diff --git a/arch/alpha/include/asm/bitops.h b/arch/alpha/include/asm/bitops.h
index bafb1c1f0fdc1..3e33621922c31 100644
--- a/arch/alpha/include/asm/bitops.h
+++ b/arch/alpha/include/asm/bitops.h
@@ -286,6 +286,26 @@ arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
 #define arch_test_bit generic_test_bit
 #define arch_test_bit_acquire generic_test_bit_acquire
 
+static inline bool xor_unlock_is_negative_byte(unsigned long mask,
+		volatile unsigned long *p)
+{
+	unsigned long temp, old;
+
+	__asm__ __volatile__(
+	"1:	ldl_l %0,%4\n"
+	"	mov %0,%2\n"
+	"	xor %0,%3,%0\n"
+	"	stl_c %0,%1\n"
+	"	beq %0,2f\n"
+	".subsection 2\n"
+	"2:	br 1b\n"
+	".previous"
+	:"=&r" (temp), "=m" (*p), "=&r" (old)
+	:"Ir" (mask), "m" (*p));
+
+	return (old & BIT(7)) != 0;
+}
+
 /*
  * ffz = Find First Zero in word. Undefined if no zero exists,
  * so code should check against ~0UL first..
diff --git a/arch/m68k/include/asm/bitops.h b/arch/m68k/include/asm/bitops.h
index e984af71df6be..14c64a6f12176 100644
--- a/arch/m68k/include/asm/bitops.h
+++ b/arch/m68k/include/asm/bitops.h
@@ -319,6 +319,27 @@ arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
 	return test_and_change_bit(nr, addr);
 }
 
+static inline bool xor_unlock_is_negative_byte(unsigned long mask,
+		volatile unsigned long *p)
+{
+#ifdef CONFIG_COLDFIRE
+	__asm__ __volatile__ ("eorl %1, %0"
+		: "+m" (*p)
+		: "d" (mask)
+		: "memory");
+	return *p & (1 << 7);
+#else
+	char result;
+	char *cp = (char *)p + 3;	/* m68k is big-endian */
+
+	__asm__ __volatile__ ("eor.b %1, %2; smi %0"
+		: "=d" (result)
+		: "di" (mask), "o" (*cp)
+		: "memory");
+	return result;
+#endif
+}
+
 /*
  *	The true 68020 and more advanced processors support the "bfffo"
  *	instruction for finding bits. ColdFire and simple 68000 parts
diff --git a/arch/mips/include/asm/bitops.h b/arch/mips/include/asm/bitops.h
index b4bf754f7db3f..89f73d1a4ea4e 100644
--- a/arch/mips/include/asm/bitops.h
+++ b/arch/mips/include/asm/bitops.h
@@ -73,7 +73,8 @@ int __mips_test_and_clear_bit(unsigned long nr,
 			      volatile unsigned long *addr);
 int __mips_test_and_change_bit(unsigned long nr,
 			       volatile unsigned long *addr);
-
+bool __mips_xor_is_negative_byte(unsigned long mask,
+		volatile unsigned long *addr);
 
 /*
  * set_bit - Atomically set a bit in memory
@@ -279,6 +280,28 @@ static inline int test_and_change_bit(unsigned long nr,
 	return res;
 }
 
+static inline bool xor_unlock_is_negative_byte(unsigned long mask,
+		volatile unsigned long *p)
+{
+	unsigned long orig;
+	bool res;
+
+	smp_mb__before_atomic();
+
+	if (!kernel_uses_llsc) {
+		res = __mips_xor_is_negative_byte(mask, p);
+	} else {
+		orig = __test_bit_op(*p, "%0",
+				     "xor\t%1, %0, %3",
+				     "ir"(mask));
+		res = (orig & BIT(7)) != 0;
+	}
+
+	smp_llsc_mb();
+
+	return res;
+}
+
 #undef __bit_op
 #undef __test_bit_op
 
