lkml.org 
[lkml]   [2020]   [Nov]   [9]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    Patch in this message
    /
    From
    Subject[RFC][PATCH 14/24] x86/pti: Use PTI stack instead of trampoline stack
    Date
    When entering the kernel from userland, use the per-task PTI stack
    instead of the per-cpu trampoline stack. Like the trampoline stack,
    the PTI stack is mapped both in the kernel and in the user page-table.
    Using a per-task stack which is mapped into the kernel and the user
    page-table instead of a per-cpu stack will allow executing more code
    before switching to the kernel stack and to the kernel page-table.

    Additional changes will be made to later to switch to the kernel stack
    (which is only mapped in the kernel page-table).

    Signed-off-by: Alexandre Chartre <alexandre.chartre@oracle.com>
    ---
    arch/x86/entry/entry_64.S | 42 +++++++++-----------------------
    arch/x86/include/asm/pti.h | 8 ++++++
    arch/x86/include/asm/switch_to.h | 7 +++++-
    3 files changed, 26 insertions(+), 31 deletions(-)

    diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
    index 458af12ed9a1..29beab46bedd 100644
    --- a/arch/x86/entry/entry_64.S
    +++ b/arch/x86/entry/entry_64.S
    @@ -194,19 +194,9 @@ syscall_return_via_sysret:
    /* rcx and r11 are already restored (see code above) */
    POP_REGS pop_rdi=0 skip_r11rcx=1

    - /*
    - * Now all regs are restored except RSP and RDI.
    - * Save old stack pointer and switch to trampoline stack.
    - */
    - movq %rsp, %rdi
    - movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp
    - UNWIND_HINT_EMPTY
    -
    - pushq RSP-RDI(%rdi) /* RSP */
    - pushq (%rdi) /* RDI */
    -
    /*
    * We are on the trampoline stack. All regs except RDI are live.
    + * We are on the trampoline stack. All regs except RSP are live.
    * We can do future final exit work right here.
    */
    STACKLEAK_ERASE_NOCLOBBER
    @@ -214,7 +204,7 @@ syscall_return_via_sysret:
    SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi

    popq %rdi
    - popq %rsp
    + movq RSP-ORIG_RAX(%rsp), %rsp
    USERGS_SYSRET64
    SYM_CODE_END(entry_SYSCALL_64)

    @@ -606,24 +596,6 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
    #endif
    POP_REGS pop_rdi=0

    - /*
    - * The stack is now user RDI, orig_ax, RIP, CS, EFLAGS, RSP, SS.
    - * Save old stack pointer and switch to trampoline stack.
    - */
    - movq %rsp, %rdi
    - movq PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp
    - UNWIND_HINT_EMPTY
    -
    - /* Copy the IRET frame to the trampoline stack. */
    - pushq 6*8(%rdi) /* SS */
    - pushq 5*8(%rdi) /* RSP */
    - pushq 4*8(%rdi) /* EFLAGS */
    - pushq 3*8(%rdi) /* CS */
    - pushq 2*8(%rdi) /* RIP */
    -
    - /* Push user RDI on the trampoline stack. */
    - pushq (%rdi)
    -
    /*
    * We are on the trampoline stack. All regs except RDI are live.
    * We can do future final exit work right here.
    @@ -634,6 +606,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)

    /* Restore RDI. */
    popq %rdi
    + addq $8, %rsp /* skip regs->orig_ax */
    SWAPGS
    INTERRUPT_RETURN

    @@ -1062,6 +1035,15 @@ SYM_CODE_START_LOCAL(error_entry)
    SWITCH_TO_KERNEL_CR3 scratch_reg=%rax

    .Lerror_entry_from_usermode_after_swapgs:
    + /*
    + * We are on the trampoline stack. With PTI, the trampoline
    + * stack is a per-thread stack so we are all set and we can
    + * return.
    + *
    + * Without PTI, the trampoline stack is a per-cpu stack and
    + * we need to switch to the normal thread stack.
    + */
    + ALTERNATIVE "", "ret", X86_FEATURE_PTI
    /* Put us onto the real thread stack. */
    popq %r12 /* save return addr in %12 */
    movq %rsp, %rdi /* arg0 = pt_regs pointer */
    diff --git a/arch/x86/include/asm/pti.h b/arch/x86/include/asm/pti.h
    index 5484e69ff8d3..ed211fcc3a50 100644
    --- a/arch/x86/include/asm/pti.h
    +++ b/arch/x86/include/asm/pti.h
    @@ -17,8 +17,16 @@ extern void pti_check_boottime_disable(void);
    extern void pti_finalize(void);
    extern void pti_clone_pgtable(struct mm_struct *mm, unsigned long start,
    unsigned long end, enum pti_clone_level level);
    +static inline bool pti_enabled(void)
    +{
    + return static_cpu_has(X86_FEATURE_PTI);
    +}
    #else
    static inline void pti_check_boottime_disable(void) { }
    +static inline bool pti_enabled(void)
    +{
    + return false;
    +}
    #endif

    #endif /* __ASSEMBLY__ */
    diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
    index 9f69cc497f4b..457458228462 100644
    --- a/arch/x86/include/asm/switch_to.h
    +++ b/arch/x86/include/asm/switch_to.h
    @@ -3,6 +3,7 @@
    #define _ASM_X86_SWITCH_TO_H

    #include <linux/sched/task_stack.h>
    +#include <asm/pti.h>

    struct task_struct; /* one of the stranger aspects of C forward declarations */

    @@ -76,8 +77,12 @@ static inline void update_task_stack(struct task_struct *task)
    * doesn't work on x86-32 because sp1 and
    * cpu_current_top_of_stack have different values (because of
    * the non-zero stack-padding on 32bit).
    + *
    + * If PTI is enabled, sp0 points to the PTI stack (mapped in
    + * the kernel and user page-table) which is used when entering
    + * the kernel.
    */
    - if (static_cpu_has(X86_FEATURE_XENPV))
    + if (static_cpu_has(X86_FEATURE_XENPV) || pti_enabled())
    load_sp0(task_top_of_stack(task));
    #endif
    }
    --
    2.18.4
    \
     
     \ /
      Last update: 2020-11-09 12:23    [W:4.769 / U:0.176 seconds]
    ©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site