Re: [PATCH 07/39] x86/entry/32: Enter the kernel via trampoline stack

[Brian Gerst]

On Wed, Jul 18, 2018 at 5:41 AM Joerg Roedel <joro@xxxxxxxxxx> wrote:
>
> From: Joerg Roedel <jroedel@xxxxxxx>
>
> Use the entry-stack as a trampoline to enter the kernel. The
> entry-stack is already in the cpu_entry_area and will be
> mapped to userspace when PTI is enabled.
>
> Signed-off-by: Joerg Roedel <jroedel@xxxxxxx>
> ---
>  arch/x86/entry/entry_32.S        | 119 ++++++++++++++++++++++++++++++++-------
>  arch/x86/include/asm/switch_to.h |  14 ++++-
>  arch/x86/kernel/asm-offsets.c    |   1 +
>  arch/x86/kernel/cpu/common.c     |   5 +-
>  arch/x86/kernel/process.c        |   2 -
>  arch/x86/kernel/process_32.c     |   2 -
>  6 files changed, 115 insertions(+), 28 deletions(-)
>
> diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
> index 7251c4f..fea49ec 100644
> --- a/arch/x86/entry/entry_32.S
> +++ b/arch/x86/entry/entry_32.S
> @@ -154,7 +154,7 @@
>
>  #endif /* CONFIG_X86_32_LAZY_GS */
>
> -.macro SAVE_ALL pt_regs_ax=%eax
> +.macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0
>         cld
>         PUSH_GS
>         pushl   %fs
> @@ -173,6 +173,12 @@
>         movl    $(__KERNEL_PERCPU), %edx
>         movl    %edx, %fs
>         SET_KERNEL_GS %edx
> +
> +       /* Switch to kernel stack if necessary */
> +.if \switch_stacks > 0
> +       SWITCH_TO_KERNEL_STACK
> +.endif
> +
>  .endm
>
>  /*
> @@ -269,6 +275,73 @@
>  .Lend_\@:
>  #endif /* CONFIG_X86_ESPFIX32 */
>  .endm
> +
> +
> +/*
> + * Called with pt_regs fully populated and kernel segments loaded,
> + * so we can access PER_CPU and use the integer registers.
> + *
> + * We need to be very careful here with the %esp switch, because an NMI
> + * can happen everywhere. If the NMI handler finds itself on the
> + * entry-stack, it will overwrite the task-stack and everything we
> + * copied there. So allocate the stack-frame on the task-stack and
> + * switch to it before we do any copying.
> + */
> +.macro SWITCH_TO_KERNEL_STACK
> +
> +       ALTERNATIVE     "", "jmp .Lend_\@", X86_FEATURE_XENPV
> +
> +       /* Are we on the entry stack? Bail out if not! */
> +       movl    PER_CPU_VAR(cpu_entry_area), %ecx
> +       addl    $CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
> +       subl    %esp, %ecx      /* ecx = (end of entry_stack) - esp */
> +       cmpl    $SIZEOF_entry_stack, %ecx
> +       jae     .Lend_\@
> +
> +       /* Load stack pointer into %esi and %edi */
> +       movl    %esp, %esi
> +       movl    %esi, %edi
> +
> +       /* Move %edi to the top of the entry stack */
> +       andl    $(MASK_entry_stack), %edi
> +       addl    $(SIZEOF_entry_stack), %edi
> +
> +       /* Load top of task-stack into %edi */
> +       movl    TSS_entry2task_stack(%edi), %edi
> +
> +       /* Bytes to copy */
> +       movl    $PTREGS_SIZE, %ecx
> +
> +#ifdef CONFIG_VM86
> +       testl   $X86_EFLAGS_VM, PT_EFLAGS(%esi)
> +       jz      .Lcopy_pt_regs_\@
> +
> +       /*
> +        * Stack-frame contains 4 additional segment registers when
> +        * coming from VM86 mode
> +        */
> +       addl    $(4 * 4), %ecx
> +
> +.Lcopy_pt_regs_\@:
> +#endif
> +
> +       /* Allocate frame on task-stack */
> +       subl    %ecx, %edi
> +
> +       /* Switch to task-stack */
> +       movl    %edi, %esp
> +
> +       /*
> +        * We are now on the task-stack and can safely copy over the
> +        * stack-frame
> +        */
> +       shrl    $2, %ecx

This shift can be removed if you divide the constants by 4 above.
Ditto on the exit path in the next patch.

--
Brian Gerst