diff --git a/arch/mips/lib/bitops.c b/arch/mips/lib/bitops.c
index 116d0bd8b2ae9..00aee98e9d545 100644
--- a/arch/mips/lib/bitops.c
+++ b/arch/mips/lib/bitops.c
@@ -146,3 +146,17 @@ int __mips_test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
 	return res;
 }
 EXPORT_SYMBOL(__mips_test_and_change_bit);
+
+bool __mips_xor_is_negative_byte(unsigned long mask,
+		volatile unsigned long *addr)
+{
+	unsigned long flags;
+	unsigned long data;
+
+	raw_local_irq_save(flags);
+	data = *addr;
+	*addr = data ^ mask;
+	raw_local_irq_restore(flags);
+
+	return (data & BIT(7)) != 0;
+}
diff --git a/arch/powerpc/include/asm/bitops.h b/arch/powerpc/include/asm/bitops.h
index 7e0f0322912b6..671ecc6711e36 100644
--- a/arch/powerpc/include/asm/bitops.h
+++ b/arch/powerpc/include/asm/bitops.h
@@ -233,35 +233,24 @@ static inline int arch_test_and_change_bit(unsigned long nr,
 	return test_and_change_bits(BIT_MASK(nr), addr + BIT_WORD(nr)) != 0;
 }
 
-#ifdef CONFIG_PPC64
-static inline unsigned long
-clear_bit_unlock_return_word(int nr, volatile unsigned long *addr)
+static inline bool arch_xor_unlock_is_negative_byte(unsigned long mask,
+		volatile unsigned long *p)
 {
 	unsigned long old, t;
-	unsigned long *p = (unsigned long *)addr + BIT_WORD(nr);
-	unsigned long mask = BIT_MASK(nr);
 
 	__asm__ __volatile__ (
 	PPC_RELEASE_BARRIER
 "1:"	PPC_LLARX "%0,0,%3,0\n"
-	"andc %1,%0,%2\n"
+	"xor %1,%0,%2\n"
 	PPC_STLCX "%1,0,%3\n"
 	"bne- 1b\n"
 	: "=&r" (old), "=&r" (t)
 	: "r" (mask), "r" (p)
 	: "cc", "memory");
 
-	return old;
+	return (old & BIT_MASK(7)) != 0;
 }
-
-/*
- * This is a special function for mm/filemap.c
- * Bit 7 corresponds to PG_waiters.
- */
-#define arch_clear_bit_unlock_is_negative_byte(nr, addr)		\
-	(clear_bit_unlock_return_word(nr, addr) & BIT_MASK(7))
-
-#endif /* CONFIG_PPC64 */
+#define arch_xor_unlock_is_negative_byte arch_xor_unlock_is_negative_byte
 
 #include <asm-generic/bitops/non-atomic.h>
 
diff --git a/arch/riscv/include/asm/bitops.h b/arch/riscv/include/asm/bitops.h
index 3540b690944be..65f6eee4ab8d7 100644
--- a/arch/riscv/include/asm/bitops.h
+++ b/arch/riscv/include/asm/bitops.h
@@ -191,6 +191,18 @@ static inline void __clear_bit_unlock(
 	clear_bit_unlock(nr, addr);
 }
 
+static inline bool xor_unlock_is_negative_byte(unsigned long mask,
+		volatile unsigned long *addr)
+{
+	unsigned long res;
+	__asm__ __volatile__ (
+		__AMO(xor) ".rl %0, %2, %1"
+		: "=r" (res), "+A" (*addr)
+		: "r" (__NOP(mask))
+		: "memory");
+	return (res & BIT(7)) != 0;
+}
+
 #undef __test_and_op_bit
 #undef __op_bit
 #undef __NOP
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index 2de74fcd0578f..c467dffa8c12a 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -201,6 +201,16 @@ static inline void arch___clear_bit_unlock(unsigned long nr,
 	arch___clear_bit(nr, ptr);
 }
 
