONFIG_SET_FS
 #define MAKE_MM_SEG(s)	((mm_segment_t) { (s) })
 
 #ifndef KERNEL_DS
@@ -86,9 +116,10 @@
 }
 #endif
 
-#ifndef segment_eq
-#define segment_eq(a, b) ((a).seg == (b).seg)
+#ifndef uaccess_kernel
+#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg)
 #endif
+#endif /* CONFIG_SET_FS */
 
 #define access_ok(addr, size) __access_ok((unsigned long)(addr),(size))
 
diff --git a/include/asm-generic/vdso/vsyscall.h b/include/asm-generic/vdso/vsyscall.h
index cec543d..c835607 100644
--- a/include/asm-generic/vdso/vsyscall.h
+++ b/include/asm-generic/vdso/vsyscall.h
@@ -11,20 +11,6 @@
 }
 #endif /* __arch_get_k_vdso_data */
 
-#ifndef __arch_update_vdso_data
-static __always_inline bool __arch_update_vdso_data(void)
-{
-	return true;
-}
-#endif /* __arch_update_vdso_data */
-
-#ifndef __arch_get_clock_mode
-static __always_inline int __arch_get_clock_mode(struct timekeeper *tk)
-{
-	return 0;
-}
-#endif /* __arch_get_clock_mode */
-
 #ifndef __arch_update_vsyscall
 static __always_inline void __arch_update_vsyscall(struct vdso_data *vdata,
 						   struct timekeeper *tk)
diff --git a/include/asm-generic/vermagic.h b/include/asm-generic/vermagic.h
new file mode 100644
index 0000000..084274a
--- /dev/null
+++ b/include/asm-generic/vermagic.h
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _ASM_GENERIC_VERMAGIC_H
+#define _ASM_GENERIC_VERMAGIC_H
+
+#define MODULE_ARCH_VERMAGIC ""
+
+#endif /* _ASM_GENERIC_VERMAGIC_H */
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 8a5ced9..a774361 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -23,18 +23,18 @@
  *	_etext = .;
  *
  *      _sdata = .;
- *	RO_DATA_SECTION(PAGE_SIZE)
- *	RW_DATA_SECTION(...)
+ *	RO_DATA(PAGE_SIZE)
+ *	RW_DATA(...)
  *	_edata = .;
  *
  *	EXCEPTION_TABLE(...)
- *	NOTES
  *
  *	BSS_SECTION(0, 0, 0)
  *	_end = .;
  *
  *	STABS_DEBUG
  *	DWARF_DEBUG
+ *	ELF_DETAILS
  *
  *	DISCARDS		// must be the last
  * }
@@ -54,6 +54,33 @@
 #define LOAD_OFFSET 0
 #endif
 
+/*
+ * Only some architectures want to have the .notes segment visible in
+ * a separate PT_NOTE ELF Program Header. When this happens, it needs
+ * to be visible in both the kernel text's PT_LOAD and the PT_NOTE
+ * Program Headers. In this case, though, the PT_LOAD needs to be made
+ * the default again so that all the following sections don't also end
+ * up in the PT_NOTE Program Header.
+ */
+#ifdef EMITS_PT_NOTE
+#define NOTES_HEADERS		:text :note
+#define NOTES_HEADERS_RESTORE	__restore_ph : { *(.__restore_ph) } :text
+#else
+#define NOTES_HEADERS
+#define NOTES_HEADERS_RESTORE
+#endif
+
+/*
+ * Some architectures have non-executable read-only exception tables.
+ * They can be added to the RO_DATA segment by specifying their desired
+ * alignment.
+ */
+#ifdef RO_EXCEPTION_TABLE_ALIGN
+#define RO_EXCEPTION_TABLE	EXCEPTION_TABLE(RO_EXCEPTION_TABLE_ALIGN)
+#else
+#define RO_EXCEPTION_TABLE
+#endif
+
 /* Align . to a 8 byte boundary equals to maximum function alignment. */
 #define ALIGN_FUNCTION()  . = ALIGN(8)
 
