diff --git a/xen/arch/arm/arm32/head.S b/xen/arch/arm/arm32/head.S
index f3f1ccce58..999233452d 100644
--- a/xen/arch/arm/arm32/head.S
+++ b/xen/arch/arm/arm32/head.S
@@ -149,7 +149,6 @@ past_zImage:
         mov   r12, #0                /* r12 := is_secondary_cpu */
 
         bl    check_cpu_mode
-        bl    zero_bss
         bl    cpu_init
         bl    create_page_tables
         bl    enable_mmu
@@ -163,6 +162,7 @@ primary_switched:
         /* Use a virtual address to access the UART. */
         mov_w r11, EARLY_UART_VIRTUAL_ADDRESS
 #endif
+        bl    zero_bss
         PRINT("- Ready -\r\n")
         /* Setup the arguments for start_xen and jump to C world */
         mov   r0, r10                /* r0 := Physical offset */
@@ -273,17 +273,12 @@ ENDPROC(check_cpu_mode)
 /*
  * Zero BSS
  *
- * Inputs:
- *   r10: Physical offset
- *
  * Clobbers r0 - r3
  */
 zero_bss:
         PRINT("- Zero BSS -\r\n")
-        ldr   r0, =__bss_start       /* Load start & end of bss */
-        ldr   r1, =__bss_end
-        add   r0, r0, r10            /* Apply physical offset */
-        add   r1, r1, r10
+        ldr   r0, =__bss_start       /* r0 := vaddr(__bss_start) */
+        ldr   r1, =__bss_end         /* r1 := vaddr(__bss_start) */
 
         mov   r2, #0
 1:      str   r2, [r0], #4
diff --git a/xen/arch/arm/arm64/head.S b/xen/arch/arm/arm64/head.S
index 790b485f04..ba24b05fa2 100644
--- a/xen/arch/arm/arm64/head.S
+++ b/xen/arch/arm/arm64/head.S
@@ -304,7 +304,6 @@ real_start_efi:
         mov   x22, #0                /* x22 := is_secondary_cpu */
 
         bl    check_cpu_mode
-        bl    zero_bss
         bl    cpu_init
         bl    create_page_tables
         bl    enable_mmu
@@ -318,6 +317,7 @@ primary_switched:
         /* Use a virtual address to access the UART. */
         ldr   x23, =EARLY_UART_VIRTUAL_ADDRESS
 #endif
+        bl    zero_bss
         PRINT("- Ready -\r\n")
         /* Setup the arguments for start_xen and jump to C world */
         mov   x0, x20                /* x0 := Physical offset */
@@ -420,7 +420,6 @@ ENDPROC(check_cpu_mode)
  * Zero BSS
  *
  * Inputs:
- *   x20: Physical offset
  *   x26: Do we need to zero BSS?
  *
  * Clobbers x0 - x3
@@ -430,8 +429,8 @@ zero_bss:
         cbnz  x26, skip_bss
 
         PRINT("- Zero BSS -\r\n")
-        load_paddr x0, __bss_start    /* Load paddr of start & end of bss */
-        load_paddr x1, __bss_end
+        ldr   x0, =__bss_start       /* x0 := vaddr(__bss_start) */
+        ldr   x1, =__bss_end         /* x1 := vaddr(__bss_start) */
 
 1:      str   xzr, [x0], #8
         cmp   x0, x1
diff --git a/xen/arch/arm/mm.c b/xen/arch/arm/mm.c
index e1cdeaaf2f..65552da4ba 100644
--- a/xen/arch/arm/mm.c
+++ b/xen/arch/arm/mm.c
@@ -62,6 +62,17 @@ mm_printk(const char *fmt, ...) {}
     } while (0);
 #endif
 
+/*
+ * Macros to define page-tables:
+ *  - DEFINE_BOOT_PAGE_TABLE is used to define page-table that are used
+ *  in assembly code before BSS is zeroed.
+ *  - DEFINE_PAGE_TABLE{,S} are used to define one or multiple
+ *  page-tables to be used after BSS is zeroed (typically they are only used
+ *  in C).
+ */
+#define DEFINE_BOOT_PAGE_TABLE(name)                                          \
+lpae_t __aligned(PAGE_SIZE) __section(".data.page_aligned") name[LPAE_ENTRIES]
+
 #define DEFINE_PAGE_TABLES(name, nr)                    \
 lpae_t __aligned(PAGE_SIZE) name[LPAE_ENTRIES * (nr)]
 
@@ -90,13 +101,13 @@ lpae_t __aligned(PAGE_SIZE) name[LPAE_ENTRIES * (nr)]
  * Finally, if EARLY_PRINTK is enabled then xen_fixmap will be mapped
  * by the CPU once it has moved off the 1:1 mapping.
  */
-DEFINE_PAGE_TABLE(boot_pgtable);
+DEFINE_BOOT_PAGE_TABLE(boot_pgtable);
 #ifdef CONFIG_ARM_64
-DEFINE_PAGE_TABLE(boot_first);
-DEFINE_PAGE_TABLE(boot_first_id);
+DEFINE_BOOT_PAGE_TABLE(boot_first);
+DEFINE_BOOT_PAGE_TABLE(boot_first_id);
 #endif
-DEFINE_PAGE_TABLE(boot_second);
-DEFINE_PAGE_TABLE(boot_third);
+DEFINE_BOOT_PAGE_TABLE(boot_second);
+DEFINE_BOOT_PAGE_TABLE(boot_third);
 
 /* Main runtime page tables */
 
@@ -149,7 +160,7 @@ static __initdata int xenheap_first_first_slot = -1;
  */
 static DEFINE_PAGE_TABLES(xen_second, 2);
 /* First level page table used for fixmap */
-DEFINE_PAGE_TABLE(xen_fixmap);
+DEFINE_BOOT_PAGE_TABLE(xen_fixmap);
 /* First level page table used to map Xen itself with the XN bit set
  * as appropriate. */
 static DEFINE_PAGE_TABLE(xen_xenmap);