+static inline bool arch_xor_unlock_is_negative_byte(unsigned long mask,
+		volatile unsigned long *ptr)
+{
+	unsigned long old;
+
+	old = __atomic64_xor_barrier(mask, (long *)ptr);
+	return old & BIT(7);
+}
+#define arch_xor_unlock_is_negative_byte arch_xor_unlock_is_negative_byte
+
 #include <asm-generic/bitops/instrumented-atomic.h>
 #include <asm-generic/bitops/instrumented-non-atomic.h>
 #include <asm-generic/bitops/instrumented-lock.h>
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 2edf68475fec4..f03c0a50ec3a2 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -94,18 +94,17 @@ arch___clear_bit(unsigned long nr, volatile unsigned long *addr)
 	asm volatile(__ASM_SIZE(btr) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
 }
 
-static __always_inline bool
-arch_clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr)
+static __always_inline bool arch_xor_unlock_is_negative_byte(unsigned long mask,
+		volatile unsigned long *addr)
 {
 	bool negative;
-	asm volatile(LOCK_PREFIX "andb %2,%1"
+	asm volatile(LOCK_PREFIX "xorb %2,%1"
 		CC_SET(s)
 		: CC_OUT(s) (negative), WBYTE_ADDR(addr)
-		: "ir" ((char) ~(1 << nr)) : "memory");
+		: "iq" ((char)mask) : "memory");
 	return negative;
 }
-#define arch_clear_bit_unlock_is_negative_byte                                 \
-	arch_clear_bit_unlock_is_negative_byte
+#define arch_xor_unlock_is_negative_byte arch_xor_unlock_is_negative_byte
 
 static __always_inline void
 arch___clear_bit_unlock(long nr, volatile unsigned long *addr)
diff --git a/fs/buffer.c b/fs/buffer.c
index 99b8a831c1abc..11da16b6da1bb 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -282,13 +282,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
 	} while (tmp != bh);
 	spin_unlock_irqrestore(&first->b_uptodate_lock, flags);
 
-	/*
-	 * If all of the buffers are uptodate then we can set the page
-	 * uptodate.
-	 */
-	if (folio_uptodate)
-		folio_mark_uptodate(folio);
-	folio_unlock(folio);
+	folio_end_read(folio, folio_uptodate);
 	return;
 
 still_busy:
@@ -2439,12 +2433,10 @@ int block_read_full_folio(struct folio *folio, get_block_t *get_block)
 
 	if (!nr) {
 		/*
-		 * All buffers are uptodate - we can set the folio uptodate
-		 * as well. But not if get_block() returned an error.
+		 * All buffers are uptodate or get_block() returned an
+		 * error when trying to map them - we can finish the read.
 		 */
-		if (!page_error)
-			folio_mark_uptodate(folio);
-		folio_unlock(folio);
+		folio_end_read(folio, !page_error);
 		return 0;
 	}
 
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
index 8cb83e7b699bd..8494492582abe 100644
--- a/fs/ext4/readpage.c
+++ b/fs/ext4/readpage.c
@@ -70,15 +70,8 @@ static void __read_end_io(struct bio *bio)
 {
 	struct folio_iter fi;
 
-	bio_for_each_folio_all(fi, bio) {
-		struct folio *folio = fi.folio;
-
-		if (bio->bi_status)
-			folio_clear_uptodate(folio);
-		else
-			folio_mark_uptodate(folio);
-		folio_unlock(folio);
-	}
+	bio_for_each_folio_all(fi, bio)
+		folio_end_read(fi.folio, bio->bi_status == 0);
 	if (bio->bi_private)
 		mempool_free(bio->bi_private, bio_post_read_ctx_pool);
 	bio_put(bio);
@@ -335,8 +328,7 @@ int ext4_mpage_readpages(struct inode *inode,
 				if (ext4_need_verity(inode, folio->index) &&
 				    !fsverity_verify_folio(folio))
 					goto set_error_page;
-				folio_mark_uptodate(folio);
-				folio_unlock(folio);
+				folio_end_read(folio, true);
 				continue;
 			}
 		} else if (fully_mapped) {
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 7ffdf0d037fae..a010a41c49402 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -29,9 +29,9 @@ typedef int (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length);
  * and I/O completions.
  */
 struct iomap_folio_state {
-	atomic_t		read_bytes_pending;
-	atomic_t		write_bytes_pending;
 	spinlock_t		state_lock;
+	unsigned int		read_bytes_pending;
+	atomic_t		write_bytes_pending;
 
