diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 9fdde2f9cc0f..eb54c0289c8a 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -122,29 +122,6 @@ SYM_CODE_START_LOCAL(preserve_boot_args)
 	b	dcache_inval_poc		// tail call
 SYM_CODE_END(preserve_boot_args)
 
-/*
- * Macro to create a table entry to the next page.
- *
- *	tbl:	page table address
- *	virt:	virtual address
- *	shift:	#imm page table shift
- *	ptrs:	#imm pointers per table page
- *
- * Preserves:	virt
- * Corrupts:	ptrs, tmp1, tmp2
- * Returns:	tbl -> next level table page address
- */
-	.macro	create_table_entry, tbl, virt, shift, ptrs, tmp1, tmp2
-	add	\tmp1, \tbl, #PAGE_SIZE
-	phys_to_pte \tmp2, \tmp1
-	orr	\tmp2, \tmp2, #PMD_TYPE_TABLE	// address of next table and entry type
-	lsr	\tmp1, \virt, #\shift
-	sub	\ptrs, \ptrs, #1
-	and	\tmp1, \tmp1, \ptrs		// table index
-	str	\tmp2, [\tbl, \tmp1, lsl #3]
-	add	\tbl, \tbl, #PAGE_SIZE		// next level table page
-	.endm
-
 /*
  * Macro to populate page table entries, these entries can be pointers to the next level
  * or last level entries pointing to physical memory.
@@ -209,15 +186,27 @@ SYM_CODE_END(preserve_boot_args)
  *	phys:	physical address corresponding to vstart - physical memory is contiguous
  *	order:  #imm 2log(number of entries in PGD table)
  *
+ * If extra_shift is set, an extra level will be populated if the end address does
+ * not fit in 'extra_shift' bits. This assumes vend is in the TTBR0 range.
+ *
  * Temporaries:	istart, iend, tmp, count, sv - these need to be different registers
  * Preserves:	vstart, flags
  * Corrupts:	tbl, rtbl, vend, istart, iend, tmp, count, sv
  */
-	.macro map_memory, tbl, rtbl, vstart, vend, flags, phys, order, istart, iend, tmp, count, sv
+	.macro map_memory, tbl, rtbl, vstart, vend, flags, phys, order, istart, iend, tmp, count, sv, extra_shift
 	sub \vend, \vend, #1
 	add \rtbl, \tbl, #PAGE_SIZE
 	mov \count, #0
 
+	.ifnb	\extra_shift
+	tst	\vend, #~((1 << (\extra_shift)) - 1)
+	b.eq	.L_\@
+	compute_indices \vstart, \vend, #\extra_shift, #(PAGE_SHIFT - 3), \istart, \iend, \count
+	mov \sv, \rtbl
+	populate_entries \tbl, \rtbl, \istart, \iend, #PMD_TYPE_TABLE, #PAGE_SIZE, \tmp
+	mov \tbl, \sv
+	.endif
+.L_\@:
 	compute_indices \vstart, \vend, #PGDIR_SHIFT, #\order, \istart, \iend, \count
 	mov \sv, \rtbl
 	populate_entries \tbl, \rtbl, \istart, \iend, #PMD_TYPE_TABLE, #PAGE_SIZE, \tmp
@@ -284,20 +273,32 @@ SYM_FUNC_START_LOCAL(__create_page_tables)
 	adrp	x3, __idmap_text_start		// __pa(__idmap_text_start)
 
 	/*
-	 * VA_BITS may be too small to allow for an ID mapping to be created
-	 * that covers system RAM if that is located sufficiently high in the
-	 * physical address space. So for the ID map, use an extended virtual
-	 * range in that case, and configure an additional translation level
-	 * if needed.
+	 * The ID map carries a 1:1 mapping of the physical address range
+	 * covered by the loaded image, which could be anywhere in DRAM. This
+	 * means that the required size of the VA (== PA) space is decided at
+	 * boot time, and could be more than the configured size of the VA
+	 * space for ordinary kernel and user space mappings.
+	 *
+	 * There are three cases to consider here:
+	 * - 39 <= VA_BITS < 48, and the ID map needs up to 48 VA bits to cover
+	 *   the placement of the image. In this case, we configure one extra
+	 *   level of translation on the fly for the ID map only. (This case
+	 *   also covers 42-bit VA/52-bit PA on 64k pages).
+	 *
+	 * - VA_BITS == 48, and the ID map needs more than 48 VA bits. This can
+	 *   only happen when using 64k pages, in which case we need to extend
+	 *   the root level table rather than add a level. Note that we can
+	 *   treat this case as 'always extended' as long as we take care not
+	 *   to program an unsupported T0SZ value into the TCR register.
+	 *
+	 * - Combinations that would require two additional levels of
+	 *   translation are not supported, e.g., VA_BITS==36 on 16k pages, or
+	 *   VA_BITS==39/4k pages with 5-level paging, where the input address
+	 *   requires more than 47 or 48 bits, respectively.
 	 */
-	idmap_get_t0sz x5
-	cmp	x5, TCR_T0SZ(VA_BITS_MIN) // default T0SZ small enough?
-	b.ge	1f			// .. then skip VA range extension
-
 #if (VA_BITS < 48)
 #define IDMAP_PGD_ORDER	(VA_BITS - PGDIR_SHIFT)
 #define EXTRA_SHIFT	(PGDIR_SHIFT + PAGE_SHIFT - 3)
-#define EXTRA_PTRS	(1 << (PHYS_MASK_SHIFT - EXTRA_SHIFT))
 
 	/*
 	 * If VA_BITS < 48, we have to configure an additional table level.
@@ -309,20 +310,17 @@ SYM_FUNC_START_LOCAL(__create_page_tables)
 #if VA_BITS != EXTRA_SHIFT
 #error "Mismatch between VA_BITS and page size/number of translation levels"
 #endif
-
-	mov	x2, EXTRA_PTRS
-	create_table_entry x0, x3, EXTRA_SHIFT, x2, x5, x6
 #else
 #define IDMAP_PGD_ORDER	(PHYS_MASK_SHIFT - PGDIR_SHIFT)
+#define EXTRA_SHIFT
 	/*
 	 * If VA_BITS == 48, we don't have to configure an additional
 	 * translation level, but the top-level table has more entries.
 	 */
 #endif
-1:
 	adr_l	x6, __idmap_text_end		// __pa(__idmap_text_end)
 
-	map_memory x0, x1, x3, x6, x7, x3, IDMAP_PGD_ORDER, x10, x11, x12, x13, x14
+	map_memory x0, x1, x3, x6, x7, x3, IDMAP_PGD_ORDER, x10, x11, x12, x13, x14, EXTRA_SHIFT
 
 	/*
 	 * Map the kernel image (starting with PHYS_OFFSET).