diff --git a/Documentation/core-api/packing.rst b/Documentation/core-api/packing.rst
index 3ed13bc9a195..821691f23c54 100644
--- a/Documentation/core-api/packing.rst
+++ b/Documentation/core-api/packing.rst
@@ -151,6 +151,77 @@ the more significant 4-byte word.
 We always think of our offsets as if there were no quirk, and we translate
 them afterwards, before accessing the memory region.
 
+Note on buffer lengths not multiple of 4
+----------------------------------------
+
+To deal with memory layout quirks where groups of 4 bytes are laid out "little
+endian" relative to each other, but "big endian" within the group itself, the
+concept of groups of 4 bytes is intrinsic to the packing API (not to be
+confused with the memory access, which is performed byte by byte, though).
+
+With buffer lengths not multiple of 4, this means one group will be incomplete.
+Depending on the quirks, this may lead to discontinuities in the bit fields
+accessible through the buffer. The packing API assumes discontinuities were not
+the intention of the memory layout, so it avoids them by effectively logically
+shortening the most significant group of 4 octets to the number of octets
+actually available.
+
+Example with a 31 byte sized buffer given below. Physical buffer offsets are
+implicit, and increase from left to right within a group, and from top to
+bottom within a column.
+
+No quirks:
+
+::
+
+            31         29         28        |   Group 7 (most significant)
+ 27         26         25         24        |   Group 6
+ 23         22         21         20        |   Group 5
+ 19         18         17         16        |   Group 4
+ 15         14         13         12        |   Group 3
+ 11         10          9          8        |   Group 2
+  7          6          5          4        |   Group 1
+  3          2          1          0        |   Group 0 (least significant)
+
+QUIRK_LSW32_IS_FIRST:
+
+::
+
+  3          2          1          0        |   Group 0 (least significant)
+  7          6          5          4        |   Group 1
+ 11         10          9          8        |   Group 2
+ 15         14         13         12        |   Group 3
+ 19         18         17         16        |   Group 4
+ 23         22         21         20        |   Group 5
+ 27         26         25         24        |   Group 6
+ 30         29         28                   |   Group 7 (most significant)
+
+QUIRK_LITTLE_ENDIAN:
+
+::
+
+            30         28         29        |   Group 7 (most significant)
+ 24         25         26         27        |   Group 6
+ 20         21         22         23        |   Group 5
+ 16         17         18         19        |   Group 4
+ 12         13         14         15        |   Group 3
+  8          9         10         11        |   Group 2
+  4          5          6          7        |   Group 1
+  0          1          2          3        |   Group 0 (least significant)
+
+QUIRK_LITTLE_ENDIAN | QUIRK_LSW32_IS_FIRST:
+
+::
+
+  0          1          2          3        |   Group 0 (least significant)
+  4          5          6          7        |   Group 1
+  8          9         10         11        |   Group 2
+ 12         13         14         15        |   Group 3
+ 16         17         18         19        |   Group 4
+ 20         21         22         23        |   Group 5
+ 24         25         26         27        |   Group 6
+ 28         29         30                   |   Group 7 (most significant)
+
 Intended use
 ------------
 
diff --git a/MAINTAINERS b/MAINTAINERS
index c27f3190737f..af635dc60cfe 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17471,6 +17471,7 @@ S:	Supported
 F:	Documentation/core-api/packing.rst
 F:	include/linux/packing.h
 F:	lib/packing.c
+F:	lib/packing_test.c
 
 PADATA PARALLEL EXECUTION MECHANISM
 M:	Steffen Klassert <steffen.klassert@secunet.com>
diff --git a/include/linux/packing.h b/include/linux/packing.h
index 8d6571feb95d..5d36dcd06f60 100644
--- a/include/linux/packing.h
+++ b/include/linux/packing.h
@@ -17,33 +17,13 @@ enum packing_op {
 	UNPACK,
 };
 
-/**
- * packing - Convert numbers (currently u64) between a packed and an unpacked
- *	     format. Unpacked means laid out in memory in the CPU's native
- *	     understanding of integers, while packed means anything else that
- *	     requires translation.
- *
- * @pbuf: Pointer to a buffer holding the packed value.
- * @uval: Pointer to an u64 holding the unpacked value.
- * @startbit: The index (in logical notation, compensated for quirks) where
- *	      the packed value starts within pbuf. Must be larger than, or
- *	      equal to, endbit.
- * @endbit: The index (in logical notation, compensated for quirks) where
- *	    the packed value ends within pbuf. Must be smaller than, or equal
- *	    to, startbit.
- * @op: If PACK, then uval will be treated as const pointer and copied (packed)
- *	into pbuf, between startbit and endbit.
- *	If UNPACK, then pbuf will be treated as const pointer and the logical
- *	value between startbit and endbit will be copied (unpacked) to uval.
- * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and
- *	    QUIRK_MSB_ON_THE_RIGHT.
- *
- * Return: 0 on success, EINVAL or ERANGE if called incorrectly. Assuming
- *	   correct usage, return code may be discarded.
- *	   If op is PACK, pbuf is modified.
- *	   If op is UNPACK, uval is modified.
- */
 int packing(void *pbuf, u64 *uval, int startbit, int endbit, size_t pbuflen,
 	    enum packing_op op, u8 quirks);
 
+int pack(void *pbuf, u64 uval, size_t startbit, size_t endbit, size_t pbuflen,
+	 u8 quirks);
+
+int unpack(const void *pbuf, u64 *uval, size_t startbit, size_t endbit,
+	   size_t pbuflen, u8 quirks);
+
 #endif
diff --git a/lib/Kconfig b/lib/Kconfig
index b38849af6f13..50d85f38b569 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -40,6 +40,18 @@ config PACKING
 
 	  When in doubt, say N.
 