@@ -83,12 +110,31 @@
 #endif
 
 /*
- * Align to a 32 byte boundary equal to the
- * alignment gcc 4.5 uses for a struct
+ * GCC 4.5 and later have a 32 bytes section alignment for structures.
+ * Except GCC 4.9, that feels the need to align on 64 bytes.
  */
+#if __GNUC__ == 4 && __GNUC_MINOR__ == 9
+#define STRUCT_ALIGNMENT 64
+#else
 #define STRUCT_ALIGNMENT 32
+#endif
 #define STRUCT_ALIGN() . = ALIGN(STRUCT_ALIGNMENT)
 
+/*
+ * The order of the sched class addresses are important, as they are
+ * used to determine the order of the priority of each sched class in
+ * relation to each other.
+ */
+#define SCHED_DATA				\
+	STRUCT_ALIGN();				\
+	__begin_sched_classes = .;		\
+	*(__idle_sched_class)			\
+	*(__fair_sched_class)			\
+	*(__rt_sched_class)			\
+	*(__dl_sched_class)			\
+	*(__stop_sched_class)			\
+	__end_sched_classes = .;
+
 /* The actual configuration determine if the init/exit sections
  * are handled as text/data or they can be discarded (which
  * often happens at runtime)
@@ -110,19 +156,28 @@
 #endif
 
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
-#ifdef CC_USING_PATCHABLE_FUNCTION_ENTRY
-#define MCOUNT_REC()	. = ALIGN(8);				\
-			__start_mcount_loc = .;			\
-			KEEP(*(__patchable_function_entries))	\
-			__stop_mcount_loc = .;
-#else
+/*
+ * The ftrace call sites are logged to a section whose name depends on the
+ * compiler option used. A given kernel image will only use one, AKA
+ * FTRACE_CALLSITE_SECTION. We capture all of them here to avoid header
+ * dependencies for FTRACE_CALLSITE_SECTION's definition.
+ *
+ * Need to also make ftrace_stub_graph point to ftrace_stub
+ * so that the same stub location may have different protocols
+ * and not mess up with C verifiers.
+ */
 #define MCOUNT_REC()	. = ALIGN(8);				\
 			__start_mcount_loc = .;			\
 			KEEP(*(__mcount_loc))			\
-			__stop_mcount_loc = .;
-#endif
+			KEEP(*(__patchable_function_entries))	\
+			__stop_mcount_loc = .;			\
+			ftrace_stub_graph = ftrace_stub;
 #else
-#define MCOUNT_REC()
+# ifdef CONFIG_FUNCTION_TRACER
+#  define MCOUNT_REC()	ftrace_stub_graph = ftrace_stub;
+# else
+#  define MCOUNT_REC()
+# endif
 #endif
 
 #ifdef CONFIG_TRACE_BRANCH_PROFILING
@@ -285,9 +340,9 @@
 	*(__tracepoints)						\
 	/* implement dynamic printk debug */				\
 	. = ALIGN(8);							\
-	__start___verbose = .;						\
-	KEEP(*(__verbose))                                              \
-	__stop___verbose = .;						\
+	__start___dyndbg = .;						\
+	KEEP(*(__dyndbg))						\
+	__stop___dyndbg = .;						\
 	LIKELY_PROFILE()		       				\
 	BRANCH_PROFILE()						\
 	TRACE_PRINTKS()							\
@@ -334,6 +389,15 @@
 	KEEP(*(__jump_table))						\
 	__stop___jump_table = .;
 