 	/*
 	 * Each block has two bits in this bitmap:
@@ -57,30 +57,32 @@ static inline bool ifs_block_is_uptodate(struct iomap_folio_state *ifs,
 	return test_bit(block, ifs->state);
 }
 
-static void ifs_set_range_uptodate(struct folio *folio,
+static bool ifs_set_range_uptodate(struct folio *folio,
 		struct iomap_folio_state *ifs, size_t off, size_t len)
 {
 	struct inode *inode = folio->mapping->host;
 	unsigned int first_blk = off >> inode->i_blkbits;
 	unsigned int last_blk = (off + len - 1) >> inode->i_blkbits;
 	unsigned int nr_blks = last_blk - first_blk + 1;
-	unsigned long flags;
 
-	spin_lock_irqsave(&ifs->state_lock, flags);
 	bitmap_set(ifs->state, first_blk, nr_blks);
-	if (ifs_is_fully_uptodate(folio, ifs))
-		folio_mark_uptodate(folio);
-	spin_unlock_irqrestore(&ifs->state_lock, flags);
+	return ifs_is_fully_uptodate(folio, ifs);
 }
 
 static void iomap_set_range_uptodate(struct folio *folio, size_t off,
 		size_t len)
 {
 	struct iomap_folio_state *ifs = folio->private;
+	unsigned long flags;
+	bool uptodate = true;
 
-	if (ifs)
-		ifs_set_range_uptodate(folio, ifs, off, len);
-	else
+	if (ifs) {
+		spin_lock_irqsave(&ifs->state_lock, flags);
+		uptodate = ifs_set_range_uptodate(folio, ifs, off, len);
+		spin_unlock_irqrestore(&ifs->state_lock, flags);
+	}
+
+	if (uptodate)
 		folio_mark_uptodate(folio);
 }
 
@@ -181,7 +183,7 @@ static void ifs_free(struct folio *folio)
 
 	if (!ifs)
 		return;
-	WARN_ON_ONCE(atomic_read(&ifs->read_bytes_pending));
+	WARN_ON_ONCE(ifs->read_bytes_pending != 0);
 	WARN_ON_ONCE(atomic_read(&ifs->write_bytes_pending));
 	WARN_ON_ONCE(ifs_is_fully_uptodate(folio, ifs) !=
 			folio_test_uptodate(folio));
@@ -249,20 +251,28 @@ static void iomap_adjust_read_range(struct inode *inode, struct folio *folio,
 	*lenp = plen;
 }
 
-static void iomap_finish_folio_read(struct folio *folio, size_t offset,
+static void iomap_finish_folio_read(struct folio *folio, size_t off,
 		size_t len, int error)
 {
 	struct iomap_folio_state *ifs = folio->private;
+	bool uptodate = !error;
+	bool finished = true;
 
-	if (unlikely(error)) {
-		folio_clear_uptodate(folio);
-		folio_set_error(folio);
-	} else {
-		iomap_set_range_uptodate(folio, offset, len);
+	if (ifs) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&ifs->state_lock, flags);
+		if (!error)
+			uptodate = ifs_set_range_uptodate(folio, ifs, off, len);
+		ifs->read_bytes_pending -= len;
+		finished = !ifs->read_bytes_pending;
+		spin_unlock_irqrestore(&ifs->state_lock, flags);
 	}
 
