Introduce the for_each_set_clump8 macro

index 8a1ee10014de..5277e72882ff 100644
@@ -80,4 +80,54 @@ extern unsigned long find_first_zero_bit(const unsigned long *addr,
 
 #endif /* CONFIG_GENERIC_FIND_FIRST_BIT */
 
+/**
+ * bitmap_get_value8 - get an 8-bit value within a memory region
+ * @addr: address to the bitmap memory region
+ * @start: bit offset of the 8-bit value; must be a multiple of 8
+ *
+ * Returns the 8-bit value located at the @start bit offset within the @addr
+ * memory region.
+ */
+static inline unsigned long bitmap_get_value8(const unsigned long *addr,
+					      unsigned long start)
+{
+	const size_t index = BIT_WORD(start);
+	const unsigned long offset = start % BITS_PER_LONG;
+
+	return (addr[index] >> offset) & 0xFF;
+}
+
+/**
+ * bitmap_set_value8 - set an 8-bit value within a memory region
+ * @addr: address to the bitmap memory region
+ * @value: the 8-bit value; values wider than 8 bits may clobber bitmap
+ * @start: bit offset of the 8-bit value; must be a multiple of 8
+ */
+static inline void bitmap_set_value8(unsigned long *addr, unsigned long value,
+				     unsigned long start)
+{
+	const size_t index = BIT_WORD(start);
+	const unsigned long offset = start % BITS_PER_LONG;
+
+	addr[index] &= ~(0xFF << offset);
+	addr[index] |= value << offset;
+}
+
+/**
+ * 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_ */

index cf074bce3eb3..fb94a10f7853 100644
@@ -40,6 +40,11 @@ extern unsigned long __sw_hweight64(__u64 w);
 	     (bit) < (size);					\
 	     (bit) = find_next_zero_bit((addr), (size), (bit) + 1))
 
+#define for_each_set_clump8(start, clump, bits, size) \
+	for ((start) = find_first_clump8(&(clump), (bits), (size)); \
+	     (start) < (size); \
+	     (start) = find_next_clump8(&(clump), (bits), (size), (start) + 8))
+
 static inline int get_bitmask_order(unsigned int count)
 {
 	int order;

index 5c51eb45178a..e35a76b291e6 100644
@@ -214,3 +214,17 @@ EXPORT_SYMBOL(find_next_bit_le);
 #endif
 
 #endif /* __BIG_ENDIAN */
+
+unsigned long find_next_clump8(unsigned long *clump, const unsigned long *addr,
+			       unsigned long size, unsigned long offset)
+{
+	offset = find_next_bit(addr, size, offset);
+	if (offset == size)
+		return size;
+
+	offset = round_down(offset, 8);
+	*clump = bitmap_get_value8(addr, offset);
+
+	return offset;
+}
+EXPORT_SYMBOL(find_next_clump8);

index 51a98f7ee79e..dc167c13eb39 100644
@@ -92,6 +92,36 @@ __check_eq_u32_array(const char *srcfile, unsigned int line,
 	return true;
 }
 
+static bool __init __check_eq_clump8(const char *srcfile, unsigned int line,
+				    const unsigned int offset,
+				    const unsigned int size,
+				    const unsigned char *const clump_exp,
+				    const unsigned long *const clump)
+{
+	unsigned long exp;
+
+	if (offset >= size) {
+		pr_warn("[%s:%u] bit offset for clump out-of-bounds: expected less than %u, got %u\n",
+			srcfile, line, size, offset);
+		return false;
+	}
+
+	exp = clump_exp[offset / 8];
+	if (!exp) {
+		pr_warn("[%s:%u] bit offset for zero clump: expected nonzero clump, got bit offset %u with clump value 0",
+			srcfile, line, offset);
+		return false;
+	}
+
+	if (*clump != exp) {
+		pr_warn("[%s:%u] expected clump value of 0x%lX, got clump value of 0x%lX",
+			srcfile, line, exp, *clump);
+		return false;
+	}
+
+	return true;
+}
+
 #define __expect_eq(suffix, ...)					\
 	({								\
 		int result = 0;						\

@@ -108,6 +138,7 @@ __check_eq_u32_array(const char *srcfile, unsigned int line,
 #define expect_eq_bitmap(...)		__expect_eq(bitmap, ##__VA_ARGS__)
 #define expect_eq_pbl(...)		__expect_eq(pbl, ##__VA_ARGS__)
 #define expect_eq_u32_array(...)	__expect_eq(u32_array, ##__VA_ARGS__)
+#define expect_eq_clump8(...)		__expect_eq(clump8, ##__VA_ARGS__)
 
 static void __init test_zero_clear(void)
 {

@@ -404,6 +435,39 @@ static void noinline __init test_mem_optimisations(void)
 	}
 }
 
+static const unsigned char clump_exp[] __initconst = {
+	0x01,	/* 1 bit set */
+	0x02,	/* non-edge 1 bit set */
+	0x00,	/* zero bits set */
+	0x38,	/* 3 bits set across 4-bit boundary */
+	0x38,	/* Repeated clump */
+	0x0F,	/* 4 bits set */
+	0xFF,	/* all bits set */
+	0x05,	/* non-adjacent 2 bits set */
+};
+
+static void __init test_for_each_set_clump8(void)
+{
+#define CLUMP_EXP_NUMBITS 64
+	DECLARE_BITMAP(bits, CLUMP_EXP_NUMBITS);
+	unsigned int start;
+	unsigned long clump;
+
+	/* set bitmap to test case */
+	bitmap_zero(bits, CLUMP_EXP_NUMBITS);
+	bitmap_set(bits, 0, 1);		/* 0x01 */
+	bitmap_set(bits, 9, 1);		/* 0x02 */
+	bitmap_set(bits, 27, 3);	/* 0x28 */
+	bitmap_set(bits, 35, 3);	/* 0x28 */
+	bitmap_set(bits, 40, 4);	/* 0x0F */
+	bitmap_set(bits, 48, 8);	/* 0xFF */
+	bitmap_set(bits, 56, 1);	/* 0x05 - part 1 */
+	bitmap_set(bits, 58, 1);	/* 0x05 - part 2 */
+
+	for_each_set_clump8(start, clump, bits, CLUMP_EXP_NUMBITS)
+		expect_eq_clump8(start, CLUMP_EXP_NUMBITS, clump_exp, &clump);
+}
+
 static void __init selftest(void)
 {
 	test_zero_clear();

