diff --git a/drivers/iommu/iommufd/iommufd_test.h b/drivers/iommu/iommufd/iommufd_test.h
index 9817edcd8968..1f2e93d3d4e8 100644
--- a/drivers/iommu/iommufd/iommufd_test.h
+++ b/drivers/iommu/iommufd/iommufd_test.h
@@ -20,6 +20,7 @@ enum {
 	IOMMU_TEST_OP_MOCK_DOMAIN_REPLACE,
 	IOMMU_TEST_OP_ACCESS_REPLACE_IOAS,
 	IOMMU_TEST_OP_MOCK_DOMAIN_FLAGS,
+	IOMMU_TEST_OP_DIRTY,
 };
 
 enum {
@@ -107,6 +108,14 @@ struct iommu_test_cmd {
 		struct {
 			__u32 ioas_id;
 		} access_replace_ioas;
+		struct {
+			__u32 flags;
+			__aligned_u64 iova;
+			__aligned_u64 length;
+			__aligned_u64 page_size;
+			__aligned_u64 uptr;
+			__aligned_u64 out_nr_dirty;
+		} dirty;
 	};
 	__u32 last;
 };
diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c
index 2773275566af..4eb86025dde9 100644
--- a/drivers/iommu/iommufd/selftest.c
+++ b/drivers/iommu/iommufd/selftest.c
@@ -37,6 +37,7 @@ enum {
 	_MOCK_PFN_START = MOCK_PFN_MASK + 1,
 	MOCK_PFN_START_IOVA = _MOCK_PFN_START,
 	MOCK_PFN_LAST_IOVA = _MOCK_PFN_START,
+	MOCK_PFN_DIRTY_IOVA = _MOCK_PFN_START << 1,
 };
 
 /*
@@ -179,6 +180,31 @@ static int mock_domain_read_and_clear_dirty(struct iommu_domain *domain,
 					    unsigned long flags,
 					    struct iommu_dirty_bitmap *dirty)
 {
+	struct mock_iommu_domain *mock =
+		container_of(domain, struct mock_iommu_domain, domain);
+	unsigned long i, max = size / MOCK_IO_PAGE_SIZE;
+	void *ent, *old;
+
+	if (!(mock->flags & MOCK_DIRTY_TRACK) && dirty->bitmap)
+		return -EINVAL;
+
+	for (i = 0; i < max; i++) {
+		unsigned long cur = iova + i * MOCK_IO_PAGE_SIZE;
+
+		ent = xa_load(&mock->pfns, cur / MOCK_IO_PAGE_SIZE);
+		if (ent && (xa_to_value(ent) & MOCK_PFN_DIRTY_IOVA)) {
+			unsigned long val;
+
+			/* Clear dirty */
+			val = xa_to_value(ent) & ~MOCK_PFN_DIRTY_IOVA;
+			old = xa_store(&mock->pfns, cur / MOCK_IO_PAGE_SIZE,
+				       xa_mk_value(val), GFP_KERNEL);
+			WARN_ON_ONCE(ent != old);
+			iommu_dirty_bitmap_record(dirty, cur,
+						  MOCK_IO_PAGE_SIZE);
+		}
+	}
+
 	return 0;
 }
 
@@ -310,7 +336,7 @@ static size_t mock_domain_unmap_pages(struct iommu_domain *domain,
 
 		for (cur = 0; cur != pgsize; cur += MOCK_IO_PAGE_SIZE) {
 			ent = xa_erase(&mock->pfns, iova / MOCK_IO_PAGE_SIZE);
-			WARN_ON(!ent);
+
 			/*
 			 * iommufd generates unmaps that must be a strict
 			 * superset of the map's performend So every starting
@@ -320,13 +346,13 @@ static size_t mock_domain_unmap_pages(struct iommu_domain *domain,
 			 * passed to map_pages
 			 */
 			if (first) {
-				WARN_ON(!(xa_to_value(ent) &
-					  MOCK_PFN_START_IOVA));
+				WARN_ON(ent && !(xa_to_value(ent) &
+						 MOCK_PFN_START_IOVA));
 				first = false;
 			}
 			if (pgcount == 1 && cur + MOCK_IO_PAGE_SIZE == pgsize)
-				WARN_ON(!(xa_to_value(ent) &
-					  MOCK_PFN_LAST_IOVA));
+				WARN_ON(ent && !(xa_to_value(ent) &
+						 MOCK_PFN_LAST_IOVA));
 
