@@ -82,6 +82,28 @@
.endr
.endm
+#ifdef CONFIG_SMP
+#ifdef CONFIG_32BIT
+#define PER_CPU_OFFSET_SHIFT 2
+#else
+#define PER_CPU_OFFSET_SHIFT 3
+#endif
+
+.macro asm_per_cpu dst sym tmp
+ REG_L \tmp, TASK_TI_CPU_NUM(tp)
+ slli \tmp, \tmp, PER_CPU_OFFSET_SHIFT
+ la \dst, __per_cpu_offset
+ add \dst, \dst, \tmp
+ REG_L \tmp, 0(\dst)
+ la \dst, \sym
+ add \dst, \dst, \tmp
+.endm
+#else /* CONFIG_SMP */
+.macro asm_per_cpu dst sym tmp
+ la \dst, \sym
+.endm
+#endif /* CONFIG_SMP */
+
/* save all GPs except x1 ~ x5 */
.macro save_from_x6_to_x31
REG_S x6, PT_T1(sp)
@@ -34,9 +34,6 @@
#ifndef __ASSEMBLY__
-extern long shadow_stack[SHADOW_OVERFLOW_STACK_SIZE / sizeof(long)];
-extern unsigned long spin_shadow_stack;
-
#include <asm/processor.h>
#include <asm/csr.h>
@@ -39,6 +39,7 @@ void asm_offsets(void)
OFFSET(TASK_TI_KERNEL_SP, task_struct, thread_info.kernel_sp);
OFFSET(TASK_TI_USER_SP, task_struct, thread_info.user_sp);
+ OFFSET(TASK_TI_CPU_NUM, task_struct, thread_info.cpu);
OFFSET(TASK_THREAD_F0, task_struct, thread.fstate.f[0]);
OFFSET(TASK_THREAD_F1, task_struct, thread.fstate.f[1]);
OFFSET(TASK_THREAD_F2, task_struct, thread.fstate.f[2]);
@@ -10,9 +10,11 @@
#include <asm/asm.h>
#include <asm/csr.h>
#include <asm/unistd.h>
+#include <asm/page.h>
#include <asm/thread_info.h>
#include <asm/asm-offsets.h>
#include <asm/errata_list.h>
+#include <linux/sizes.h>
SYM_CODE_START(handle_exception)
/*
@@ -170,67 +172,15 @@ SYM_CODE_END(ret_from_exception)
#ifdef CONFIG_VMAP_STACK
SYM_CODE_START_LOCAL(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
-
- //save caller register to shadow stack
- addi sp, sp, -(PT_SIZE_ON_STACK)
- REG_S x1, PT_RA(sp)
- REG_S x5, PT_T0(sp)
- REG_S x6, PT_T1(sp)
- REG_S x7, PT_T2(sp)
- REG_S x10, PT_A0(sp)
- REG_S x11, PT_A1(sp)
- REG_S x12, PT_A2(sp)
- REG_S x13, PT_A3(sp)
- REG_S x14, PT_A4(sp)
- REG_S x15, PT_A5(sp)
- REG_S x16, PT_A6(sp)
- REG_S x17, PT_A7(sp)
- REG_S x28, PT_T3(sp)
- REG_S x29, PT_T4(sp)
- REG_S x30, PT_T5(sp)
- REG_S x31, PT_T6(sp)
-
- la ra, restore_caller_reg
- tail get_overflow_stack
-
-restore_caller_reg:
- //save per-cpu overflow stack
- REG_S a0, -8(sp)
- //restore caller register from shadow_stack
- REG_L x1, PT_RA(sp)
- REG_L x5, PT_T0(sp)
- REG_L x6, PT_T1(sp)
- REG_L x7, PT_T2(sp)
- REG_L x10, PT_A0(sp)
- REG_L x11, PT_A1(sp)
- REG_L x12, PT_A2(sp)
- REG_L x13, PT_A3(sp)
- REG_L x14, PT_A4(sp)
- REG_L x15, PT_A5(sp)
- REG_L x16, PT_A6(sp)
- REG_L x17, PT_A7(sp)
- REG_L x28, PT_T3(sp)
- REG_L x29, PT_T4(sp)
- REG_L x30, PT_T5(sp)
- REG_L x31, PT_T6(sp)
+ /* we reach here from kernel context, sscratch must be 0 */
+ csrrw x31, CSR_SCRATCH, x31
+ asm_per_cpu sp, overflow_stack, x31
+ li x31, OVERFLOW_STACK_SIZE
+ add sp, sp, x31
+ /* zero out x31 again and restore x31 */
+ xor x31, x31, x31
+ csrrw x31, CSR_SCRATCH, x31
- //load per-cpu overflow stack
- REG_L sp, -8(sp)
addi sp, sp, -(PT_SIZE_ON_STACK)
//save context to overflow stack
@@ -397,48 +397,14 @@ int is_valid_bugaddr(unsigned long pc)
#endif /* CONFIG_GENERIC_BUG */
#ifdef CONFIG_VMAP_STACK
-/*
- * Extra stack space that allows us to provide panic messages when the kernel
- * has overflowed its stack.
- */
-static DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)],
+DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)],
overflow_stack)__aligned(16);
-/*
- * A temporary stack for use by handle_kernel_stack_overflow. This is used so
- * we can call into C code to get the per-hart overflow stack. Usage of this
- * stack must be protected by spin_shadow_stack.
- */
-long shadow_stack[SHADOW_OVERFLOW_STACK_SIZE/sizeof(long)] __aligned(16);
-
-/*
- * 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 unsigned long get_overflow_stack(void)
-{
- return (unsigned long)this_cpu_ptr(overflow_stack) +
- OVERFLOW_STACK_SIZE;
-}
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");