@@ -413,6 +477,7 @@ static void __init selftest(void)
 	test_bitmap_parselist();
 	test_bitmap_parselist_user();
 	test_mem_optimisations();
+	test_for_each_set_clump8();
 }
 
 KSTM_MODULE_LOADERS(test_bitmap);

index a44fa8af5b0d..977f0f6eb1ba 100644
@@ -175,46 +175,25 @@ static int dio48e_gpio_get(struct gpio_chip *chip, unsigned offset)
 	return !!(port_state & mask);
 }
 
+static const size_t ports[] = { 0, 1, 2, 4, 5, 6 };
+
 static int dio48e_gpio_get_multiple(struct gpio_chip *chip, unsigned long *mask,
 	unsigned long *bits)
 {
 	struct dio48e_gpio *const dio48egpio = gpiochip_get_data(chip);
-	size_t i;
-	static const size_t ports[] = { 0, 1, 2, 4, 5, 6 };
-	const unsigned int gpio_reg_size = 8;
-	unsigned int bits_offset;
-	size_t word_index;
-	unsigned int word_offset;
-	unsigned long word_mask;
-	const unsigned long port_mask = GENMASK(gpio_reg_size - 1, 0);
+	unsigned long offset;
+	unsigned long gpio_mask;
+	unsigned int port_addr;
 	unsigned long port_state;
 
 	/* clear bits array to a clean slate */
 	bitmap_zero(bits, chip->ngpio);
 
-	/* get bits are evaluated a gpio port register at a time */
-	for (i = 0; i < ARRAY_SIZE(ports); i++) {
-		/* gpio offset in bits array */
-		bits_offset = i * gpio_reg_size;
-
-		/* word index for bits array */
-		word_index = BIT_WORD(bits_offset);
-
-		/* gpio offset within current word of bits array */
-		word_offset = bits_offset % BITS_PER_LONG;
-
-		/* mask of get bits for current gpio within current word */
-		word_mask = mask[word_index] & (port_mask << word_offset);
-		if (!word_mask) {
-			/* no get bits in this port so skip to next one */
-			continue;
-		}
-
-		/* read bits from current gpio port */
-		port_state = inb(dio48egpio->base + ports[i]);
+	for_each_set_clump8(offset, gpio_mask, mask, ARRAY_SIZE(ports) * 8) {
+		port_addr = dio48egpio->base + ports[offset / 8];
+		port_state = inb(port_addr) & gpio_mask;
 
-		/* store acquired bits at respective bits array offset */
-		bits[word_index] |= (port_state << word_offset) & word_mask;
+		bitmap_set_value8(bits, port_state, offset);
 	}
 
 	return 0;

@@ -244,37 +223,27 @@ static void dio48e_gpio_set_multiple(struct gpio_chip *chip,
 	unsigned long *mask, unsigned long *bits)
 {
 	struct dio48e_gpio *const dio48egpio = gpiochip_get_data(chip);
-	unsigned int i;
-	const unsigned int gpio_reg_size = 8;
-	unsigned int port;
-	unsigned int out_port;
-	unsigned int bitmask;
+	unsigned long offset;
+	unsigned long gpio_mask;
+	size_t index;
+	unsigned int port_addr;
+	unsigned long bitmask;
 	unsigned long flags;
 
-	/* set bits are evaluated a gpio register size at a time */
-	for (i = 0; i < chip->ngpio; i += gpio_reg_size) {
-		/* no more set bits in this mask word; skip to the next word */
-		if (!mask[BIT_WORD(i)]) {
-			i = (BIT_WORD(i) + 1) * BITS_PER_LONG - gpio_reg_size;
-			continue;
-		}
+	for_each_set_clump8(offset, gpio_mask, mask, ARRAY_SIZE(ports) * 8) {
+		index = offset / 8;
+		port_addr = dio48egpio->base + ports[index];
 
-		port = i / gpio_reg_size;
-		out_port = (port > 2) ? port + 1 : port;
-		bitmask = mask[BIT_WORD(i)] & bits[BIT_WORD(i)];
+		bitmask = bitmap_get_value8(bits, offset) & gpio_mask;
 
 		raw_spin_lock_irqsave(&dio48egpio->lock, flags);
 
 		/* update output state data and set device gpio register */
-		dio48egpio->out_state[port] &= ~mask[BIT_WORD(i)];
-		dio48egpio->out_state[port] |= bitmask;
-		outb(dio48egpio->out_state[port], dio48egpio->base + out_port);
+		dio48egpio->out_state[index] &= ~gpio_mask;
+		dio48egpio->out_state[index] |= bitmask;
+		outb(dio48egpio->out_state[index], port_addr);
 
 		raw_spin_unlock_irqrestore(&dio48egpio->lock, flags);
-
-		/* prepare for next gpio register set */
-		mask[BIT_WORD(i)] >>= gpio_reg_size;
-		bits[BIT_WORD(i)] >>= gpio_reg_size;
 	}
 }
 

index ff53887bdaa8..bf67040cbbbb 100644
@@ -85,42 +85,20 @@ static int idi_48_gpio_get_multiple(struct gpio_chip *chip, unsigned long *mask,
 	unsigned long *bits)
 {
 	struct idi_48_gpio *const idi48gpio = gpiochip_get_data(chip);
-	size_t i;
+	unsigned long offset;
+	unsigned long gpio_mask;
 	static const size_t ports[] = { 0, 1, 2, 4, 5, 6 };
-	const unsigned int gpio_reg_size = 8;
-	unsigned int bits_offset;
-	size_t word_index;
-	unsigned int word_offset;
-	unsigned long word_mask;
-	const unsigned long port_mask = GENMASK(gpio_reg_size - 1, 0);
+	unsigned int port_addr;
 	unsigned long port_state;
 