+#define STATIC_CALL_DATA						\
+	. = ALIGN(8);							\
+	__start_static_call_sites = .;					\
+	KEEP(*(.static_call_sites))					\
+	__stop_static_call_sites = .;					\
+	__start_static_call_tramp_key = .;				\
+	KEEP(*(.static_call_tramp_key))					\
+	__stop_static_call_tramp_key = .;
+
 /*
  * Allow architectures to handle ro_after_init data on their
  * own by defining an empty RO_AFTER_INIT_DATA.
@@ -344,17 +408,19 @@
 	__start_ro_after_init = .;					\
 	*(.data..ro_after_init)						\
 	JUMP_TABLE_DATA							\
+	STATIC_CALL_DATA						\
 	__end_ro_after_init = .;
 #endif
 
 /*
  * Read only Data
  */
-#define RO_DATA_SECTION(align)						\
+#define RO_DATA(align)							\
 	. = ALIGN((align));						\
 	.rodata           : AT(ADDR(.rodata) - LOAD_OFFSET) {		\
 		__start_rodata = .;					\
 		*(.rodata) *(.rodata.*)					\
+		SCHED_DATA						\
 		RO_AFTER_INIT_DATA	/* Read only after init */	\
 		. = ALIGN(8);						\
 		__start___tracepoints_ptrs = .;				\
@@ -500,16 +566,13 @@
 		__stop___modver = .;					\
 	}								\
 									\
+	RO_EXCEPTION_TABLE						\
+	NOTES								\
 	BTF								\
 									\
 	. = ALIGN((align));						\
 	__end_rodata = .;
 
-/* RODATA & RO_DATA provided for backward compatibility.
- * All archs are supposed to use RO_DATA() */
-#define RODATA          RO_DATA_SECTION(4096)
-#define RO_DATA(align)  RO_DATA_SECTION(align)
-
 /*
  * Non-instrumentable text section
  */
@@ -587,6 +650,12 @@
 		*(.softirqentry.text)					\
 		__softirqentry_text_end = .;
 
+#define STATIC_CALL_TEXT						\
+		ALIGN_FUNCTION();					\
+		__static_call_text_start = .;				\
+		*(.static_call.text)					\
+		__static_call_text_end = .;
+
 /* Section used for early init (in .S files) */
 #define HEAD_TEXT  KEEP(*(.head.text))
 
@@ -615,6 +684,10 @@
 		__start_BTF = .;					\
 		KEEP(*(.BTF))						\
 		__stop_BTF = .;						\
+	}								\
+	. = ALIGN(4);							\
+	.BTF_ids : AT(ADDR(.BTF_ids) - LOAD_OFFSET) {			\
+		*(.BTF_ids)						\
 	}
 #else
 #define BTF
@@ -632,6 +705,7 @@
 #ifdef CONFIG_CONSTRUCTORS
 #define KERNEL_CTORS()	. = ALIGN(8);			   \
 			__ctors_start = .;		   \
+			KEEP(*(SORT(.ctors.*)))		   \
 			KEEP(*(.ctors))			   \
 			KEEP(*(SORT(.init_array.*)))	   \
 			KEEP(*(.init_array))		   \
@@ -665,7 +739,8 @@
 	THERMAL_TABLE(governor)						\
 	EARLYCON_TABLE()						\
 	LSM_TABLE()							\
-	EARLY_LSM_TABLE()
+	EARLY_LSM_TABLE()						\
+	KUNIT_TABLE()
 
 #define INIT_TEXT							\
 	*(.init.text .init.text.*)					\
@@ -765,15 +840,21 @@
 		.debug_rnglists	0 : { *(.debug_rnglists) }		\
 		.debug_str_offsets	0 : { *(.debug_str_offsets) }
 