+config PACKING_KUNIT_TEST
+	tristate "KUnit tests for packing library" if !KUNIT_ALL_TESTS
+	depends on PACKING && KUNIT
+	default KUNIT_ALL_TESTS
+	help
+	  This builds KUnit tests for the packing library.
+
+	  For more information on KUnit and unit tests in general,
+	  please refer to the KUnit documentation in Documentation/dev-tools/kunit/.
+
+	  When in doubt, say N.
+
 config BITREVERSE
 	tristate
 
diff --git a/lib/Makefile b/lib/Makefile
index 773adf88af41..811ba12c8cd0 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -154,6 +154,7 @@ obj-$(CONFIG_DEBUG_OBJECTS) += debugobjects.o
 obj-$(CONFIG_BITREVERSE) += bitrev.o
 obj-$(CONFIG_LINEAR_RANGES) += linear_ranges.o
 obj-$(CONFIG_PACKING)	+= packing.o
+obj-$(CONFIG_PACKING_KUNIT_TEST) += packing_test.o
 obj-$(CONFIG_CRC_CCITT)	+= crc-ccitt.o
 obj-$(CONFIG_CRC16)	+= crc16.o
 obj-$(CONFIG_CRC_T10DIF)+= crc-t10dif.o
diff --git a/lib/packing.c b/lib/packing.c
index 3f656167c17e..793942745e34 100644
--- a/lib/packing.c
+++ b/lib/packing.c
@@ -9,43 +9,271 @@
 #include <linux/types.h>
 #include <linux/bitrev.h>
 
-static int get_le_offset(int offset)
+/**
+ * calculate_box_addr - Determine physical location of byte in buffer
+ * @box: Index of byte within buffer seen as a logical big-endian big number
+ * @len: Size of buffer in bytes
+ * @quirks: mask of QUIRK_LSW32_IS_FIRST and QUIRK_LITTLE_ENDIAN
+ *
+ * Function interprets the buffer as a @len byte sized big number, and returns
+ * the physical offset of the @box logical octet within it. Internally, it
+ * treats the big number as groups of 4 bytes. If @len is not a multiple of 4,
+ * the last group may be shorter.
+ *
+ * @QUIRK_LSW32_IS_FIRST gives the ordering of groups of 4 octets relative to
+ * each other. If set, the most significant group of 4 octets is last in the
+ * buffer (and may be truncated if @len is not a multiple of 4).
+ *
+ * @QUIRK_LITTLE_ENDIAN gives the ordering of bytes within each group of 4.
+ * If set, the most significant byte is last in the group. If @len takes the
+ * form of 4k+3, the last group will only be able to represent 24 bits, and its
+ * most significant octet is byte 2.
+ *
+ * Return: the physical offset into the buffer corresponding to the logical box.
+ */
+static size_t calculate_box_addr(size_t box, size_t len, u8 quirks)
 {
-	int closest_multiple_of_4;
+	size_t offset_of_group, offset_in_group, this_group = box / 4;
+	size_t group_size;
 
-	closest_multiple_of_4 = (offset / 4) * 4;
-	offset -= closest_multiple_of_4;
-	return closest_multiple_of_4 + (3 - offset);
+	if (quirks & QUIRK_LSW32_IS_FIRST)
+		offset_of_group = this_group * 4;
+	else
+		offset_of_group = len - ((this_group + 1) * 4);
+
+	group_size = min(4, len - offset_of_group);
+
+	if (quirks & QUIRK_LITTLE_ENDIAN)
+		offset_in_group = box - this_group * 4;
+	else
+		offset_in_group = group_size - (box - this_group * 4) - 1;
+
+	return offset_of_group + offset_in_group;
 }
 
-static int get_reverse_lsw32_offset(int offset, size_t len)
+/**
+ * pack - Pack u64 number into bitfield of buffer.
+ *
+ * @pbuf: Pointer to a buffer holding the packed value.
+ * @uval: CPU-readable unpacked value to pack.
+ * @startbit: The index (in logical notation, compensated for quirks) where
+ *	      the packed value starts within pbuf. Must be larger than, or
+ *	      equal to, endbit.
+ * @endbit: The index (in logical notation, compensated for quirks) where
+ *	    the packed value ends within pbuf. Must be smaller than, or equal
+ *	    to, startbit.
+ * @pbuflen: The length in bytes of the packed buffer pointed to by @pbuf.
+ * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and
+ *	    QUIRK_MSB_ON_THE_RIGHT.
+ *
+ * Return: 0 on success, EINVAL or ERANGE if called incorrectly. Assuming
+ *	   correct usage, return code may be discarded. The @pbuf memory will
+ *	   be modified on success.
+ */
+int pack(void *pbuf, u64 uval, size_t startbit, size_t endbit, size_t pbuflen,
+	 u8 quirks)
 {
-	int closest_multiple_of_4;
-	int word_index;
+	/* Logical byte indices corresponding to the
+	 * start and end of the field.
+	 */
+	int plogical_first_u8, plogical_last_u8, box;
+	/* width of the field to access in the pbuf */
+	u64 value_width;
 