 	/* clear bits array to a clean slate */
 	bitmap_zero(bits, chip->ngpio);
 
-	/* get bits are evaluated a gpio port register at a time */
-	for (i = 0; i < ARRAY_SIZE(ports); i++) {
-		/* gpio offset in bits array */
-		bits_offset = i * gpio_reg_size;
+	for_each_set_clump8(offset, gpio_mask, mask, ARRAY_SIZE(ports) * 8) {
+		port_addr = idi48gpio->base + ports[offset / 8];
+		port_state = inb(port_addr) & gpio_mask;
 
-		/* word index for bits array */
-		word_index = BIT_WORD(bits_offset);
-
-		/* gpio offset within current word of bits array */
-		word_offset = bits_offset % BITS_PER_LONG;
-
-		/* mask of get bits for current gpio within current word */
-		word_mask = mask[word_index] & (port_mask << word_offset);
-		if (!word_mask) {
-			/* no get bits in this port so skip to next one */
-			continue;
-		}
-
-		/* read bits from current gpio port */
-		port_state = inb(idi48gpio->base + ports[i]);
-
-		/* store acquired bits at respective bits array offset */
-		bits[word_index] |= (port_state << word_offset) & word_mask;
+		bitmap_set_value8(bits, port_state, offset);
 	}
 
 	return 0;

index 78a1db24e931..72196ea36358 100644
@@ -164,46 +164,25 @@ static int gpiomm_gpio_get(struct gpio_chip *chip, unsigned int offset)
 	return !!(port_state & mask);
 }
 
+static const size_t ports[] = { 0, 1, 2, 4, 5, 6 };
+
 static int gpiomm_gpio_get_multiple(struct gpio_chip *chip, unsigned long *mask,
 	unsigned long *bits)
 {
 	struct gpiomm_gpio *const gpiommgpio = gpiochip_get_data(chip);
-	size_t i;
-	static const size_t ports[] = { 0, 1, 2, 4, 5, 6 };
-	const unsigned int gpio_reg_size = 8;
-	unsigned int bits_offset;
-	size_t word_index;
-	unsigned int word_offset;
-	unsigned long word_mask;
-	const unsigned long port_mask = GENMASK(gpio_reg_size - 1, 0);
+	unsigned long offset;
+	unsigned long gpio_mask;
+	unsigned int port_addr;
 	unsigned long port_state;
 
 	/* clear bits array to a clean slate */
 	bitmap_zero(bits, chip->ngpio);
 
-	/* get bits are evaluated a gpio port register at a time */
-	for (i = 0; i < ARRAY_SIZE(ports); i++) {
-		/* gpio offset in bits array */
-		bits_offset = i * gpio_reg_size;
-
-		/* word index for bits array */
-		word_index = BIT_WORD(bits_offset);
-
-		/* gpio offset within current word of bits array */
-		word_offset = bits_offset % BITS_PER_LONG;
-
-		/* mask of get bits for current gpio within current word */
-		word_mask = mask[word_index] & (port_mask << word_offset);
-		if (!word_mask) {
-			/* no get bits in this port so skip to next one */
-			continue;
-		}
-
-		/* read bits from current gpio port */
-		port_state = inb(gpiommgpio->base + ports[i]);
+	for_each_set_clump8(offset, gpio_mask, mask, ARRAY_SIZE(ports) * 8) {
+		port_addr = gpiommgpio->base + ports[offset / 8];
+		port_state = inb(port_addr) & gpio_mask;
 
-		/* store acquired bits at respective bits array offset */
-		bits[word_index] |= (port_state << word_offset) & word_mask;
+		bitmap_set_value8(bits, port_state, offset);
 	}
 
 	return 0;

@@ -234,37 +213,27 @@ static void gpiomm_gpio_set_multiple(struct gpio_chip *chip,
 	unsigned long *mask, unsigned long *bits)
 {
 	struct gpiomm_gpio *const gpiommgpio = gpiochip_get_data(chip);
-	unsigned int i;
-	const unsigned int gpio_reg_size = 8;
-	unsigned int port;
-	unsigned int out_port;
-	unsigned int bitmask;
+	unsigned long offset;
+	unsigned long gpio_mask;
+	size_t index;
+	unsigned int port_addr;
+	unsigned long bitmask;
 	unsigned long flags;
 
-	/* set bits are evaluated a gpio register size at a time */
-	for (i = 0; i < chip->ngpio; i += gpio_reg_size) {
-		/* no more set bits in this mask word; skip to the next word */
-		if (!mask[BIT_WORD(i)]) {
-			i = (BIT_WORD(i) + 1) * BITS_PER_LONG - gpio_reg_size;
-			continue;
-		}
+	for_each_set_clump8(offset, gpio_mask, mask, ARRAY_SIZE(ports) * 8) {
+		index = offset / 8;
+		port_addr = gpiommgpio->base + ports[index];
 
-		port = i / gpio_reg_size;
-		out_port = (port > 2) ? port + 1 : port;
-		bitmask = mask[BIT_WORD(i)] & bits[BIT_WORD(i)];
+		bitmask = bitmap_get_value8(bits, offset) & gpio_mask;
 
 		spin_lock_irqsave(&gpiommgpio->lock, flags);
 