 			iova += MOCK_IO_PAGE_SIZE;
 			ret += MOCK_IO_PAGE_SIZE;
@@ -1053,6 +1079,71 @@ static_assert((unsigned int)MOCK_ACCESS_RW_WRITE == IOMMUFD_ACCESS_RW_WRITE);
 static_assert((unsigned int)MOCK_ACCESS_RW_SLOW_PATH ==
 	      __IOMMUFD_ACCESS_RW_SLOW_PATH);
 
+static int iommufd_test_dirty(struct iommufd_ucmd *ucmd, unsigned int mockpt_id,
+			      unsigned long iova, size_t length,
+			      unsigned long page_size, void __user *uptr,
+			      u32 flags)
+{
+	unsigned long bitmap_size, i, max = length / page_size;
+	struct iommu_test_cmd *cmd = ucmd->cmd;
+	struct iommufd_hw_pagetable *hwpt;
+	struct mock_iommu_domain *mock;
+	int rc, count = 0;
+	void *tmp;
+
+	if (iova % page_size || length % page_size || !uptr)
+		return -EINVAL;
+
+	hwpt = get_md_pagetable(ucmd, mockpt_id, &mock);
+	if (IS_ERR(hwpt))
+		return PTR_ERR(hwpt);
+
+	if (!(mock->flags & MOCK_DIRTY_TRACK)) {
+		rc = -EINVAL;
+		goto out_put;
+	}
+
+	bitmap_size = max / BITS_PER_BYTE;
+
+	tmp = kvzalloc(bitmap_size, GFP_KERNEL_ACCOUNT);
+	if (!tmp) {
+		rc = -ENOMEM;
+		goto out_put;
+	}
+
+	if (copy_from_user(tmp, uptr, bitmap_size)) {
+		rc = -EFAULT;
+		goto out_free;
+	}
+
+	for (i = 0; i < max; i++) {
+		unsigned long cur = iova + i * page_size;
+		void *ent, *old;
+
+		if (!test_bit(i, (unsigned long *)tmp))
+			continue;
+
+		ent = xa_load(&mock->pfns, cur / page_size);
+		if (ent) {
+			unsigned long val;
+
+			val = xa_to_value(ent) | MOCK_PFN_DIRTY_IOVA;
+			old = xa_store(&mock->pfns, cur / page_size,
+				       xa_mk_value(val), GFP_KERNEL);
+			WARN_ON_ONCE(ent != old);
+			count++;
+		}
+	}
+
+	cmd->dirty.out_nr_dirty = count;
+	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
+out_free:
+	kvfree(tmp);
+out_put:
+	iommufd_put_object(&hwpt->obj);
+	return rc;
+}
+
 void iommufd_selftest_destroy(struct iommufd_object *obj)
 {
 	struct selftest_obj *sobj = container_of(obj, struct selftest_obj, obj);
@@ -1118,6 +1209,12 @@ int iommufd_test(struct iommufd_ucmd *ucmd)
 			return -EINVAL;
 		iommufd_test_memory_limit = cmd->memory_limit.limit;
 		return 0;
+	case IOMMU_TEST_OP_DIRTY:
+		return iommufd_test_dirty(ucmd, cmd->id, cmd->dirty.iova,
+					  cmd->dirty.length,
+					  cmd->dirty.page_size,
+					  u64_to_user_ptr(cmd->dirty.uptr),
+					  cmd->dirty.flags);
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c
index 8c46012006e1..891250acf47e 100644
--- a/tools/testing/selftests/iommu/iommufd.c
+++ b/tools/testing/selftests/iommu/iommufd.c
@@ -1440,13 +1440,47 @@ FIXTURE(iommufd_dirty_tracking)
 	uint32_t hwpt_id;
 	uint32_t stdev_id;
 	uint32_t idev_id;
+	unsigned long page_size;
+	unsigned long bitmap_size;
+	void *bitmap;
+	void *buffer;
+};
+
+FIXTURE_VARIANT(iommufd_dirty_tracking)
+{
+	unsigned long buffer_size;
 };
 