-	if (!ifs || atomic_sub_and_test(len, &ifs->read_bytes_pending))
-		folio_unlock(folio);
+	if (error)
+		folio_set_error(folio);
+	if (finished)
+		folio_end_read(folio, uptodate);
 }
 
 static void iomap_read_end_io(struct bio *bio)
@@ -359,8 +369,11 @@ static loff_t iomap_readpage_iter(const struct iomap_iter *iter,
 	}
 
 	ctx->cur_folio_in_bio = true;
-	if (ifs)
-		atomic_add(plen, &ifs->read_bytes_pending);
+	if (ifs) {
+		spin_lock_irq(&ifs->state_lock);
+		ifs->read_bytes_pending += plen;
+		spin_unlock_irq(&ifs->state_lock);
+	}
 
 	sector = iomap_sector(iomap, pos);
 	if (!ctx->bio ||
diff --git a/include/asm-generic/bitops/instrumented-lock.h b/include/asm-generic/bitops/instrumented-lock.h
index eb64bd4f11f3c..542d3727ee4e3 100644
--- a/include/asm-generic/bitops/instrumented-lock.h
+++ b/include/asm-generic/bitops/instrumented-lock.h
@@ -58,27 +58,25 @@ static inline bool test_and_set_bit_lock(long nr, volatile unsigned long *addr)
 	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
+ * xor_unlock_is_negative_byte - XOR a single byte in memory and test if
+ * it is negative, for unlock.
+ * @mask: Change the bits which are set in this mask.
+ * @addr: The address of the word containing the byte to change.
  *
+ * Changes some of bits 0-6 in the word pointed to by @addr.
  * This operation is atomic and provides release barrier semantics.
+ * Used to optimise some folio operations which are commonly paired
+ * with an unlock or end of writeback.  Bit 7 is used as PG_waiters to
+ * indicate whether anybody is waiting for the unlock.
  *
- * This is a bit of a one-trick-pony for the filemap code, which clears
- * PG_locked and tests PG_waiters,
+ * Return: Whether the top bit of the byte is set.
  */
-static inline bool
-clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr)
+static inline bool xor_unlock_is_negative_byte(unsigned long mask,
+		volatile unsigned long *addr)
 {
 	kcsan_release();
-	instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
-	return arch_clear_bit_unlock_is_negative_byte(nr, addr);
+	instrument_atomic_write(addr, sizeof(long));
+	return arch_xor_unlock_is_negative_byte(mask, 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/lock.h b/include/asm-generic/bitops/lock.h
index 40913516e654c..14d4ec8c5152d 100644
--- a/include/asm-generic/bitops/lock.h
+++ b/include/asm-generic/bitops/lock.h
@@ -66,27 +66,15 @@ arch___clear_bit_unlock(unsigned int nr, volatile unsigned long *p)
 	raw_atomic_long_set_release((atomic_long_t *)p, old);
 }
 
-/**
- * arch_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 is a bit of a one-trick-pony for the filemap code, which clears
- * PG_locked and tests PG_waiters,
- */
-#ifndef arch_clear_bit_unlock_is_negative_byte
-static inline bool arch_clear_bit_unlock_is_negative_byte(unsigned int nr,
-							  volatile unsigned long *p)
+#ifndef arch_xor_unlock_is_negative_byte
+static inline bool arch_xor_unlock_is_negative_byte(unsigned long mask,
+		volatile unsigned long *p)
 {
 	long old;
-	unsigned long mask = BIT_MASK(nr);
 
-	p += BIT_WORD(nr);
-	old = raw_atomic_long_fetch_andnot_release(mask, (atomic_long_t *)p);
+	old = raw_atomic_long_fetch_xor_release(mask, (atomic_long_t *)p);
 	return !!(old & BIT(7));
 }
-#define arch_clear_bit_unlock_is_negative_byte arch_clear_bit_unlock_is_negative_byte
 #endif
 
 #include <asm-generic/bitops/instrumented-lock.h>
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index c8f5438c6fc79..3cbe24d32e35f 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -726,6 +726,25 @@ TESTPAGEFLAG_FALSE(Ksm, ksm)
 
 u64 stable_page_flags(struct page *page);
 