 		/* update output state data and set device gpio register */
-		gpiommgpio->out_state[port] &= ~mask[BIT_WORD(i)];
-		gpiommgpio->out_state[port] |= bitmask;
-		outb(gpiommgpio->out_state[port], gpiommgpio->base + out_port);
+		gpiommgpio->out_state[index] &= ~gpio_mask;
+		gpiommgpio->out_state[index] |= bitmask;
+		outb(gpiommgpio->out_state[index], port_addr);
 
 		spin_unlock_irqrestore(&gpiommgpio->lock, flags);
-
-		/* prepare for next gpio register set */
-		mask[BIT_WORD(i)] >>= gpio_reg_size;
-		bits[BIT_WORD(i)] >>= gpio_reg_size;
 	}
 }
 

index e0ef66b6a237..51aaa5c17fce 100644
@@ -126,42 +126,19 @@ static int ws16c48_gpio_get_multiple(struct gpio_chip *chip,
 	unsigned long *mask, unsigned long *bits)
 {
 	struct ws16c48_gpio *const ws16c48gpio = gpiochip_get_data(chip);
-	const unsigned int gpio_reg_size = 8;
-	size_t i;
-	const size_t num_ports = chip->ngpio / gpio_reg_size;
-	unsigned int bits_offset;
-	size_t word_index;
-	unsigned int word_offset;
-	unsigned long word_mask;
-	const unsigned long port_mask = GENMASK(gpio_reg_size - 1, 0);
+	unsigned long offset;
+	unsigned long gpio_mask;
+	unsigned int port_addr;
 	unsigned long port_state;
 
 	/* clear bits array to a clean slate */
 	bitmap_zero(bits, chip->ngpio);
 
-	/* get bits are evaluated a gpio port register at a time */
-	for (i = 0; i < num_ports; i++) {
-		/* gpio offset in bits array */
-		bits_offset = i * gpio_reg_size;
+	for_each_set_clump8(offset, gpio_mask, mask, chip->ngpio) {
+		port_addr = ws16c48gpio->base + offset / 8;
+		port_state = inb(port_addr) & gpio_mask;
 
-		/* word index for bits array */
-		word_index = BIT_WORD(bits_offset);
-
-		/* gpio offset within current word of bits array */
-		word_offset = bits_offset % BITS_PER_LONG;
-
-		/* mask of get bits for current gpio within current word */
-		word_mask = mask[word_index] & (port_mask << word_offset);
-		if (!word_mask) {
-			/* no get bits in this port so skip to next one */
-			continue;
-		}
-
-		/* read bits from current gpio port */
-		port_state = inb(ws16c48gpio->base + i);
-
-		/* store acquired bits at respective bits array offset */
-		bits[word_index] |= (port_state << word_offset) & word_mask;
+		bitmap_set_value8(bits, port_state, offset);
 	}
 
 	return 0;

@@ -195,39 +172,29 @@ static void ws16c48_gpio_set_multiple(struct gpio_chip *chip,
 	unsigned long *mask, unsigned long *bits)
 {
 	struct ws16c48_gpio *const ws16c48gpio = gpiochip_get_data(chip);
-	unsigned int i;
-	const unsigned int gpio_reg_size = 8;
-	unsigned int port;
-	unsigned int iomask;
-	unsigned int bitmask;
+	unsigned long offset;
+	unsigned long gpio_mask;
+	size_t index;
+	unsigned int port_addr;
+	unsigned long bitmask;
 	unsigned long flags;
 
-	/* set bits are evaluated a gpio register size at a time */
-	for (i = 0; i < chip->ngpio; i += gpio_reg_size) {
-		/* no more set bits in this mask word; skip to the next word */
-		if (!mask[BIT_WORD(i)]) {
-			i = (BIT_WORD(i) + 1) * BITS_PER_LONG - gpio_reg_size;
-			continue;
-		}
-
-		port = i / gpio_reg_size;
+	for_each_set_clump8(offset, gpio_mask, mask, chip->ngpio) {
+		index = offset / 8;
+		port_addr = ws16c48gpio->base + index;
 
 		/* mask out GPIO configured for input */
-		iomask = mask[BIT_WORD(i)] & ~ws16c48gpio->io_state[port];
-		bitmask = iomask & bits[BIT_WORD(i)];
+		gpio_mask &= ~ws16c48gpio->io_state[index];
+		bitmask = bitmap_get_value8(bits, offset) & gpio_mask;
 
 		raw_spin_lock_irqsave(&ws16c48gpio->lock, flags);
 
 		/* update output state data and set device gpio register */
-		ws16c48gpio->out_state[port] &= ~iomask;
-		ws16c48gpio->out_state[port] |= bitmask;
-		outb(ws16c48gpio->out_state[port], ws16c48gpio->base + port);
+		ws16c48gpio->out_state[index] &= ~gpio_mask;
+		ws16c48gpio->out_state[index] |= bitmask;
+		outb(ws16c48gpio->out_state[index], port_addr);
 
 		raw_spin_unlock_irqrestore(&ws16c48gpio->lock, flags);
-
-		/* prepare for next gpio register set */
-		mask[BIT_WORD(i)] >>= gpio_reg_size;
-		bits[BIT_WORD(i)] >>= gpio_reg_size;
 	}
 }
 

index 5aa136a6a3e0..6c117e57078c 100644
@@ -100,45 +100,23 @@ static int idio_16_gpio_get_multiple(struct gpio_chip *chip,
 	unsigned long *mask, unsigned long *bits)
 {
 	struct idio_16_gpio *const idio16gpio = gpiochip_get_data(chip);
-	size_t i;
-	const unsigned int gpio_reg_size = 8;
-	unsigned int bits_offset;
-	size_t word_index;
-	unsigned int word_offset;
-	unsigned long word_mask;
-	const unsigned long port_mask = GENMASK(gpio_reg_size - 1, 0);
-	unsigned long port_state;
+	unsigned long offset;
+	unsigned long gpio_mask;
 	void __iomem *ports[] = {
 		&idio16gpio->reg->out0_7, &idio16gpio->reg->out8_15,
 		&idio16gpio->reg->in0_7, &idio16gpio->reg->in8_15,
 	};
+	void __iomem *port_addr;
+	unsigned long port_state;
 