 FIXTURE_SETUP(iommufd_dirty_tracking)
 {
+	void *vrc;
+	int rc;
+
 	self->fd = open("/dev/iommu", O_RDWR);
 	ASSERT_NE(-1, self->fd);
 
+	rc = posix_memalign(&self->buffer, HUGEPAGE_SIZE, variant->buffer_size);
+	if (rc || !self->buffer) {
+		SKIP(return, "Skipping buffer_size=%lu due to errno=%d",
+			   variant->buffer_size, rc);
+	}
+
+	assert((uintptr_t)self->buffer % HUGEPAGE_SIZE == 0);
+	vrc = mmap(self->buffer, variant->buffer_size, PROT_READ | PROT_WRITE,
+		   MAP_SHARED | MAP_ANONYMOUS | MAP_FIXED, -1, 0);
+	assert(vrc == self->buffer);
+
+	self->page_size = MOCK_PAGE_SIZE;
+	self->bitmap_size =
+		variant->buffer_size / self->page_size / BITS_PER_BYTE;
+
+	/* Provision with an extra (MOCK_PAGE_SIZE) for the unaligned case */
+	rc = posix_memalign(&self->bitmap, PAGE_SIZE,
+			    self->bitmap_size + MOCK_PAGE_SIZE);
+	assert(!rc);
+	assert(self->bitmap);
+	assert((uintptr_t)self->bitmap % PAGE_SIZE == 0);
+
 	test_ioctl_ioas_alloc(&self->ioas_id);
 	test_cmd_mock_domain(self->ioas_id, &self->stdev_id, &self->hwpt_id,
 			     &self->idev_id);
@@ -1454,9 +1488,41 @@ FIXTURE_SETUP(iommufd_dirty_tracking)
 
 FIXTURE_TEARDOWN(iommufd_dirty_tracking)
 {
+	munmap(self->buffer, variant->buffer_size);
+	munmap(self->bitmap, self->bitmap_size);
 	teardown_iommufd(self->fd, _metadata);
 }
 
+FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty128k)
+{
+	/* one u32 index bitmap */
+	.buffer_size = 128UL * 1024UL,
+};
+
+FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty256k)
+{
+	/* one u64 index bitmap */
+	.buffer_size = 256UL * 1024UL,
+};
+
+FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty640k)
+{
+	/* two u64 index and trailing end bitmap */
+	.buffer_size = 640UL * 1024UL,
+};
+
+FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty128M)
+{
+	/* 4K bitmap (128M IOVA range) */
+	.buffer_size = 128UL * 1024UL * 1024UL,
+};
+
+FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty256M)
+{
+	/* 8K bitmap (256M IOVA range) */
+	.buffer_size = 256UL * 1024UL * 1024UL,
+};
+
 TEST_F(iommufd_dirty_tracking, enforce_dirty)
 {
 	uint32_t ioas_id, stddev_id, idev_id;
@@ -1497,6 +1563,36 @@ TEST_F(iommufd_dirty_tracking, set_dirty_tracking)
 	test_ioctl_destroy(hwpt_id);
 }
 
