Unverified Commit 7e186433 authored by Jisheng Zhang's avatar Jisheng Zhang Committed by Palmer Dabbelt
Browse files

riscv: fix race when vmap stack overflow 



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 be swap between its own address and 0 in atomic way, when the
var is set, it means the shadow_stack is being used; when the var
is cleared, it means the shadow_stack isn't being used.

Fixes: 31da94c2 ("riscv: add VMAP_STACK overflow detection")
Signed-off-by: default avatarJisheng Zhang <jszhang@kernel.org>
Suggested-by: default avatarGuo Ren <guoren@kernel.org>
Reviewed-by: default avatarGuo Ren <guoren@kernel.org>
Link: https://lore.kernel.org/r/20221030124517.2370-1-jszhang@kernel.org


[Palmer: Add AQ to the swap, and also some comments.]
Signed-off-by: default avatarPalmer Dabbelt <palmer@rivosinc.com>
parent 31da94c2

arch/riscv/include/asm/asm.h

+1 −0
Original line number Diff line number Diff line
@@ -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_AQ	__REG_SEL(amoswap.d.aq, amoswap.w.aq)

#define REG_ASM		__REG_SEL(.dword, .word)

#define SZREG		__REG_SEL(8, 4)

#define LGREG		__REG_SEL(3, 2)

arch/riscv/kernel/entry.S

+13 −0
Original line number Diff line number Diff line
@@ -387,6 +387,19 @@ handle_syscall_trace_exit: 


#ifdef CONFIG_VMAP_STACK

handle_kernel_stack_overflow:

	/*

	 * Takes the psuedo-spinlock for the shadow stack, in case multiple

	 * harts are concurrently overflowing their kernel stacks.  We could

	 * store any value here, but since we're overflowing the kernel stack

	 * already we only have SP to use as a scratch register.  So we just

	 * swap in the address of the spinlock, as that's definately non-zero.

	 *

	 * Pairs with a store_release in handle_bad_stack().

	 */

1:	la sp, spin_shadow_stack

	REG_AMOSWAP_AQ sp, sp, (sp)

	bnez sp, 1b



	la sp, shadow_stack

	addi sp, sp, SHADOW_OVERFLOW_STACK_SIZE

arch/riscv/kernel/traps.c

+18 −0
Original line number Diff line number Diff line
@@ -213,11 +213,29 @@ asmlinkage unsigned long get_overflow_stack(void) 
		OVERFLOW_STACK_SIZE;

}



/*

 * A pseudo spinlock to protect the shadow stack from being used by multiple

 * harts concurrently.  This isn't a real spinlock because the lock side must

 * be taken without a valid stack and only a single register, it's only taken

 * while in the process of panicing anyway so the performance and error

 * checking a proper spinlock gives us doesn't matter.

 */

unsigned long 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);



	/*

	 * We're done with the shadow stack by this point, as we're on the

	 * overflow stack.  Tell any other concurrent overflowing harts that

	 * they can proceed with panicing by releasing the pseudo-spinlock.

	 *

	 * This pairs with an amoswap.aq in handle_kernel_stack_overflow.

	 */

	smp_store_release(&spin_shadow_stack, 0);



	console_verbose();



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