 	/* clear bits array to a clean slate */
 	bitmap_zero(bits, chip->ngpio);
 
-	/* get bits are evaluated a gpio port register at a time */
-	for (i = 0; i < ARRAY_SIZE(ports); i++) {
-		/* gpio offset in bits array */
-		bits_offset = i * gpio_reg_size;
-
-		/* word index for bits array */
-		word_index = BIT_WORD(bits_offset);
-
-		/* gpio offset within current word of bits array */
-		word_offset = bits_offset % BITS_PER_LONG;
-
-		/* mask of get bits for current gpio within current word */
-		word_mask = mask[word_index] & (port_mask << word_offset);
-		if (!word_mask) {
-			/* no get bits in this port so skip to next one */
-			continue;
-		}
+	for_each_set_clump8(offset, gpio_mask, mask, ARRAY_SIZE(ports) * 8) {
+		port_addr = ports[offset / 8];
+		port_state = ioread8(port_addr) & gpio_mask;
 
-		/* read bits from current gpio port */
-		port_state = ioread8(ports[i]);
-
-		/* store acquired bits at respective bits array offset */
-		bits[word_index] |= (port_state << word_offset) & word_mask;
+		bitmap_set_value8(bits, port_state, offset);
 	}
 
 	return 0;

@@ -178,30 +156,31 @@ static void idio_16_gpio_set_multiple(struct gpio_chip *chip,
 	unsigned long *mask, unsigned long *bits)
 {
 	struct idio_16_gpio *const idio16gpio = gpiochip_get_data(chip);
+	unsigned long offset;
+	unsigned long gpio_mask;
+	void __iomem *ports[] = {
+		&idio16gpio->reg->out0_7, &idio16gpio->reg->out8_15,
+	};
+	size_t index;
+	void __iomem *port_addr;
+	unsigned long bitmask;
 	unsigned long flags;
-	unsigned int out_state;
+	unsigned long out_state;
 
-	raw_spin_lock_irqsave(&idio16gpio->lock, flags);
+	for_each_set_clump8(offset, gpio_mask, mask, ARRAY_SIZE(ports) * 8) {
+		index = offset / 8;
+		port_addr = ports[index];
 
-	/* process output lines 0-7 */
-	if (*mask & 0xFF) {
-		out_state = ioread8(&idio16gpio->reg->out0_7) & ~*mask;
-		out_state |= *mask & *bits;
-		iowrite8(out_state, &idio16gpio->reg->out0_7);
-	}
+		bitmask = bitmap_get_value8(bits, offset) & gpio_mask;
+
+		raw_spin_lock_irqsave(&idio16gpio->lock, flags);
 
-	/* shift to next output line word */
-	*mask >>= 8;
+		out_state = ioread8(port_addr) & ~gpio_mask;
+		out_state |= bitmask;
+		iowrite8(out_state, port_addr);
 
-	/* process output lines 8-15 */
-	if (*mask & 0xFF) {
-		*bits >>= 8;
-		out_state = ioread8(&idio16gpio->reg->out8_15) & ~*mask;
-		out_state |= *mask & *bits;
-		iowrite8(out_state, &idio16gpio->reg->out8_15);
+		raw_spin_unlock_irqrestore(&idio16gpio->lock, flags);
 	}
-
-	raw_spin_unlock_irqrestore(&idio16gpio->lock, flags);
 }
 
 static void idio_16_irq_ack(struct irq_data *data)

index 52f1647a46fd..924ec916b358 100644
@@ -198,52 +198,34 @@ static int idio_24_gpio_get_multiple(struct gpio_chip *chip,
 	unsigned long *mask, unsigned long *bits)
 {
 	struct idio_24_gpio *const idio24gpio = gpiochip_get_data(chip);
-	size_t i;
-	const unsigned int gpio_reg_size = 8;
-	unsigned int bits_offset;
-	size_t word_index;
-	unsigned int word_offset;
-	unsigned long word_mask;
-	const unsigned long port_mask = GENMASK(gpio_reg_size - 1, 0);
-	unsigned long port_state;
+	unsigned long offset;
+	unsigned long gpio_mask;
 	void __iomem *ports[] = {
 		&idio24gpio->reg->out0_7, &idio24gpio->reg->out8_15,
 		&idio24gpio->reg->out16_23, &idio24gpio->reg->in0_7,
 		&idio24gpio->reg->in8_15, &idio24gpio->reg->in16_23,
 	};
+	size_t index;
+	unsigned long port_state;
 	const unsigned long out_mode_mask = BIT(1);
 
 	/* clear bits array to a clean slate */
 	bitmap_zero(bits, chip->ngpio);
 
-	/* get bits are evaluated a gpio port register at a time */
-	for (i = 0; i < ARRAY_SIZE(ports) + 1; i++) {
-		/* gpio offset in bits array */
-		bits_offset = i * gpio_reg_size;
-
-		/* word index for bits array */
-		word_index = BIT_WORD(bits_offset);
-
-		/* gpio offset within current word of bits array */
-		word_offset = bits_offset % BITS_PER_LONG;
-
-		/* mask of get bits for current gpio within current word */
-		word_mask = mask[word_index] & (port_mask << word_offset);
-		if (!word_mask) {
-			/* no get bits in this port so skip to next one */
-			continue;
-		}
+	for_each_set_clump8(offset, gpio_mask, mask, ARRAY_SIZE(ports) * 8) {
+		index = offset / 8;
 