-	word_index = offset / 4;
-	closest_multiple_of_4 = word_index * 4;
-	offset -= closest_multiple_of_4;
-	word_index = (len / 4) - word_index - 1;
-	return word_index * 4 + offset;
+	/* startbit is expected to be larger than endbit, and both are
+	 * expected to be within the logically addressable range of the buffer.
+	 */
+	if (unlikely(startbit < endbit || startbit >= BITS_PER_BYTE * pbuflen))
+		/* Invalid function call */
+		return -EINVAL;
+
+	value_width = startbit - endbit + 1;
+	if (unlikely(value_width > 64))
+		return -ERANGE;
+
+	/* Check if "uval" fits in "value_width" bits.
+	 * If value_width is 64, the check will fail, but any
+	 * 64-bit uval will surely fit.
+	 */
+	if (unlikely(value_width < 64 && uval >= (1ull << value_width)))
+		/* Cannot store "uval" inside "value_width" bits.
+		 * Truncating "uval" is most certainly not desirable,
+		 * so simply erroring out is appropriate.
+		 */
+		return -ERANGE;
+
+	/* Iterate through an idealistic view of the pbuf as an u64 with
+	 * no quirks, u8 by u8 (aligned at u8 boundaries), from high to low
+	 * logical bit significance. "box" denotes the current logical u8.
+	 */
+	plogical_first_u8 = startbit / BITS_PER_BYTE;
+	plogical_last_u8  = endbit / BITS_PER_BYTE;
+
+	for (box = plogical_first_u8; box >= plogical_last_u8; box--) {
+		/* Bit indices into the currently accessed 8-bit box */
+		size_t box_start_bit, box_end_bit, box_addr;
+		u8  box_mask;
+		/* Corresponding bits from the unpacked u64 parameter */
+		size_t proj_start_bit, proj_end_bit;
+		u64 proj_mask;
+		u64 pval;
+
+		/* This u8 may need to be accessed in its entirety
+		 * (from bit 7 to bit 0), or not, depending on the
+		 * input arguments startbit and endbit.
+		 */
+		if (box == plogical_first_u8)
+			box_start_bit = startbit % BITS_PER_BYTE;
+		else
+			box_start_bit = 7;
+		if (box == plogical_last_u8)
+			box_end_bit = endbit % BITS_PER_BYTE;
+		else
+			box_end_bit = 0;
+
+		/* We have determined the box bit start and end.
+		 * Now we calculate where this (masked) u8 box would fit
+		 * in the unpacked (CPU-readable) u64 - the u8 box's
+		 * projection onto the unpacked u64. Though the
+		 * box is u8, the projection is u64 because it may fall
+		 * anywhere within the unpacked u64.
+		 */
+		proj_start_bit = ((box * BITS_PER_BYTE) + box_start_bit) - endbit;
+		proj_end_bit = ((box * BITS_PER_BYTE) + box_end_bit) - endbit;
+		proj_mask = GENMASK_ULL(proj_start_bit, proj_end_bit);
+		box_mask = GENMASK(box_start_bit, box_end_bit);
+
+		/* Determine the offset of the u8 box inside the pbuf,
+		 * adjusted for quirks. The adjusted box_addr will be used for
+		 * effective addressing inside the pbuf (so it's not
+		 * logical any longer).
+		 */
+		box_addr = calculate_box_addr(box, pbuflen, quirks);
+
+		/* Write to pbuf, read from uval */
+		pval = uval & proj_mask;
+		pval >>= proj_end_bit;
+		pval <<= box_end_bit;
+
+		if (quirks & QUIRK_MSB_ON_THE_RIGHT) {
+			pval = bitrev8(pval);
+			box_mask = bitrev8(box_mask);
+		}
+
+		((u8 *)pbuf)[box_addr] &= ~box_mask;
+		((u8 *)pbuf)[box_addr] |= pval;
+	}
+	return 0;
 }
+EXPORT_SYMBOL(pack);
 
-static void adjust_for_msb_right_quirk(u64 *to_write, int *box_start_bit,
-				       int *box_end_bit, u8 *box_mask)
+/**
+ * unpack - Unpack u64 number from packed buffer.
+ *
+ * @pbuf: Pointer to a buffer holding the packed value.
+ * @uval: Pointer to an u64 holding the unpacked value.
+ * @startbit: The index (in logical notation, compensated for quirks) where
+ *	      the packed value starts within pbuf. Must be larger than, or
+ *	      equal to, endbit.
+ * @endbit: The index (in logical notation, compensated for quirks) where
+ *	    the packed value ends within pbuf. Must be smaller than, or equal
+ *	    to, startbit.
+ * @pbuflen: The length in bytes of the packed buffer pointed to by @pbuf.
+ * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and
+ *	    QUIRK_MSB_ON_THE_RIGHT.
+ *
+ * Return: 0 on success, EINVAL or ERANGE if called incorrectly. Assuming
+ *	   correct usage, return code may be discarded. The @uval will be
+ *	   modified on success.
+ */
+int unpack(const void *pbuf, u64 *uval, size_t startbit, size_t endbit,
+	   size_t pbuflen, u8 quirks)
 {
-	int box_bit_width = *box_start_bit - *box_end_bit + 1;
-	int new_box_start_bit, new_box_end_bit;
+	/* Logical byte indices corresponding to the
+	 * start and end of the field.
+	 */
+	int plogical_first_u8, plogical_last_u8, box;
+	/* width of the field to access in the pbuf */
+	u64 value_width;
 
-	*to_write >>= *box_end_bit;
-	*to_write = bitrev8(*to_write) >> (8 - box_bit_width);
-	*to_write <<= *box_end_bit;
+	/* startbit is expected to be larger than endbit, and both are
+	 * expected to be within the logically addressable range of the buffer.
+	 */
+	if (unlikely(startbit < endbit || startbit >= BITS_PER_BYTE * pbuflen))
+		/* Invalid function call */
+		return -EINVAL;
 