-		/* Stabs debugging sections.  */
+/* Stabs debugging sections. */
 #define STABS_DEBUG							\
 		.stab 0 : { *(.stab) }					\
 		.stabstr 0 : { *(.stabstr) }				\
 		.stab.excl 0 : { *(.stab.excl) }			\
 		.stab.exclstr 0 : { *(.stab.exclstr) }			\
 		.stab.index 0 : { *(.stab.index) }			\
-		.stab.indexstr 0 : { *(.stab.indexstr) }		\
-		.comment 0 : { *(.comment) }
+		.stab.indexstr 0 : { *(.stab.indexstr) }
+
+/* Required sections not related to debugging. */
+#define ELF_DETAILS							\
+		.comment 0 : { *(.comment) }				\
+		.symtab 0 : { *(.symtab) }				\
+		.strtab 0 : { *(.strtab) }				\
+		.shstrtab 0 : { *(.shstrtab) }
 
 #ifdef CONFIG_GENERIC_BUG
 #define BUG_TABLE							\
@@ -829,7 +910,8 @@
 		__start_notes = .;					\
 		KEEP(*(.note.*))					\
 		__stop_notes = .;					\
-	}
+	} NOTES_HEADERS							\
+	NOTES_HEADERS_RESTORE
 
 #define INIT_SETUP(initsetup_align)					\
 		. = ALIGN(initsetup_align);				\
@@ -861,6 +943,13 @@
 		KEEP(*(.con_initcall.init))				\
 		__con_initcall_end = .;
 
+/* Alignment must be consistent with (kunit_suite *) in include/kunit/test.h */
+#define KUNIT_TABLE()							\
+		. = ALIGN(8);						\
+		__kunit_suites_start = .;				\
+		KEEP(*(.kunit_test_suites))				\
+		__kunit_suites_end = .;
+
 #ifdef CONFIG_BLK_DEV_INITRD
 #define INIT_RAM_FS							\
 	. = ALIGN(4);							\
@@ -900,14 +989,47 @@
  * section definitions so that such archs put those in earlier section
  * definitions.
  */
-#define DISCARDS							\
-	/DISCARD/ : {							\
+#ifdef RUNTIME_DISCARD_EXIT
+#define EXIT_DISCARDS
+#else
+#define EXIT_DISCARDS							\
 	EXIT_TEXT							\
-	EXIT_DATA							\
-	EXIT_CALL							\
+	EXIT_DATA
+#endif
+
+/*
+ * Clang's -fprofile-arcs, -fsanitize=kernel-address, and
+ * -fsanitize=thread produce unwanted sections (.eh_frame
+ * and .init_array.*), but CONFIG_CONSTRUCTORS wants to
+ * keep any .init_array.* sections.
+ * https://bugs.llvm.org/show_bug.cgi?id=46478
+ */
+#if defined(CONFIG_GCOV_KERNEL) || defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KCSAN)
+# ifdef CONFIG_CONSTRUCTORS
+#  define SANITIZER_DISCARDS						\
+	*(.eh_frame)
+# else
+#  define SANITIZER_DISCARDS						\
+	*(.init_array) *(.init_array.*)					\
+	*(.eh_frame)
+# endif
+#else
+# define SANITIZER_DISCARDS
+#endif
+
+#define COMMON_DISCARDS							\
+	SANITIZER_DISCARDS						\
 	*(.discard)							\
 	*(.discard.*)							\
 	*(.modinfo)							\
+	/* ld.bfd warns about .gnu.version* even when not emitted */	\
+	*(.gnu.version*)						\
+
+#define DISCARDS							\
+	/DISCARD/ : {							\
+	EXIT_DISCARDS							\
+	EXIT_CALL							\
+	COMMON_DISCARDS							\
 	}
 
 /**
@@ -1002,7 +1124,7 @@
  * matches the requirement of PAGE_ALIGNED_DATA.
  *
  * use 0 as page_align if page_aligned data is not used */
-#define RW_DATA_SECTION(cacheline, pagealigned, inittask)		\
+#define RW_DATA(cacheline, pagealigned, inittask)			\
 	. = ALIGN(PAGE_SIZE);						\
 	.data : AT(ADDR(.data) - LOAD_OFFSET) {				\
 		INIT_TASK_DATA(inittask)				\