 		/* read bits from current gpio port (port 6 is TTL GPIO) */
-		if (i < 6)
-			port_state = ioread8(ports[i]);
+		if (index < 6)
+			port_state = ioread8(ports[index]);
 		else if (ioread8(&idio24gpio->reg->ctl) & out_mode_mask)
 			port_state = ioread8(&idio24gpio->reg->ttl_out0_7);
 		else
 			port_state = ioread8(&idio24gpio->reg->ttl_in0_7);
 
-		/* store acquired bits at respective bits array offset */
-		bits[word_index] |= (port_state << word_offset) & word_mask;
+		port_state &= gpio_mask;
+
+		bitmap_set_value8(bits, port_state, offset);
 	}
 
 	return 0;

@@ -294,59 +276,48 @@ static void idio_24_gpio_set_multiple(struct gpio_chip *chip,
 	unsigned long *mask, unsigned long *bits)
 {
 	struct idio_24_gpio *const idio24gpio = gpiochip_get_data(chip);
-	size_t i;
-	unsigned long bits_offset;
+	unsigned long offset;
 	unsigned long gpio_mask;
-	const unsigned int gpio_reg_size = 8;
-	const unsigned long port_mask = GENMASK(gpio_reg_size, 0);
-	unsigned long flags;
-	unsigned int out_state;
 	void __iomem *ports[] = {
 		&idio24gpio->reg->out0_7, &idio24gpio->reg->out8_15,
 		&idio24gpio->reg->out16_23
 	};
+	size_t index;
+	unsigned long bitmask;
+	unsigned long flags;
+	unsigned long out_state;
 	const unsigned long out_mode_mask = BIT(1);
-	const unsigned int ttl_offset = 48;
-	const size_t ttl_i = BIT_WORD(ttl_offset);
-	const unsigned int word_offset = ttl_offset % BITS_PER_LONG;
-	const unsigned long ttl_mask = (mask[ttl_i] >> word_offset) & port_mask;
-	const unsigned long ttl_bits = (bits[ttl_i] >> word_offset) & ttl_mask;
-
-	/* set bits are processed a gpio port register at a time */
-	for (i = 0; i < ARRAY_SIZE(ports); i++) {
-		/* gpio offset in bits array */
-		bits_offset = i * gpio_reg_size;
-
-		/* check if any set bits for current port */
-		gpio_mask = (*mask >> bits_offset) & port_mask;
-		if (!gpio_mask) {
-			/* no set bits for this port so move on to next port */
-			continue;
-		}
 
-		raw_spin_lock_irqsave(&idio24gpio->lock, flags);
+	for_each_set_clump8(offset, gpio_mask, mask, ARRAY_SIZE(ports) * 8) {
+		index = offset / 8;
 
-		/* process output lines */
-		out_state = ioread8(ports[i]) & ~gpio_mask;
-		out_state |= (*bits >> bits_offset) & gpio_mask;
-		iowrite8(out_state, ports[i]);
+		bitmask = bitmap_get_value8(bits, offset) & gpio_mask;
 
-		raw_spin_unlock_irqrestore(&idio24gpio->lock, flags);
-	}
+		raw_spin_lock_irqsave(&idio24gpio->lock, flags);
 
-	/* check if setting TTL lines and if they are in output mode */
-	if (!ttl_mask || !(ioread8(&idio24gpio->reg->ctl) & out_mode_mask))
-		return;
+		/* read bits from current gpio port (port 6 is TTL GPIO) */
+		if (index < 6) {
+			out_state = ioread8(ports[index]);
+		} else if (ioread8(&idio24gpio->reg->ctl) & out_mode_mask) {
+			out_state = ioread8(&idio24gpio->reg->ttl_out0_7);
+		} else {
+			/* skip TTL GPIO if set for input */
+			raw_spin_unlock_irqrestore(&idio24gpio->lock, flags);
+			continue;
+		}
 
-	/* handle TTL output */
-	raw_spin_lock_irqsave(&idio24gpio->lock, flags);
+		/* set requested bit states */
+		out_state &= ~gpio_mask;
+		out_state |= bitmask;
 
-	/* process output lines */
-	out_state = ioread8(&idio24gpio->reg->ttl_out0_7) & ~ttl_mask;
-	out_state |= ttl_bits;
-	iowrite8(out_state, &idio24gpio->reg->ttl_out0_7);
+		/* write bits for current gpio port (port 6 is TTL GPIO) */
+		if (index < 6)
+			iowrite8(out_state, ports[index]);
+		else
+			iowrite8(out_state, &idio24gpio->reg->ttl_out0_7);
 
-	raw_spin_unlock_irqrestore(&idio24gpio->lock, flags);
+		raw_spin_unlock_irqrestore(&idio24gpio->lock, flags);
+	}
 }
 
 static void idio_24_irq_ack(struct irq_data *data)

index 93cdcc41e9fb..3e4b15d0231e 100644
@@ -15,9 +15,6 @@
 #include <linux/spinlock.h>
 #include <dt-bindings/gpio/uniphier-gpio.h>
 
-#define UNIPHIER_GPIO_BANK_MASK		\
-				GENMASK((UNIPHIER_GPIO_LINES_PER_BANK) - 1, 0)
-
 #define UNIPHIER_GPIO_IRQ_MAX_NUM	24
 
 #define UNIPHIER_GPIO_PORT_DATA		0x0	/* data */

@@ -147,15 +144,14 @@ static void uniphier_gpio_set(struct gpio_chip *chip,
 static void uniphier_gpio_set_multiple(struct gpio_chip *chip,
 				       unsigned long *mask, unsigned long *bits)
 {
-	unsigned int bank, shift, bank_mask, bank_bits;
-	int i;
+	unsigned long i;
+	unsigned long bank_mask;
+	unsigned long bank;
+	unsigned long bank_bits;
 
