Re: [PATCH] riscv: fix race when vmap stack overflow

[Guo Ren]

On Wed, Oct 19, 2022 at 11:57 PM Jisheng Zhang <jszhang@xxxxxxxxxx> wrote:
>
> Currently, when detecting vmap stack overflow, riscv firstly switches
> to the so called shadow stack, then use this shadow stack to call the
> get_overflow_stack() to get the overflow stack. However, there's
> a race here if two or more harts use the same shadow stack at the same
> time.
>
> To solve this race, we introduce spin_shadow_stack atomic var, which
> will make the shadow stack usage serialized.
>
> Fixes: 31da94c25aea ("riscv: add VMAP_STACK overflow detection")
> Signed-off-by: Jisheng Zhang <jszhang@xxxxxxxxxx>
> Suggested-by: Guo Ren <guoren@xxxxxxxxxx>
> ---
>  arch/riscv/kernel/entry.S | 4 ++++
>  arch/riscv/kernel/traps.c | 4 ++++
>  2 files changed, 8 insertions(+)
>
> diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
> index b9eda3fcbd6d..7b924b16792b 100644
> --- a/arch/riscv/kernel/entry.S
> +++ b/arch/riscv/kernel/entry.S
> @@ -404,6 +404,10 @@ handle_syscall_trace_exit:
>
>  #ifdef CONFIG_VMAP_STACK
>  handle_kernel_stack_overflow:
> +1:     la sp, spin_shadow_stack
> +       amoswap.w sp, sp, (sp)
If CONFIG_64BIT=y, it would be broken. Because we only hold 32bit of
the sp, and the next loop would get the wrong sp value of
&spin_shadow_stack.
Here is the correction.
-----
diff --git a/arch/riscv/include/asm/asm.h b/arch/riscv/include/asm/asm.h
index 1b471ff73178..acf563072b8b 100644
--- a/arch/riscv/include/asm/asm.h
+++ b/arch/riscv/include/asm/asm.h
@@ -23,6 +23,7 @@
 #define REG_L          __REG_SEL(ld, lw)
 #define REG_S          __REG_SEL(sd, sw)
 #define REG_SC         __REG_SEL(sc.d, sc.w)
+#define REG_AMOSWAP    __REG_SEL(amoswap.d, amoswap.w)
 #define REG_ASM                __REG_SEL(.dword, .word)
 #define SZREG          __REG_SEL(8, 4)
 #define LGREG          __REG_SEL(3, 2)
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index b9eda3fcbd6d..ea6b78dac739 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -404,6 +404,10 @@ handle_syscall_trace_exit:

 #ifdef CONFIG_VMAP_STACK
 handle_kernel_stack_overflow:
+1:     la sp, spin_shadow_stack
+       /* Reuse the address as the spin value, so they must be all
XLEN's width. */
+       REG_AMOSWAP sp, sp, (sp)
+       bnez sp, 1b
+
        la sp, shadow_stack
        addi sp, sp, SHADOW_OVERFLOW_STACK_SIZE

diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
index f3e96d60a2ff..9e6cc0d63833 100644
--- a/arch/riscv/kernel/traps.c
+++ b/arch/riscv/kernel/traps.c
@@ -221,11 +221,15 @@ asmlinkage unsigned long get_overflow_stack(void)
                OVERFLOW_STACK_SIZE;
 }

+unsigned long spin_shadow_stack = 0;
+
 asmlinkage void handle_bad_stack(struct pt_regs *regs)
 {
        unsigned long tsk_stk = (unsigned long)current->stack;
        unsigned long ovf_stk = (unsigned long)this_cpu_ptr(overflow_stack);

+       smp_store_release(&spin_shadow_stack, 0);
+
        console_verbose();

        pr_emerg("Insufficient stack space to handle exception!\n");

> +       bnez sp, 1b
> +
>         la sp, shadow_stack
>         addi sp, sp, SHADOW_OVERFLOW_STACK_SIZE
>
> diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
> index f3e96d60a2ff..88a54947dffb 100644
> --- a/arch/riscv/kernel/traps.c
> +++ b/arch/riscv/kernel/traps.c
> @@ -221,11 +221,15 @@ asmlinkage unsigned long get_overflow_stack(void)
>                 OVERFLOW_STACK_SIZE;
>  }
>
> +atomic_t spin_shadow_stack;
> +
>  asmlinkage void handle_bad_stack(struct pt_regs *regs)
>  {
>         unsigned long tsk_stk = (unsigned long)current->stack;
>         unsigned long ovf_stk = (unsigned long)this_cpu_ptr(overflow_stack);
>
> +       atomic_set_release(&spin_shadow_stack, 0);
> +
>         console_verbose();
>
>         pr_emerg("Insufficient stack space to handle exception!\n");
> --
> 2.37.2
>
--
Best Regards
 Guo Ren