-	new_box_end_bit   = box_bit_width - *box_start_bit - 1;
-	new_box_start_bit = box_bit_width - *box_end_bit - 1;
-	*box_mask = GENMASK_ULL(new_box_start_bit, new_box_end_bit);
-	*box_start_bit = new_box_start_bit;
-	*box_end_bit   = new_box_end_bit;
+	value_width = startbit - endbit + 1;
+	if (unlikely(value_width > 64))
+		return -ERANGE;
+
+	/* Initialize parameter */
+	*uval = 0;
+
+	/* Iterate through an idealistic view of the pbuf as an u64 with
+	 * no quirks, u8 by u8 (aligned at u8 boundaries), from high to low
+	 * logical bit significance. "box" denotes the current logical u8.
+	 */
+	plogical_first_u8 = startbit / BITS_PER_BYTE;
+	plogical_last_u8  = endbit / BITS_PER_BYTE;
+
+	for (box = plogical_first_u8; box >= plogical_last_u8; box--) {
+		/* Bit indices into the currently accessed 8-bit box */
+		size_t box_start_bit, box_end_bit, box_addr;
+		u8  box_mask;
+		/* Corresponding bits from the unpacked u64 parameter */
+		size_t proj_start_bit, proj_end_bit;
+		u64 proj_mask;
+		u64 pval;
+
+		/* This u8 may need to be accessed in its entirety
+		 * (from bit 7 to bit 0), or not, depending on the
+		 * input arguments startbit and endbit.
+		 */
+		if (box == plogical_first_u8)
+			box_start_bit = startbit % BITS_PER_BYTE;
+		else
+			box_start_bit = 7;
+		if (box == plogical_last_u8)
+			box_end_bit = endbit % BITS_PER_BYTE;
+		else
+			box_end_bit = 0;
+
+		/* We have determined the box bit start and end.
+		 * Now we calculate where this (masked) u8 box would fit
+		 * in the unpacked (CPU-readable) u64 - the u8 box's
+		 * projection onto the unpacked u64. Though the
+		 * box is u8, the projection is u64 because it may fall
+		 * anywhere within the unpacked u64.
+		 */
+		proj_start_bit = ((box * BITS_PER_BYTE) + box_start_bit) - endbit;
+		proj_end_bit = ((box * BITS_PER_BYTE) + box_end_bit) - endbit;
+		proj_mask = GENMASK_ULL(proj_start_bit, proj_end_bit);
+		box_mask = GENMASK(box_start_bit, box_end_bit);
+
+		/* Determine the offset of the u8 box inside the pbuf,
+		 * adjusted for quirks. The adjusted box_addr will be used for
+		 * effective addressing inside the pbuf (so it's not
+		 * logical any longer).
+		 */
+		box_addr = calculate_box_addr(box, pbuflen, quirks);
+
+		/* Read from pbuf, write to uval */
+		pval = ((u8 *)pbuf)[box_addr];
+
+		if (quirks & QUIRK_MSB_ON_THE_RIGHT)
+			pval = bitrev8(pval);
+
+		pval &= box_mask;
+
+		pval >>= box_end_bit;
+		pval <<= proj_end_bit;
+		*uval &= ~proj_mask;
+		*uval |= pval;
+	}
+	return 0;
 }
+EXPORT_SYMBOL(unpack);
 
 /**
  * packing - Convert numbers (currently u64) between a packed and an unpacked
@@ -69,6 +297,8 @@ static void adjust_for_msb_right_quirk(u64 *to_write, int *box_start_bit,
  * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and
  *	    QUIRK_MSB_ON_THE_RIGHT.
  *
+ * Note: this is deprecated, prefer to use pack() or unpack() in new code.
+ *
  * Return: 0 on success, EINVAL or ERANGE if called incorrectly. Assuming
  *	   correct usage, return code may be discarded.
  *	   If op is PACK, pbuf is modified.
@@ -77,124 +307,10 @@ static void adjust_for_msb_right_quirk(u64 *to_write, int *box_start_bit,
 int packing(void *pbuf, u64 *uval, int startbit, int endbit, size_t pbuflen,
 	    enum packing_op op, u8 quirks)
 {
-	/* Number of bits for storing "uval"
-	 * also width of the field to access in the pbuf
-	 */
-	u64 value_width;
-	/* Logical byte indices corresponding to the
-	 * start and end of the field.
-	 */
-	int plogical_first_u8, plogical_last_u8, box;
+	if (op == PACK)
+		return pack(pbuf, *uval, startbit, endbit, pbuflen, quirks);
 