-	for (i = 0; i < chip->ngpio; i += UNIPHIER_GPIO_LINES_PER_BANK) {
+	for_each_set_clump8(i, bank_mask, mask, chip->ngpio) {
 		bank = i / UNIPHIER_GPIO_LINES_PER_BANK;
-		shift = i % BITS_PER_LONG;
-		bank_mask = (mask[BIT_WORD(i)] >> shift) &
-						UNIPHIER_GPIO_BANK_MASK;
-		bank_bits = bits[BIT_WORD(i)] >> shift;
+		bank_bits = bitmap_get_value8(bits, i);
 
 		uniphier_gpio_bank_write(chip, bank, UNIPHIER_GPIO_PORT_DATA,
 					 bank_mask, bank_bits);

index e81307f9754e..05637d585152 100644
@@ -6,6 +6,7 @@
  *  Copyright (C) 2010 Miguel Gaio <[email protected]>
  */
 
+#include <linux/bitops.h>
 #include <linux/gpio/consumer.h>
 #include <linux/gpio/driver.h>
 #include <linux/module.h>

@@ -72,20 +73,18 @@ static void gen_74x164_set_multiple(struct gpio_chip *gc, unsigned long *mask,
 				    unsigned long *bits)
 {
 	struct gen_74x164_chip *chip = gpiochip_get_data(gc);
-	unsigned int i, idx, shift;
-	u8 bank, bankmask;
+	unsigned long offset;
+	unsigned long bankmask;
+	size_t bank;
+	unsigned long bitmask;
 
 	mutex_lock(&chip->lock);
-	for (i = 0, bank = chip->registers - 1; i < chip->registers;
-	     i++, bank--) {
-		idx = i / sizeof(*mask);
-		shift = i % sizeof(*mask) * BITS_PER_BYTE;
-		bankmask = mask[idx] >> shift;
-		if (!bankmask)
-			continue;
+	for_each_set_clump8(offset, bankmask, mask, chip->registers * 8) {
+		bank = chip->registers - 1 - offset / 8;
+		bitmask = bitmap_get_value8(bits, offset) & bankmask;
 
 		chip->buffer[bank] &= ~bankmask;
-		chip->buffer[bank] |= bankmask & (bits[idx] >> shift);
+		chip->buffer[bank] |= bitmask;
 	}
 	__gen_74x164_write_config(chip);
 	mutex_unlock(&chip->lock);

index 5716b62e0f73..901f64bb5b9c 100644
@@ -6,6 +6,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/bitops.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/interrupt.h>

@@ -102,6 +103,7 @@ static int update_trip_temp(struct intel_soc_dts_sensor_entry *dts,
 {
 	int status;
 	u32 temp_out;
+	unsigned long update_ptps;
 	u32 out;
 	u32 store_ptps;
 	u32 store_ptmc;

@@ -120,8 +122,9 @@ static int update_trip_temp(struct intel_soc_dts_sensor_entry *dts,
 	if (status)
 		return status;
 
-	out = (store_ptps & ~(0xFF << (thres_index * 8)));
-	out |= (temp_out & 0xFF) << (thres_index * 8);
+	update_ptps = store_ptps;
+	bitmap_set_value8(&update_ptps, temp_out & 0xFF, thres_index * 8);
+	out = update_ptps;
 	status = iosf_mbi_write(BT_MBI_UNIT_PMC, MBI_REG_WRITE,
 				SOC_DTS_OFFSET_PTPS, out);
 	if (status)

@@ -223,6 +226,7 @@ static int sys_get_curr_temp(struct thermal_zone_device *tzd,
 	u32 out;
 	struct intel_soc_dts_sensor_entry *dts;
 	struct intel_soc_dts_sensors *sensors;
+	unsigned long temp_raw;
 
 	dts = tzd->devdata;
 	sensors = dts->sensors;

@@ -231,7 +235,8 @@ static int sys_get_curr_temp(struct thermal_zone_device *tzd,
 	if (status)
 		return status;
 
-	out = (out & dts->temp_mask) >> dts->temp_shift;
+	temp_raw = out;
+	out = bitmap_get_value8(&temp_raw, dts->id * 8);
 	out -= SOC_DTS_TJMAX_ENCODING;
 	*temp = sensors->tj_max - out * 1000;
 

@@ -281,10 +286,13 @@ static int add_dts_thermal_zone(int id, struct intel_soc_dts_sensor_entry *dts,
 {
 	char name[10];
 	int trip_count = 0;
+	int writable_trip_count = 0;
 	int trip_mask = 0;
 	u32 store_ptps;
 	int ret;
-	int i;
+	unsigned long i;
+	unsigned long trip;
+	unsigned long ptps;
 
 	/* Store status to restor on exit */
 	ret = iosf_mbi_read(BT_MBI_UNIT_PMC, MBI_REG_READ,

@@ -293,11 +301,10 @@ static int add_dts_thermal_zone(int id, struct intel_soc_dts_sensor_entry *dts,
 		goto err_ret;
 
 	dts->id = id;
-	dts->temp_mask = 0x00FF << (id * 8);
-	dts->temp_shift = id * 8;
 	if (notification_support) {
 		trip_count = min(SOC_MAX_DTS_TRIPS, trip_cnt);
-		trip_mask = BIT(trip_count - read_only_trip_cnt) - 1;
+		writable_trip_count = trip_count - read_only_trip_cnt;
+		trip_mask = GENMASK(writable_trip_count - 1, 0);
 	}
 
