Re: [patch 13/16] x86/ldt: Introduce LDT write fault handler

[Andy Lutomirski]

On Tue, Dec 12, 2017 at 9:32 AM, Thomas Gleixner <tglx@xxxxxxxxxxxxx> wrote:
> From: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
>
> When the LDT is mapped RO, the CPU will write fault the first time it uses
> a segment descriptor in order to set the ACCESS bit (for some reason it
> doesn't always observe that it already preset). Catch the fault and set the
> ACCESS bit in the handler.
>
> Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
> ---
>  arch/x86/include/asm/mmu_context.h |    7 +++++++
>  arch/x86/kernel/ldt.c              |   30 ++++++++++++++++++++++++++++++
>  arch/x86/mm/fault.c                |   19 +++++++++++++++++++
>  3 files changed, 56 insertions(+)
>
> --- a/arch/x86/include/asm/mmu_context.h
> +++ b/arch/x86/include/asm/mmu_context.h
> @@ -76,6 +76,11 @@ static inline void init_new_context_ldt(
>  int ldt_dup_context(struct mm_struct *oldmm, struct mm_struct *mm);
>  void ldt_exit_user(struct pt_regs *regs);
>  void destroy_context_ldt(struct mm_struct *mm);
> +bool __ldt_write_fault(unsigned long address);
> +static inline bool ldt_is_active(struct mm_struct *mm)
> +{
> +       return mm && mm->context.ldt != NULL;
> +}
>  #else  /* CONFIG_MODIFY_LDT_SYSCALL */
>  static inline void init_new_context_ldt(struct task_struct *task,
>                                         struct mm_struct *mm) { }
> @@ -86,6 +91,8 @@ static inline int ldt_dup_context(struct
>  }
>  static inline void ldt_exit_user(struct pt_regs *regs) { }
>  static inline void destroy_context_ldt(struct mm_struct *mm) { }
> +static inline bool __ldt_write_fault(unsigned long address) { return false; }
> +static inline bool ldt_is_active(struct mm_struct *mm)  { return false; }
>  #endif
>
>  static inline void load_mm_ldt(struct mm_struct *mm, struct task_struct *tsk)
> --- a/arch/x86/kernel/ldt.c
> +++ b/arch/x86/kernel/ldt.c
> @@ -82,6 +82,36 @@ static void ldt_install_mm(struct mm_str
>         mutex_unlock(&mm->context.lock);
>  }
>
> +/*
> + * ldt_write_fault() already checked whether there is an ldt installed in
> + * __do_page_fault(), so it's safe to access it here because interrupts are
> + * disabled and any ipi which would change it is blocked until this
> + * returns.  The underlying page mapping cannot change as long as the ldt
> + * is the active one in the context.
> + *
> + * The fault error code is X86_PF_WRITE | X86_PF_PROT and checked in
> + * __do_page_fault() already. This happens when a segment is selected and
> + * the CPU tries to set the accessed bit in desc_struct.type because the
> + * LDT entries are mapped RO. Set it manually.
> + */
> +bool __ldt_write_fault(unsigned long address)
> +{
> +       struct ldt_struct *ldt = current->mm->context.ldt;
> +       unsigned long start, end, entry;
> +       struct desc_struct *desc;
> +
> +       start = (unsigned long) ldt->entries;
> +       end = start + ldt->nr_entries * LDT_ENTRY_SIZE;
> +
> +       if (address < start || address >= end)
> +               return false;
> +
> +       desc = (struct desc_struct *) ldt->entries;
> +       entry = (address - start) / LDT_ENTRY_SIZE;
> +       desc[entry].type |= 0x01;

You have another patch that unconditionally sets the accessed bit on
installation.  What gives?

Also, this patch is going to die a horrible death if IRET ever hits
this condition.  Or load gs.