-	/* startbit is expected to be larger than endbit */
-	if (startbit < endbit)
-		/* Invalid function call */
-		return -EINVAL;
-
-	value_width = startbit - endbit + 1;
-	if (value_width > 64)
-		return -ERANGE;
-
-	/* Check if "uval" fits in "value_width" bits.
-	 * If value_width is 64, the check will fail, but any
-	 * 64-bit uval will surely fit.
-	 */
-	if (op == PACK && value_width < 64 && (*uval >= (1ull << value_width)))
-		/* Cannot store "uval" inside "value_width" bits.
-		 * Truncating "uval" is most certainly not desirable,
-		 * so simply erroring out is appropriate.
-		 */
-		return -ERANGE;
-
-	/* Initialize parameter */
-	if (op == UNPACK)
-		*uval = 0;
-
-	/* Iterate through an idealistic view of the pbuf as an u64 with
-	 * no quirks, u8 by u8 (aligned at u8 boundaries), from high to low
-	 * logical bit significance. "box" denotes the current logical u8.
-	 */
-	plogical_first_u8 = startbit / 8;
-	plogical_last_u8  = endbit / 8;
-
-	for (box = plogical_first_u8; box >= plogical_last_u8; box--) {
-		/* Bit indices into the currently accessed 8-bit box */
-		int box_start_bit, box_end_bit, box_addr;
-		u8  box_mask;
-		/* Corresponding bits from the unpacked u64 parameter */
-		int proj_start_bit, proj_end_bit;
-		u64 proj_mask;
-
-		/* This u8 may need to be accessed in its entirety
-		 * (from bit 7 to bit 0), or not, depending on the
-		 * input arguments startbit and endbit.
-		 */
-		if (box == plogical_first_u8)
-			box_start_bit = startbit % 8;
-		else
-			box_start_bit = 7;
-		if (box == plogical_last_u8)
-			box_end_bit = endbit % 8;
-		else
-			box_end_bit = 0;
-
-		/* We have determined the box bit start and end.
-		 * Now we calculate where this (masked) u8 box would fit
-		 * in the unpacked (CPU-readable) u64 - the u8 box's
-		 * projection onto the unpacked u64. Though the
-		 * box is u8, the projection is u64 because it may fall
-		 * anywhere within the unpacked u64.
-		 */
-		proj_start_bit = ((box * 8) + box_start_bit) - endbit;
-		proj_end_bit   = ((box * 8) + box_end_bit) - endbit;
-		proj_mask = GENMASK_ULL(proj_start_bit, proj_end_bit);
-		box_mask  = GENMASK_ULL(box_start_bit, box_end_bit);
-
-		/* Determine the offset of the u8 box inside the pbuf,
-		 * adjusted for quirks. The adjusted box_addr will be used for
-		 * effective addressing inside the pbuf (so it's not
-		 * logical any longer).
-		 */
-		box_addr = pbuflen - box - 1;
-		if (quirks & QUIRK_LITTLE_ENDIAN)
-			box_addr = get_le_offset(box_addr);
-		if (quirks & QUIRK_LSW32_IS_FIRST)
-			box_addr = get_reverse_lsw32_offset(box_addr,
-							    pbuflen);
-
-		if (op == UNPACK) {
-			u64 pval;
-
-			/* Read from pbuf, write to uval */
-			pval = ((u8 *)pbuf)[box_addr] & box_mask;
-			if (quirks & QUIRK_MSB_ON_THE_RIGHT)
-				adjust_for_msb_right_quirk(&pval,
-							   &box_start_bit,
-							   &box_end_bit,
-							   &box_mask);
-
-			pval >>= box_end_bit;
-			pval <<= proj_end_bit;
-			*uval &= ~proj_mask;
-			*uval |= pval;
-		} else {
-			u64 pval;
-
-			/* Write to pbuf, read from uval */
-			pval = (*uval) & proj_mask;
-			pval >>= proj_end_bit;
-			if (quirks & QUIRK_MSB_ON_THE_RIGHT)
-				adjust_for_msb_right_quirk(&pval,
-							   &box_start_bit,
-							   &box_end_bit,
-							   &box_mask);
-
-			pval <<= box_end_bit;
-			((u8 *)pbuf)[box_addr] &= ~box_mask;
-			((u8 *)pbuf)[box_addr] |= pval;
-		}
-	}
-	return 0;
+	return unpack(pbuf, uval, startbit, endbit, pbuflen, quirks);
 }
 EXPORT_SYMBOL(packing);
 
