On 30.09.2024 14:06, Andrew Cooper wrote: > --- a/xen/arch/x86/boot/head.S > +++ b/xen/arch/x86/boot/head.S > @@ -344,6 +344,66 @@ __efi64_mb2_start: > lea .Lmb2_no_ih(%rip),%r15 > jz x86_32_switch > > + push %rax > + push %rcx > + push %rdx > + push %rsi > + push %rdi > + > + /* Merge lower half of EFI pagtables with upper half of Xen > pagetables */ > + mov %cr3, %rsi > + lea efi_l4_bootmap(%rip), %rdi > + mov $L4_PAGETABLE_ENTRIES / 2, %ecx > + rep movsq > + lea ((L4_PAGETABLE_ENTRIES / 2) * 8) + idle_pg_table(%rip), %rsi > + mov $L4_PAGETABLE_ENTRIES / 2, %ecx > + rep movsq > + > + /* Switch to merged pagetables */ > + lea efi_l4_bootmap(%rip), %rax > + mov %rax, %cr3
While it may appear to work in some environments, I don't think we're allowed to replace page tables prior to calling ExitBootServices(). IOW we may not complain if somewhere this fails to work. This also builds on the assumption that no new L4 entries would be made by firmware, nor that it would put anything in the upper half of the L4 table. > + lea __image_base__(%rip), %esi > + > + /* Map Xen into the higher mappings using 2M superpages. */ > + lea _PAGE_PSE + PAGE_HYPERVISOR_RWX + sym_esi(_start), %eax I'm surprised to see you put in place new RWX mappings, when the goal supposedly is to get rid of any such. > + mov $sym_offs(_start), %ecx /* %eax = PTE to write ^ */ > + mov $sym_offs(_end - 1), %edx > + shr $L2_PAGETABLE_SHIFT, %ecx /* %ecx = First slot to write */ > + shr $L2_PAGETABLE_SHIFT, %edx /* %edx = Final slot to write */ > + > +1: mov %eax, sym_offs(l2_xenmap)(%esi, %ecx, 8) > + add $1, %ecx > + add $1 << L2_PAGETABLE_SHIFT, %eax > + > + cmp %edx, %ecx > + jbe 1b > + > + /* > + * Map Xen into the directmap (needed for early-boot pagetable > + * handling/walking), and identity map Xen into bootmap (needed for > + * the transition into long mode), using 2M superpages. > + */ > + 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 > + > + pop %rdi > + pop %rsi > + pop %rdx > + pop %rcx > + pop %rax > + > /* Save Multiboot2 magic on the stack. */ > push %rax > > @@ -354,8 +414,15 @@ __efi64_mb2_start: > * efi_multiboot2() is called according to System V AMD64 ABI: > * - IN: %rdi - EFI ImageHandle, %rsi - EFI SystemTable, > * %rdx - MB2 cmdline > + * > + * Call via the high mappings > */ > - call efi_multiboot2 > + lea __image_base__(%rip), %r10 > + lea efi_multiboot2(%rip), %rax > + sub %r10, %rax > + mov $__XEN_VIRT_START, %r10 > + addq %r10, %rax > + call *%rax While with this you arrange for all %rip-relative addressing to result in using the linked-at positions, static pointers requiring base relocations will still point at the loaded-at locations. Things would get particularly interesting if the difference of two such (dissimilar) pointers would then be calculated. Jan
