x86/boot: Size the boot/directmap mappings dynamically

... rather than presuming that 16M will do.  On the EFI side, use
l2e_add_flags() to reduce the code-generation overhead of using
l2e_from_paddr() twice.

Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>

xen/arch/x86/boot/head.S

@@ -687,14 +687,19 @@ trampoline_setup:
          * handling/walking), and identity map Xen into bootmap (needed for
          * the transition into long mode), using 2M superpages.
          */
-        lea     sym_esi(start),%ebx
-        lea     (1<<L2_PAGETABLE_SHIFT)*7+(PAGE_HYPERVISOR_RWX|_PAGE_PSE)(%ebx),%eax
-        shr     $(L2_PAGETABLE_SHIFT-3),%ebx
-        mov     $8,%ecx
-1:      mov     %eax,sym_fs(l2_bootmap)-8(%ebx,%ecx,8)
-        mov     %eax,sym_fs(l2_directmap)-8(%ebx,%ecx,8)
-        sub     $(1<<L2_PAGETABLE_SHIFT),%eax
-        loop    1b
+        lea     sym_esi(_start), %ecx
+        lea     -1 + sym_esi(_end), %edx
+        lea     _PAGE_PSE + PAGE_HYPERVISOR_RWX(%ecx), %eax /* PTE to write. */
+        shr     $L2_PAGETABLE_SHIFT, %ecx                   /* First slot to write. */
+        shr     $L2_PAGETABLE_SHIFT, %edx                   /* Final slot to write. */
+
+1:      mov     %eax, sym_offs(l2_bootmap)  (%esi, %ecx, 8)
+        mov     %eax, sym_offs(l2_directmap)(%esi, %ecx, 8)
+        add     $1, %ecx
+        add     $1 << L2_PAGETABLE_SHIFT, %eax
+
+        cmp     %edx, %ecx
+        jbe     1b
 
         /* Initialize L3 boot-map page directory entries. */
         lea     __PAGE_HYPERVISOR+(L2_PAGETABLE_ENTRIES*8)*3+sym_esi(l2_bootmap),%eax

xen/arch/x86/efi/efi-boot.h

@@ -611,15 +611,28 @@ static void __init efi_arch_memory_setup(void)
      * Map Xen into the directmap (needed for early-boot pagetable
      * handling/walking), and identity map Xen into bootmap (needed for the
      * transition from the EFI pagetables to Xen), using 2M superpages.
+     *
+     * NB: We are currently in physical mode, so a RIP-relative relocation
+     * against _start/_end gets their real position in memory, which are the
+     * appropriate l2 slots to map.
      */
-    for ( i = 0; i < 8; ++i )
-    {
-        unsigned int slot = (xen_phys_start >> L2_PAGETABLE_SHIFT) + i;
-        paddr_t addr = slot << L2_PAGETABLE_SHIFT;
+#define l2_4G_offset(a)                                                 \
+    (((UINTN)(a) >> L2_PAGETABLE_SHIFT) & (4 * L2_PAGETABLE_ENTRIES - 1))
 
-        l2_directmap[slot] = l2e_from_paddr(addr, PAGE_HYPERVISOR|_PAGE_PSE);
-        l2_bootmap[slot] = l2e_from_paddr(addr, __PAGE_HYPERVISOR|_PAGE_PSE);
+    for ( i  = l2_4G_offset(_start);
+          i <= l2_4G_offset(_end - 1); ++i )
+    {
+        l2_pgentry_t pte = l2e_from_paddr(i << L2_PAGETABLE_SHIFT,
+                                          __PAGE_HYPERVISOR | _PAGE_PSE);
+
+        l2_bootmap[i] = pte;
+
+        /* Bootmap RWX/Non-global.  Directmap RW/Global. */
+        l2e_add_flags(pte, PAGE_HYPERVISOR);
+
+        l2_directmap[i] = pte;
     }
+#undef l2_4G_offset
 }
 
 static void __init efi_arch_handle_module(struct file *file, const CHAR16 *name,