diff --git a/lib/packing_test.c b/lib/packing_test.c
new file mode 100644
index 000000000000..015ad1180d23
--- /dev/null
+++ b/lib/packing_test.c
@@ -0,0 +1,412 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2024, Vladimir Oltean <olteanv@gmail.com>
+ * Copyright (c) 2024, Intel Corporation.
+ */
+#include <kunit/test.h>
+#include <linux/packing.h>
+
+struct packing_test_case {
+	const char *desc;
+	const u8 *pbuf;
+	size_t pbuf_size;
+	u64 uval;
+	size_t start_bit;
+	size_t end_bit;
+	u8 quirks;
+};
+
+#define NO_QUIRKS	0
+
+/**
+ * PBUF - Initialize .pbuf and .pbuf_size
+ * @array: elements of constant physical buffer
+ *
+ * Initializes the .pbuf and .pbuf_size fields of a struct packing_test_case
+ * with a constant array of the specified elements.
+ */
+#define PBUF(array...)					\
+	.pbuf = (const u8[]){ array },			\
+	.pbuf_size = sizeof((const u8 []){ array })
+
+static const struct packing_test_case cases[] = {
+	/* These tests pack and unpack a magic 64-bit value
+	 * (0xcafedeadbeefcafe) at a fixed logical offset (32) within an
+	 * otherwise zero array of 128 bits (16 bytes). They test all possible
+	 * bit layouts of the 128 bit buffer.
+	 */
+	{
+		.desc = "no quirks, 16 bytes",
+		PBUF(0x00, 0x00, 0x00, 0x00, 0xca, 0xfe, 0xde, 0xad,
+		     0xbe, 0xef, 0xca, 0xfe, 0x00, 0x00, 0x00, 0x00),
+		.uval = 0xcafedeadbeefcafe,
+		.start_bit = 95,
+		.end_bit = 32,
+		.quirks = NO_QUIRKS,
+	},
+	{
+		.desc = "lsw32 first, 16 bytes",
+		PBUF(0x00, 0x00, 0x00, 0x00, 0xbe, 0xef, 0xca, 0xfe,
+		     0xca, 0xfe, 0xde, 0xad, 0x00, 0x00, 0x00, 0x00),
+		.uval = 0xcafedeadbeefcafe,
+		.start_bit = 95,
+		.end_bit = 32,
+		.quirks = QUIRK_LSW32_IS_FIRST,
+	},
+	{
+		.desc = "little endian words, 16 bytes",
+		PBUF(0x00, 0x00, 0x00, 0x00, 0xad, 0xde, 0xfe, 0xca,
+		     0xfe, 0xca, 0xef, 0xbe, 0x00, 0x00, 0x00, 0x00),
+		.uval = 0xcafedeadbeefcafe,
+		.start_bit = 95,
+		.end_bit = 32,
+		.quirks = QUIRK_LITTLE_ENDIAN,
+	},
+	{
+		.desc = "lsw32 first + little endian words, 16 bytes",
+		PBUF(0x00, 0x00, 0x00, 0x00, 0xfe, 0xca, 0xef, 0xbe,
+		     0xad, 0xde, 0xfe, 0xca, 0x00, 0x00, 0x00, 0x00),
+		.uval = 0xcafedeadbeefcafe,
+		.start_bit = 95,
+		.end_bit = 32,
+		.quirks = QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN,
+	},
+	{
+		.desc = "msb right, 16 bytes",
+		PBUF(0x00, 0x00, 0x00, 0x00, 0x53, 0x7f, 0x7b, 0xb5,
+		     0x7d, 0xf7, 0x53, 0x7f, 0x00, 0x00, 0x00, 0x00),
+		.uval = 0xcafedeadbeefcafe,
+		.start_bit = 95,
+		.end_bit = 32,
+		.quirks = QUIRK_MSB_ON_THE_RIGHT,
+	},
+	{
+		.desc = "msb right + lsw32 first, 16 bytes",
+		PBUF(0x00, 0x00, 0x00, 0x00, 0x7d, 0xf7, 0x53, 0x7f,
+		     0x53, 0x7f, 0x7b, 0xb5, 0x00, 0x00, 0x00, 0x00),
+		.uval = 0xcafedeadbeefcafe,
+		.start_bit = 95,
+		.end_bit = 32,
+		.quirks = QUIRK_MSB_ON_THE_RIGHT | QUIRK_LSW32_IS_FIRST,
+	},
+	{
+		.desc = "msb right + little endian words, 16 bytes",
+		PBUF(0x00, 0x00, 0x00, 0x00, 0xb5, 0x7b, 0x7f, 0x53,
+		     0x7f, 0x53, 0xf7, 0x7d, 0x00, 0x00, 0x00, 0x00),
+		.uval = 0xcafedeadbeefcafe,
+		.start_bit = 95,
+		.end_bit = 32,
+		.quirks = QUIRK_MSB_ON_THE_RIGHT | QUIRK_LITTLE_ENDIAN,
+	},
+	{
+		.desc = "msb right + lsw32 first + little endian words, 16 bytes",
+		PBUF(0x00, 0x00, 0x00, 0x00, 0x7f, 0x53, 0xf7, 0x7d,
+		     0xb5, 0x7b, 0x7f, 0x53, 0x00, 0x00, 0x00, 0x00),
+		.uval = 0xcafedeadbeefcafe,
+		.start_bit = 95,
+		.end_bit = 32,
+		.quirks = QUIRK_MSB_ON_THE_RIGHT | QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN,
+	},
+	/* These tests pack and unpack a magic 64-bit value
+	 * (0xcafedeadbeefcafe) at a fixed logical offset (32) within an
+	 * otherwise zero array of varying size from 18 bytes to 24 bytes.
+	 */
+	{
+		.desc = "no quirks, 18 bytes",
+		PBUF(0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xca, 0xfe,
+		     0xde, 0xad, 0xbe, 0xef, 0xca, 0xfe, 0x00, 0x00,
+		     0x00, 0x00),
+		.uval = 0xcafedeadbeefcafe,
+		.start_bit = 95,
+		.end_bit = 32,
+		.quirks = NO_QUIRKS,
+	},
+	{
+		.desc = "no quirks, 19 bytes",
+		PBUF(0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0xca,
+		     0xfe, 0xde, 0xad, 0xbe, 0xef, 0xca, 0xfe, 0x00,
+		     0x00, 0x00, 0x00),
+		.uval = 0xcafedeadbeefcafe,
+		.start_bit = 95,
+		.end_bit = 32,
+		.quirks = NO_QUIRKS,
+	},
+	{
+		.desc = "no quirks, 20 bytes",
+		PBUF(0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		     0xca, 0xfe, 0xde, 0xad, 0xbe, 0xef, 0xca, 0xfe,
+		     0x00, 0x00, 0x00, 0x00),
+		.uval = 0xcafedeadbeefcafe,
+		.start_bit = 95,
+		.end_bit = 32,
+		.quirks = NO_QUIRKS,
+	},
+	{
+		.desc = "no quirks, 22 bytes",