+TEST_F(iommufd_dirty_tracking, get_dirty_bitmap)
+{
+	uint32_t stddev_id;
+	uint32_t hwpt_id;
+	uint32_t ioas_id;
+
+	test_ioctl_ioas_alloc(&ioas_id);
+	test_ioctl_ioas_map_fixed_id(ioas_id, self->buffer,
+				     variant->buffer_size, MOCK_APERTURE_START);
+
+	test_cmd_hwpt_alloc(self->idev_id, ioas_id,
+			    IOMMU_HWPT_ALLOC_DIRTY_TRACKING, &hwpt_id);
+	test_cmd_mock_domain(hwpt_id, &stddev_id, NULL, NULL);
+
+	test_cmd_set_dirty_tracking(hwpt_id, true);
+
+	test_mock_dirty_bitmaps(hwpt_id, variant->buffer_size,
+				MOCK_APERTURE_START, self->page_size,
+				self->bitmap, self->bitmap_size, _metadata);
+
+	/* PAGE_SIZE unaligned bitmap */
+	test_mock_dirty_bitmaps(hwpt_id, variant->buffer_size,
+				MOCK_APERTURE_START, self->page_size,
+				self->bitmap + MOCK_PAGE_SIZE,
+				self->bitmap_size, _metadata);
+
+	test_ioctl_destroy(stddev_id);
+	test_ioctl_destroy(hwpt_id);
+}
+
 /* VFIO compatibility IOCTLs */
 
 TEST_F(iommufd, simple_ioctls)
diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h
index e37af6291b22..b129cf23b824 100644
--- a/tools/testing/selftests/iommu/iommufd_utils.h
+++ b/tools/testing/selftests/iommu/iommufd_utils.h
@@ -16,6 +16,25 @@
 /* Hack to make assertions more readable */
 #define _IOMMU_TEST_CMD(x) IOMMU_TEST_CMD
 
+/* Imported from include/asm-generic/bitops/generic-non-atomic.h */
+#define BITS_PER_BYTE 8
+#define BITS_PER_LONG __BITS_PER_LONG
+#define BIT_MASK(nr) (1UL << ((nr) % __BITS_PER_LONG))
+#define BIT_WORD(nr) ((nr) / __BITS_PER_LONG)
+
+static inline void set_bit(unsigned int nr, unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+
+	*p |= mask;
+}
+
+static inline bool test_bit(unsigned int nr, unsigned long *addr)
+{
+	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG - 1)));
+}
+
 static void *buffer;
 static unsigned long BUFFER_SIZE;
 
@@ -196,6 +215,103 @@ static int _test_cmd_set_dirty_tracking(int fd, __u32 hwpt_id, bool enabled)
 #define test_cmd_set_dirty_tracking(hwpt_id, enabled) \
 	ASSERT_EQ(0, _test_cmd_set_dirty_tracking(self->fd, hwpt_id, enabled))
 