+/**
+ * folio_xor_flags_has_waiters - Change some folio flags.
+ * @folio: The folio.
+ * @mask: Bits set in this word will be changed.
+ *
+ * This must only be used for flags which are changed with the folio
+ * lock held.  For example, it is unsafe to use for PG_dirty as that
+ * can be set without the folio lock held.  It can also only be used
+ * on flags which are in the range 0-6 as some of the implementations
+ * only affect those bits.
+ *
+ * Return: Whether there are tasks waiting on the folio.
+ */
+static inline bool folio_xor_flags_has_waiters(struct folio *folio,
+		unsigned long mask)
+{
+	return xor_unlock_is_negative_byte(mask, folio_flags(folio, 0));
+}
+
 /**
  * folio_test_uptodate - Is this folio up to date?
  * @folio: The folio.
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 8e9547ec2686e..7514246539a21 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -1162,6 +1162,7 @@ static inline void wait_on_page_locked(struct page *page)
 	folio_wait_locked(page_folio(page));
 }
 
+void folio_end_read(struct folio *folio, bool success);
 void wait_on_page_writeback(struct page *page);
 void folio_wait_writeback(struct folio *folio);
 int folio_wait_writeback_killable(struct folio *folio);
diff --git a/kernel/kcsan/kcsan_test.c b/kernel/kcsan/kcsan_test.c
index 9d8c95defdd67..9924eb3f74cf3 100644
--- a/kernel/kcsan/kcsan_test.c
+++ b/kernel/kcsan/kcsan_test.c
@@ -699,12 +699,9 @@ static void test_barrier_nothreads(struct kunit *test)
 	KCSAN_EXPECT_RW_BARRIER(spin_unlock(&test_spinlock), true);
 	KCSAN_EXPECT_RW_BARRIER(mutex_lock(&test_mutex), false);
 	KCSAN_EXPECT_RW_BARRIER(mutex_unlock(&test_mutex), true);
-
-#ifdef clear_bit_unlock_is_negative_byte
-	KCSAN_EXPECT_READ_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var), true);
-	KCSAN_EXPECT_WRITE_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var), true);
-	KCSAN_EXPECT_RW_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var), true);
-#endif
+	KCSAN_EXPECT_READ_BARRIER(xor_unlock_is_negative_byte(1, &test_var), true);
+	KCSAN_EXPECT_WRITE_BARRIER(xor_unlock_is_negative_byte(1, &test_var), true);
+	KCSAN_EXPECT_RW_BARRIER(xor_unlock_is_negative_byte(1, &test_var), true);
 	kcsan_nestable_atomic_end();
 }
 
diff --git a/kernel/kcsan/selftest.c b/kernel/kcsan/selftest.c
index 8679322450f22..84a1200271aff 100644
--- a/kernel/kcsan/selftest.c
+++ b/kernel/kcsan/selftest.c
@@ -227,12 +227,9 @@ static bool __init test_barrier(void)
 	KCSAN_CHECK_RW_BARRIER(arch_spin_unlock(&arch_spinlock));
 	spin_lock(&test_spinlock);
 	KCSAN_CHECK_RW_BARRIER(spin_unlock(&test_spinlock));
-
-#ifdef clear_bit_unlock_is_negative_byte
-	KCSAN_CHECK_RW_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var));
-	KCSAN_CHECK_READ_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var));
-	KCSAN_CHECK_WRITE_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var));
-#endif
+	KCSAN_CHECK_RW_BARRIER(xor_unlock_is_negative_byte(1, &test_var));
+	KCSAN_CHECK_READ_BARRIER(xor_unlock_is_negative_byte(1, &test_var));
+	KCSAN_CHECK_WRITE_BARRIER(xor_unlock_is_negative_byte(1, &test_var));
 	kcsan_nestable_atomic_end();
 
 	return ret;
diff --git a/mm/filemap.c b/mm/filemap.c
index a7c0ad7b058fb..e2bfb8ce9e9ee 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1186,13 +1186,6 @@ static void folio_wake_bit(struct folio *folio, int bit_nr)
 	spin_unlock_irqrestore(&q->lock, flags);
 }
 