+		PBUF(0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		     0x00, 0x00, 0xca, 0xfe, 0xde, 0xad, 0xbe, 0xef,
+		     0xca, 0xfe, 0x00, 0x00, 0x00, 0x00),
+		.uval = 0xcafedeadbeefcafe,
+		.start_bit = 95,
+		.end_bit = 32,
+		.quirks = NO_QUIRKS,
+	},
+	{
+		.desc = "no quirks, 24 bytes",
+		PBUF(0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		     0x00, 0x00, 0x00, 0x00, 0xca, 0xfe, 0xde, 0xad,
+		     0xbe, 0xef, 0xca, 0xfe, 0x00, 0x00, 0x00, 0x00),
+		.uval = 0xcafedeadbeefcafe,
+		.start_bit = 95,
+		.end_bit = 32,
+		.quirks = NO_QUIRKS,
+	},
+	{
+		.desc = "lsw32 first + little endian words, 18 bytes",
+		PBUF(0x00, 0x00, 0x00, 0x00, 0xfe, 0xca, 0xef, 0xbe,
+		     0xad, 0xde, 0xfe, 0xca, 0x00, 0x00, 0x00, 0x00,
+		     0x00, 0x00),
+		.uval = 0xcafedeadbeefcafe,
+		.start_bit = 95,
+		.end_bit = 32,
+		.quirks = QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN,
+	},
+	{
+		.desc = "lsw32 first + little endian words, 19 bytes",
+		PBUF(0x00, 0x00, 0x00, 0x00, 0xfe, 0xca, 0xef, 0xbe,
+		     0xad, 0xde, 0xfe, 0xca, 0x00, 0x00, 0x00, 0x00,
+		     0x00, 0x00, 0x00),
+		.uval = 0xcafedeadbeefcafe,
+		.start_bit = 95,
+		.end_bit = 32,
+		.quirks = QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN,
+	},
+	{
+		.desc = "lsw32 first + little endian words, 20 bytes",
+		PBUF(0x00, 0x00, 0x00, 0x00, 0xfe, 0xca, 0xef, 0xbe,
+		     0xad, 0xde, 0xfe, 0xca, 0x00, 0x00, 0x00, 0x00,
+		     0x00, 0x00, 0x00, 0x00),
+		.uval = 0xcafedeadbeefcafe,
+		.start_bit = 95,
+		.end_bit = 32,
+		.quirks = QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN,
+	},
+	{
+		.desc = "lsw32 first + little endian words, 22 bytes",
+		PBUF(0x00, 0x00, 0x00, 0x00, 0xfe, 0xca, 0xef, 0xbe,
+		     0xad, 0xde, 0xfe, 0xca, 0x00, 0x00, 0x00, 0x00,
+		     0x00, 0x00, 0x00, 0x00, 0x00, 0x00),
+		.uval = 0xcafedeadbeefcafe,
+		.start_bit = 95,
+		.end_bit = 32,
+		.quirks = QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN,
+	},
+	{
+		.desc = "lsw32 first + little endian words, 24 bytes",
+		PBUF(0x00, 0x00, 0x00, 0x00, 0xfe, 0xca, 0xef, 0xbe,
+		     0xad, 0xde, 0xfe, 0xca, 0x00, 0x00, 0x00, 0x00,
+		     0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00),
+		.uval = 0xcafedeadbeefcafe,
+		.start_bit = 95,
+		.end_bit = 32,
+		.quirks = QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN,
+	},
+	/* These tests pack and unpack a magic 64-bit value
+	 * (0x1122334455667788) at an odd starting bit (43) within an
+	 * otherwise zero array of 128 bits (16 bytes). They test all possible
+	 * bit layouts of the 128 bit buffer.
+	 */
+	{
+		.desc = "no quirks, 16 bytes, non-aligned",
+		PBUF(0x00, 0x00, 0x00, 0x89, 0x11, 0x9a, 0x22, 0xab,
+		     0x33, 0xbc, 0x40, 0x00, 0x00, 0x00, 0x00, 0x00),
+		.uval = 0x1122334455667788,
+		.start_bit = 106,
+		.end_bit = 43,
+		.quirks = NO_QUIRKS,
+	},
+	{
+		.desc = "lsw32 first, 16 bytes, non-aligned",
+		PBUF(0x00, 0x00, 0x00, 0x00, 0x33, 0xbc, 0x40, 0x00,
+		     0x11, 0x9a, 0x22, 0xab, 0x00, 0x00, 0x00, 0x89),
+		.uval = 0x1122334455667788,
+		.start_bit = 106,
+		.end_bit = 43,
+		.quirks = QUIRK_LSW32_IS_FIRST,
+	},
+	{
+		.desc = "little endian words, 16 bytes, non-aligned",
+		PBUF(0x89, 0x00, 0x00, 0x00, 0xab, 0x22, 0x9a, 0x11,
+		     0x00, 0x40, 0xbc, 0x33, 0x00, 0x00, 0x00, 0x00),
+		.uval = 0x1122334455667788,
+		.start_bit = 106,
+		.end_bit = 43,
+		.quirks = QUIRK_LITTLE_ENDIAN,
+	},
+	{
+		.desc = "lsw32 first + little endian words, 16 bytes, non-aligned",
+		PBUF(0x00, 0x00, 0x00, 0x00, 0x00, 0x40, 0xbc, 0x33,
+		     0xab, 0x22, 0x9a, 0x11, 0x89, 0x00, 0x00, 0x00),
+		.uval = 0x1122334455667788,
+		.start_bit = 106,
+		.end_bit = 43,
+		.quirks = QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN,
+	},
+	{
+		.desc = "msb right, 16 bytes, non-aligned",
+		PBUF(0x00, 0x00, 0x00, 0x91, 0x88, 0x59, 0x44, 0xd5,
+		     0xcc, 0x3d, 0x02, 0x00, 0x00, 0x00, 0x00, 0x00),
+		.uval = 0x1122334455667788,
+		.start_bit = 106,
+		.end_bit = 43,
+		.quirks = QUIRK_MSB_ON_THE_RIGHT,
+	},
+	{
+		.desc = "msb right + lsw32 first, 16 bytes, non-aligned",
+		PBUF(0x00, 0x00, 0x00, 0x00, 0xcc, 0x3d, 0x02, 0x00,
+		     0x88, 0x59, 0x44, 0xd5, 0x00, 0x00, 0x00, 0x91),
+		.uval = 0x1122334455667788,
+		.start_bit = 106,
+		.end_bit = 43,
+		.quirks = QUIRK_MSB_ON_THE_RIGHT | QUIRK_LSW32_IS_FIRST,
+	},
+	{
+		.desc = "msb right + little endian words, 16 bytes, non-aligned",
+		PBUF(0x91, 0x00, 0x00, 0x00, 0xd5, 0x44, 0x59, 0x88,
+		     0x00, 0x02, 0x3d, 0xcc, 0x00, 0x00, 0x00, 0x00),
+		.uval = 0x1122334455667788,
+		.start_bit = 106,