+static int _test_cmd_get_dirty_bitmap(int fd, __u32 hwpt_id, size_t length,
+				      __u64 iova, size_t page_size,
+				      __u64 *bitmap)
+{
+	struct iommu_hwpt_get_dirty_bitmap cmd = {
+		.size = sizeof(cmd),
+		.hwpt_id = hwpt_id,
+		.iova = iova,
+		.length = length,
+		.page_size = page_size,
+		.data = (uintptr_t)bitmap,
+	};
+	int ret;
+
+	ret = ioctl(fd, IOMMU_HWPT_GET_DIRTY_BITMAP, &cmd);
+	if (ret)
+		return ret;
+	return 0;
+}
+
+#define test_cmd_get_dirty_bitmap(fd, hwpt_id, length, iova, page_size,    \
+				  bitmap)                                  \
+	ASSERT_EQ(0, _test_cmd_get_dirty_bitmap(fd, hwpt_id, length, iova, \
+						page_size, bitmap))
+
+static int _test_cmd_mock_domain_set_dirty(int fd, __u32 hwpt_id, size_t length,
+					   __u64 iova, size_t page_size,
+					   __u64 *bitmap, __u64 *dirty)
+{
+	struct iommu_test_cmd cmd = {
+		.size = sizeof(cmd),
+		.op = IOMMU_TEST_OP_DIRTY,
+		.id = hwpt_id,
+		.dirty = {
+			.iova = iova,
+			.length = length,
+			.page_size = page_size,
+			.uptr = (uintptr_t)bitmap,
+		}
+	};
+	int ret;
+
+	ret = ioctl(fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_DIRTY), &cmd);
+	if (ret)
+		return -ret;
+	if (dirty)
+		*dirty = cmd.dirty.out_nr_dirty;
+	return 0;
+}
+
+#define test_cmd_mock_domain_set_dirty(fd, hwpt_id, length, iova, page_size, \
+				       bitmap, nr)                           \
+	ASSERT_EQ(0,                                                         \
+		  _test_cmd_mock_domain_set_dirty(fd, hwpt_id, length, iova, \
+						  page_size, bitmap, nr))
+
+static int _test_mock_dirty_bitmaps(int fd, __u32 hwpt_id, size_t length,
+				    __u64 iova, size_t page_size, __u64 *bitmap,
+				    __u64 bitmap_size,
+				    struct __test_metadata *_metadata)
+{
+	unsigned long i, count, nbits = bitmap_size * BITS_PER_BYTE;
+	unsigned long nr = nbits / 2;
+	__u64 out_dirty = 0;
+
+	/* Mark all even bits as dirty in the mock domain */
+	for (count = 0, i = 0; i < nbits; count += !(i % 2), i++)
+		if (!(i % 2))
+			set_bit(i, (unsigned long *)bitmap);
+	ASSERT_EQ(nr, count);
+
+	test_cmd_mock_domain_set_dirty(fd, hwpt_id, length, iova, page_size,
+				       bitmap, &out_dirty);
+	ASSERT_EQ(nr, out_dirty);
+
+	/* Expect all even bits as dirty in the user bitmap */
+	memset(bitmap, 0, bitmap_size);
+	test_cmd_get_dirty_bitmap(fd, hwpt_id, length, iova, page_size, bitmap);
+	for (count = 0, i = 0; i < nbits; count += !(i % 2), i++)
+		ASSERT_EQ(!(i % 2), test_bit(i, (unsigned long *)bitmap));
+	ASSERT_EQ(count, out_dirty);
+
+	memset(bitmap, 0, bitmap_size);
+	test_cmd_get_dirty_bitmap(fd, hwpt_id, length, iova, page_size, bitmap);
+
+	/* It as read already -- expect all zeroes */
+	for (i = 0; i < nbits; i++)
+		ASSERT_EQ(0, test_bit(i, (unsigned long *)bitmap));
+
+	return 0;
+}
+#define test_mock_dirty_bitmaps(hwpt_id, length, iova, page_size, bitmap,      \
+				bitmap_size, _metadata)                        \
+	ASSERT_EQ(0, _test_mock_dirty_bitmaps(self->fd, hwpt_id, length, iova, \
+					      page_size, bitmap, bitmap_size,  \
+					      _metadata))
+
 static int _test_cmd_create_access(int fd, unsigned int ioas_id,
 				   __u32 *access_id, unsigned int flags)
 {
@@ -320,6 +436,17 @@ static int _test_ioctl_ioas_map(int fd, unsigned int ioas_id, void *buffer,
 					     IOMMU_IOAS_MAP_READABLE));       \
 	})
 
+#define test_ioctl_ioas_map_fixed_id(ioas_id, buffer, length, iova)           \
+	({                                                                    \
+		__u64 __iova = iova;                                          \
+		ASSERT_EQ(0,                                                  \
+			  _test_ioctl_ioas_map(                               \
+				  self->fd, ioas_id, buffer, length, &__iova, \
+				  IOMMU_IOAS_MAP_FIXED_IOVA |                 \
+					  IOMMU_IOAS_MAP_WRITEABLE |          \
+					  IOMMU_IOAS_MAP_READABLE));          \
+	})
+
 #define test_err_ioctl_ioas_map_fixed(_errno, buffer, length, iova)           \
 	({                                                                    \
 		__u64 __iova = iova;                                          \