On Fri, Jul 28, 2023 at 11:09:05AM +0200, Ard Biesheuvel wrote:
> The 32-bit trampoline no longer uses the stack for anything except
> performing a far return back to long mode. Currently, this stack is
> placed in the same page that carries the trampoline code, which means
> this page must be mapped writable and executable, and the stack is
> therefore executable as well.
>
> Replace the far return with a far jump, so that the return address can
> be pre-calculated and patched into the code before it is called. This
> removes the need for a stack entirely, and in a later patch, this will
> be taken advantage of by removing writable permissions from (and adding
> executable permissions to) this code page explicitly when booting via
> the EFI stub.
>
> Not touching the stack pointer also makes it more straight-forward to
> call the trampoline code as an ordinary 64-bit function from C code.
>
> Note that we need to preserve the value of RSP across the switch into
^^
Passive voice pls.
> compatibility mode: the stack pointer may get truncated to 32 bits.
>
> Acked-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
> Signed-off-by: Ard Biesheuvel <ardb@xxxxxxxxxx>
> ---
> arch/x86/boot/compressed/head_64.S | 64 ++++++++++----------
> arch/x86/boot/compressed/pgtable.h | 4 +-
> arch/x86/boot/compressed/pgtable_64.c | 12 +++-
> 3 files changed, 44 insertions(+), 36 deletions(-)
>
> diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
> index 491d985be75fd5b0..1b0c61d1b389fd37 100644
> --- a/arch/x86/boot/compressed/head_64.S
> +++ b/arch/x86/boot/compressed/head_64.S
> @@ -449,9 +449,6 @@ SYM_CODE_START(startup_64)
> leaq TRAMPOLINE_32BIT_CODE_OFFSET(%rax), %rax
> call *%rax
>
> - /* Restore the stack, the 32-bit trampoline uses its own stack */
> - leaq rva(boot_stack_end)(%rbx), %rsp
> -
> /*
> * cleanup_trampoline() would restore trampoline memory.
> *
> @@ -537,32 +534,37 @@ SYM_FUNC_END(.Lrelocated)
> * EDI contains the base address of the trampoline memory.
> * Non-zero ESI means trampoline needs to enable 5-level paging.
> */
> + .section ".rodata", "a", @progbits
> SYM_CODE_START(trampoline_32bit_src)
> - /* Grab return address */
> - movq (%rsp), %rax
> -
> - /* Set up 32-bit addressable stack */
> - leaq TRAMPOLINE_32BIT_STACK_END(%rdi), %rsp
> -
> - /* Preserve return address and other live 64-bit registers */
> - pushq %rax
> + /* Preserve live 64-bit registers */
> pushq %r15
> pushq %rbp
> pushq %rbx
>
> + /* Preserve top half of RSP in a legacy mode GPR to avoid truncation */
> + movq %rsp, %rbx
> + shrq $32, %rbx
> +
> /* Switch to compatibility mode (CS.L = 0 CS.D = 1) via far return */
> pushq $__KERNEL32_CS
> leaq 0f(%rip), %rax
> pushq %rax
> lretq
>
> + /*
> + * The 32-bit code below will do a far jump back to long mode and end
> + * up here after reconfiguring the number of paging levels.
> + */
> +.Lret: shlq $32, %rbx // Reconstruct stack pointer
No side comments pls.
--
Regards/Gruss,
Boris.
https://people.kernel.org/tglx/notes-about-netiquette