-static void folio_wake(struct folio *folio, int bit)
-{
-	if (!folio_test_waiters(folio))
-		return;
-	folio_wake_bit(folio, bit);
-}
-
 /*
  * A choice of three behaviors for folio_wait_bit_common():
  */
@@ -1493,29 +1486,6 @@ void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter)
 }
 EXPORT_SYMBOL_GPL(folio_add_wait_queue);
 
-#ifndef clear_bit_unlock_is_negative_byte
-
-/*
- * PG_waiters is the high bit in the same byte as PG_lock.
- *
- * On x86 (and on many other architectures), we can clear PG_lock and
- * test the sign bit at the same time. But if the architecture does
- * not support that special operation, we just do this all by hand
- * instead.
- *
- * The read of PG_waiters has to be after (or concurrently with) PG_locked
- * being cleared, but a memory barrier should be unnecessary since it is
- * in the same byte as PG_locked.
- */
-static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem)
-{
-	clear_bit_unlock(nr, mem);
-	/* smp_mb__after_atomic(); */
-	return test_bit(PG_waiters, mem);
-}
-
-#endif
-
 /**
  * folio_unlock - Unlock a locked folio.
  * @folio: The folio.
@@ -1531,11 +1501,41 @@ void folio_unlock(struct folio *folio)
 	BUILD_BUG_ON(PG_waiters != 7);
 	BUILD_BUG_ON(PG_locked > 7);
 	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
-	if (clear_bit_unlock_is_negative_byte(PG_locked, folio_flags(folio, 0)))
+	if (folio_xor_flags_has_waiters(folio, 1 << PG_locked))
 		folio_wake_bit(folio, PG_locked);
 }
 EXPORT_SYMBOL(folio_unlock);
 
+/**
+ * folio_end_read - End read on a folio.
+ * @folio: The folio.
+ * @success: True if all reads completed successfully.
+ *
+ * When all reads against a folio have completed, filesystems should
+ * call this function to let the pagecache know that no more reads
+ * are outstanding.  This will unlock the folio and wake up any thread
+ * sleeping on the lock.  The folio will also be marked uptodate if all
+ * reads succeeded.
+ *
+ * Context: May be called from interrupt or process context.  May not be
+ * called from NMI context.
+ */
+void folio_end_read(struct folio *folio, bool success)
+{
+	unsigned long mask = 1 << PG_locked;
+
+	/* Must be in bottom byte for x86 to work */
+	BUILD_BUG_ON(PG_uptodate > 7);
+	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
+	VM_BUG_ON_FOLIO(folio_test_uptodate(folio), folio);
+
+	if (likely(success))
+		mask |= 1 << PG_uptodate;
+	if (folio_xor_flags_has_waiters(folio, mask))
+		folio_wake_bit(folio, PG_locked);
+}
+EXPORT_SYMBOL(folio_end_read);
+
 /**
  * folio_end_private_2 - Clear PG_private_2 and wake any waiters.
  * @folio: The folio.
@@ -1597,9 +1597,15 @@ EXPORT_SYMBOL(folio_wait_private_2_killable);
 /**
  * folio_end_writeback - End writeback against a folio.
  * @folio: The folio.
+ *
+ * The folio must actually be under writeback.
+ *
+ * Context: May be called from process or interrupt context.
  */
 void folio_end_writeback(struct folio *folio)
 {
+	VM_BUG_ON_FOLIO(!folio_test_writeback(folio), folio);
+
 	/*
 	 * folio_test_clear_reclaim() could be used here but it is an
 	 * atomic operation and overkill in this particular case. Failing
@@ -1616,14 +1622,11 @@ void folio_end_writeback(struct folio *folio)
 	 * Writeback does not hold a folio reference of its own, relying
 	 * on truncation to wait for the clearing of PG_writeback.
 	 * But here we must make sure that the folio is not freed and
-	 * reused before the folio_wake().
+	 * reused before the folio_wake_bit().
 	 */
 	folio_get(folio);
-	if (!__folio_end_writeback(folio))
-		BUG();
-
-	smp_mb__after_atomic();
-	folio_wake(folio, PG_writeback);
+	if (__folio_end_writeback(folio))
+		folio_wake_bit(folio, PG_writeback);
 	acct_reclaim_writeback(folio);
 	folio_put(folio);
 }
diff --git a/mm/kasan/kasan_test.c b/mm/kasan/kasan_test.c
index ecf9f5aa35200..c73fc568eec81 100644
--- a/mm/kasan/kasan_test.c
+++ b/mm/kasan/kasan_test.c
@@ -1098,11 +1098,9 @@ static void kasan_bitops_test_and_modify(struct kunit *test, int nr, void *addr)
 	KUNIT_EXPECT_KASAN_FAIL(test, test_and_change_bit(nr, addr));
 	KUNIT_EXPECT_KASAN_FAIL(test, __test_and_change_bit(nr, addr));
 	KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result = test_bit(nr, addr));
-
-#if defined(clear_bit_unlock_is_negative_byte)
-	KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result =
-				clear_bit_unlock_is_negative_byte(nr, addr));
-#endif
+	if (nr < 7)
+		KUNIT_EXPECT_KASAN_FAIL(test, kasan_int_result =
+				xor_unlock_is_negative_byte(1 << nr, addr));
 }
 