 	/* Check if the writable trip we provide is not used by BIOS */

@@ -306,11 +313,9 @@ static int add_dts_thermal_zone(int id, struct intel_soc_dts_sensor_entry *dts,
 	if (ret)
 		trip_mask = 0;
 	else {
-		for (i = 0; i < trip_count; ++i) {
-			if (trip_mask & BIT(i))
-				if (store_ptps & (0xff << (i * 8)))
-					trip_mask &= ~BIT(i);
-		}
+		ptps = store_ptps;
+		for_each_set_clump8(i, trip, &ptps, writable_trip_count * 8)
+			trip_mask &= ~BIT(i / 8);
 	}
 	dts->trip_mask = trip_mask;
 	dts->trip_count = trip_count;

index adfb09af33fc..c54945748200 100644
@@ -24,8 +24,6 @@ struct intel_soc_dts_sensors;
 
 struct intel_soc_dts_sensor_entry {
 	int id;
-	u32 temp_mask;
-	u32 temp_shift;
 	u32 store_status;
 	u32 trip_mask;
 	u32 trip_count;

index f809a5a8e9eb..9ab2c044ef52 100644
@@ -96,16 +96,16 @@ static int pisosr_gpio_get_multiple(struct gpio_chip *chip,
 				    unsigned long *mask, unsigned long *bits)
 {
 	struct pisosr_gpio *gpio = gpiochip_get_data(chip);
-	unsigned int nbytes = DIV_ROUND_UP(chip->ngpio, 8);
-	unsigned int i, j;
+	unsigned long offset;
+	unsigned long gpio_mask;
+	unsigned long buffer_state;
 
 	pisosr_gpio_refresh(gpio);
 
 	bitmap_zero(bits, chip->ngpio);
-	for (i = 0; i < nbytes; i++) {
-		j = i / sizeof(unsigned long);
-		bits[j] |= ((unsigned long) gpio->buffer[i])
-			   << (8 * (i % sizeof(unsigned long)));
+	for_each_set_clump8(offset, gpio_mask, mask, chip->ngpio) {
+		buffer_state = gpio->buffer[offset / 8] & gpio_mask;
+		bitmap_set_value8(bits, buffer_state, offset);
 	}
 
 	return 0;

index 4b4b2ceb82fc..9a98ecf625ac 100644
@@ -31,6 +31,7 @@
  */
 
 #include <linux/bitmap.h>
+#include <linux/bitops.h>
 #include <linux/crc8.h>
 #include <linux/gpio/consumer.h>
 #include <linux/gpio/driver.h>

@@ -232,16 +233,20 @@ static int max3191x_get_multiple(struct gpio_chip *gpio, unsigned long *mask,
 				 unsigned long *bits)
 {
 	struct max3191x_chip *max3191x = gpiochip_get_data(gpio);
-	int ret, bit = 0, wordlen = max3191x_wordlen(max3191x);
+	const unsigned int wordlen = max3191x_wordlen(max3191x);
+	int ret;
+	unsigned long bit;
+	unsigned long gpio_mask;
+	unsigned long in;
 
 	mutex_lock(&max3191x->lock);
 	ret = max3191x_readout_locked(max3191x);
 	if (ret)
 		goto out_unlock;
 
-	while ((bit = find_next_bit(mask, gpio->ngpio, bit)) != gpio->ngpio) {
+	bitmap_zero(bits, gpio->ngpio);
+	for_each_set_clump8(bit, gpio_mask, mask, gpio->ngpio) {
 		unsigned int chipnum = bit / MAX3191X_NGPIO;
-		unsigned long in, shift, index;
 
 		if (max3191x_chip_is_faulting(max3191x, chipnum)) {
 			ret = -EIO;

@@ -249,12 +254,8 @@ static int max3191x_get_multiple(struct gpio_chip *gpio, unsigned long *mask,
 		}
 
 		in = ((u8 *)max3191x->xfer.rx_buf)[chipnum * wordlen];
-		shift = round_down(bit % BITS_PER_LONG, MAX3191X_NGPIO);
-		index = bit / BITS_PER_LONG;
-		bits[index] &= ~(mask[index] & (0xff << shift));
-		bits[index] |= mask[index] & (in << shift); /* copy bits */
-
-		bit = (chipnum + 1) * MAX3191X_NGPIO; /* go to next chip */
+		in &= gpio_mask;
+		bitmap_set_value8(bits, in, offset);
 	}
 
 out_unlock:

index de5d1383f28d..10b669b8f27d 100644
@@ -10,6 +10,7 @@
 
 #include <linux/acpi.h>
 #include <linux/bits.h>
+#include <linux/bitops.h>
 #include <linux/gpio/driver.h>
 #include <linux/gpio/consumer.h>
 #include <linux/i2c.h>

@@ -456,7 +457,8 @@ static void pca953x_gpio_set_multiple(struct gpio_chip *gc,
 				      unsigned long *mask, unsigned long *bits)
 {
 	struct pca953x_chip *chip = gpiochip_get_data(gc);
-	unsigned int bank_mask, bank_val;
+	unsigned long offset;
+	unsigned long bank_mask;
 	int bank;
 	u8 reg_val[MAX_BANK];
 	int ret;

@@ -466,15 +468,10 @@ static void pca953x_gpio_set_multiple(struct gpio_chip *gc,
 	if (ret)
 		goto exit;
 
-	for (bank = 0; bank < NBANK(chip); bank++) {
-		bank_mask = mask[bank / sizeof(*mask)] >>
-			   ((bank % sizeof(*mask)) * 8);
-		if (bank_mask) {
-			bank_val = bits[bank / sizeof(*bits)] >>
-				  ((bank % sizeof(*bits)) * 8);
-			bank_val &= bank_mask;
-			reg_val[bank] = (reg_val[bank] & ~bank_mask) | bank_val;
-		}
+	for_each_set_clump8(offset, bank_mask, mask, gc->ngpio) {
+		bank = offset / 8;
+		reg_val[bank] &= ~bank_mask;
+		reg_val[bank] |= bitmap_get_value8(bits, offset) & bank_mask;
 	}
 
 	pca953x_write_regs(chip, chip->regs->output, reg_val);