+		.end_bit = 43,
+		.quirks = QUIRK_MSB_ON_THE_RIGHT | QUIRK_LITTLE_ENDIAN,
+	},
+	{
+		.desc = "msb right + lsw32 first + little endian words, 16 bytes, non-aligned",
+		PBUF(0x00, 0x00, 0x00, 0x00, 0x00, 0x02, 0x3d, 0xcc,
+		     0xd5, 0x44, 0x59, 0x88, 0x91, 0x00, 0x00, 0x00),
+		.uval = 0x1122334455667788,
+		.start_bit = 106,
+		.end_bit = 43,
+		.quirks = QUIRK_MSB_ON_THE_RIGHT | QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN,
+	},
+	/* These tests pack and unpack a u64 with all bits set
+	 * (0xffffffffffffffff) at an odd starting bit (43) within an
+	 * otherwise zero array of 128 bits (16 bytes). They test all possible
+	 * bit layouts of the 128 bit buffer.
+	 */
+	{
+		.desc = "no quirks, 16 bytes, non-aligned, 0xff",
+		PBUF(0x00, 0x00, 0x07, 0xff, 0xff, 0xff, 0xff, 0xff,
+		     0xff, 0xff, 0xf8, 0x00, 0x00, 0x00, 0x00, 0x00),
+		.uval = 0xffffffffffffffff,
+		.start_bit = 106,
+		.end_bit = 43,
+		.quirks = NO_QUIRKS,
+	},
+	{
+		.desc = "lsw32 first, 16 bytes, non-aligned, 0xff",
+		PBUF(0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0xf8, 0x00,
+		     0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0x07, 0xff),
+		.uval = 0xffffffffffffffff,
+		.start_bit = 106,
+		.end_bit = 43,
+		.quirks = QUIRK_LSW32_IS_FIRST,
+	},
+	{
+		.desc = "little endian words, 16 bytes, non-aligned, 0xff",
+		PBUF(0xff, 0x07, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+		     0x00, 0xf8, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00),
+		.uval = 0xffffffffffffffff,
+		.start_bit = 106,
+		.end_bit = 43,
+		.quirks = QUIRK_LITTLE_ENDIAN,
+	},
+	{
+		.desc = "lsw32 first + little endian words, 16 bytes, non-aligned, 0xff",
+		PBUF(0x00, 0x00, 0x00, 0x00, 0x00, 0xf8, 0xff, 0xff,
+		     0xff, 0xff, 0xff, 0xff, 0xff, 0x07, 0x00, 0x00),
+		.uval = 0xffffffffffffffff,
+		.start_bit = 106,
+		.end_bit = 43,
+		.quirks = QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN,
+	},
+	{
+		.desc = "msb right, 16 bytes, non-aligned, 0xff",
+		PBUF(0x00, 0x00, 0xe0, 0xff, 0xff, 0xff, 0xff, 0xff,
+		     0xff, 0xff, 0x1f, 0x00, 0x00, 0x00, 0x00, 0x00),
+		.uval = 0xffffffffffffffff,
+		.start_bit = 106,
+		.end_bit = 43,
+		.quirks = QUIRK_MSB_ON_THE_RIGHT,
+	},
+	{
+		.desc = "msb right + lsw32 first, 16 bytes, non-aligned, 0xff",
+		PBUF(0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0x1f, 0x00,
+		     0xff, 0xff, 0xff, 0xff, 0x00, 0x00, 0xe0, 0xff),
+		.uval = 0xffffffffffffffff,
+		.start_bit = 106,
+		.end_bit = 43,
+		.quirks = QUIRK_MSB_ON_THE_RIGHT | QUIRK_LSW32_IS_FIRST,
+	},
+	{
+		.desc = "msb right + little endian words, 16 bytes, non-aligned, 0xff",
+		PBUF(0xff, 0xe0, 0x00, 0x00, 0xff, 0xff, 0xff, 0xff,
+		     0x00, 0x1f, 0xff, 0xff, 0x00, 0x00, 0x00, 0x00),
+		.uval = 0xffffffffffffffff,
+		.start_bit = 106,
+		.end_bit = 43,
+		.quirks = QUIRK_MSB_ON_THE_RIGHT | QUIRK_LITTLE_ENDIAN,
+	},
+	{
+		.desc = "msb right + lsw32 first + little endian words, 16 bytes, non-aligned, 0xff",
+		PBUF(0x00, 0x00, 0x00, 0x00, 0x00, 0x1f, 0xff, 0xff,
+		     0xff, 0xff, 0xff, 0xff, 0xff, 0xe0, 0x00, 0x00),
+		.uval = 0xffffffffffffffff,
+		.start_bit = 106,
+		.end_bit = 43,
+		.quirks = QUIRK_MSB_ON_THE_RIGHT | QUIRK_LSW32_IS_FIRST | QUIRK_LITTLE_ENDIAN,
+	},
+};
+
+KUNIT_ARRAY_PARAM_DESC(packing, cases, desc);
+
+static void packing_test_pack(struct kunit *test)
+{
+	const struct packing_test_case *params = test->param_value;
+	u8 *pbuf;
+	int err;
+
+	pbuf = kunit_kzalloc(test, params->pbuf_size, GFP_KERNEL);
+
+	err = pack(pbuf, params->uval, params->start_bit, params->end_bit,
+		   params->pbuf_size, params->quirks);
+
+	KUNIT_EXPECT_EQ_MSG(test, err, 0, "pack() returned %pe\n", ERR_PTR(err));
+	KUNIT_EXPECT_MEMEQ(test, pbuf, params->pbuf, params->pbuf_size);
+}
+
+static void packing_test_unpack(struct kunit *test)
+{
+	const struct packing_test_case *params = test->param_value;
+	u64 uval;
+	int err;
+
+	err = unpack(params->pbuf, &uval, params->start_bit, params->end_bit,
+		     params->pbuf_size, params->quirks);
+	KUNIT_EXPECT_EQ_MSG(test, err, 0, "unpack() returned %pe\n", ERR_PTR(err));
+	KUNIT_EXPECT_EQ(test, uval, params->uval);
+}
+
+static struct kunit_case packing_test_cases[] = {
+	KUNIT_CASE_PARAM(packing_test_pack, packing_gen_params),
+	KUNIT_CASE_PARAM(packing_test_unpack, packing_gen_params),
+	{},
+};
+
+static struct kunit_suite packing_test_suite = {
+	.name = "packing",
+	.test_cases = packing_test_cases,
+};
+
+kunit_test_suite(packing_test_suite);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("KUnit tests for packing library");