 static void kasan_bitops_generic(struct kunit *test)
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 6e3faed567260..21cb71e65f653 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -3008,19 +3008,16 @@ bool __folio_end_writeback(struct folio *folio)
 		unsigned long flags;
 
 		xa_lock_irqsave(&mapping->i_pages, flags);
-		ret = folio_test_clear_writeback(folio);
-		if (ret) {
-			__xa_clear_mark(&mapping->i_pages, folio_index(folio),
-						PAGECACHE_TAG_WRITEBACK);
-			if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) {
-				struct bdi_writeback *wb = inode_to_wb(inode);
-
-				wb_stat_mod(wb, WB_WRITEBACK, -nr);
-				__wb_writeout_add(wb, nr);
-				if (!mapping_tagged(mapping,
-						    PAGECACHE_TAG_WRITEBACK))
-					wb_inode_writeback_end(wb);
-			}
+		ret = folio_xor_flags_has_waiters(folio, 1 << PG_writeback);
+		__xa_clear_mark(&mapping->i_pages, folio_index(folio),
+					PAGECACHE_TAG_WRITEBACK);
+		if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) {
+			struct bdi_writeback *wb = inode_to_wb(inode);
+
+			wb_stat_mod(wb, WB_WRITEBACK, -nr);
+			__wb_writeout_add(wb, nr);
+			if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK))
+				wb_inode_writeback_end(wb);
 		}
 
 		if (mapping->host && !mapping_tagged(mapping,
@@ -3029,14 +3026,14 @@ bool __folio_end_writeback(struct folio *folio)
 
 		xa_unlock_irqrestore(&mapping->i_pages, flags);
 	} else {
-		ret = folio_test_clear_writeback(folio);
-	}
-	if (ret) {
-		lruvec_stat_mod_folio(folio, NR_WRITEBACK, -nr);
-		zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr);
-		node_stat_mod_folio(folio, NR_WRITTEN, nr);
+		ret = folio_xor_flags_has_waiters(folio, 1 << PG_writeback);
 	}
+
+	lruvec_stat_mod_folio(folio, NR_WRITEBACK, -nr);
+	zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr);
+	node_stat_mod_folio(folio, NR_WRITTEN, nr);
 	folio_memcg_unlock(folio);
+
 	return ret;
 }