[armv8-arch64]linux kernel 5.9的异常量表介绍(irq,fiq,sync,svc)

在entry.S中，定义了异常向量表，从代码中我们可以知道以下信息：

• 该表的基地址在vectors处(在开机的时候，会将其写入到vbar_el1中)
• 这个表以".align 11"方式对齐，即这张表至少占据2^11 size
• kernel_entry是一个用于定义向量表offset的宏，在kernel_entry中，是以“.align 7”方式对齐的，即2^8=0x80方式对齐，与ARMV8中的向量表offset一致
• armv8的向量表中又16个offset，在Linux Kernel中，仅实现了6个
• Linux Kernel中没有实现 FIQ

(linux_5.9/arch/arm64/kernel/entry.S)

/*
 * Exception vectors.
 */
	.pushsection ".entry.text", "ax"

	.align	11
SYM_CODE_START(vectors)
	kernel_ventry	1, sync_invalid			// Synchronous EL1t
	kernel_ventry	1, irq_invalid			// IRQ EL1t
	kernel_ventry	1, fiq_invalid			// FIQ EL1t
	kernel_ventry	1, error_invalid		// Error EL1t

	kernel_ventry	1, sync				// Synchronous EL1h
	kernel_ventry	1, irq				// IRQ EL1h
	kernel_ventry	1, fiq_invalid			// FIQ EL1h
	kernel_ventry	1, error			// Error EL1h

	kernel_ventry	0, sync				// Synchronous 64-bit EL0
	kernel_ventry	0, irq				// IRQ 64-bit EL0
	kernel_ventry	0, fiq_invalid			// FIQ 64-bit EL0
	kernel_ventry	0, error			// Error 64-bit EL0

#ifdef CONFIG_COMPAT
	kernel_ventry	0, sync_compat, 32		// Synchronous 32-bit EL0
	kernel_ventry	0, irq_compat, 32		// IRQ 32-bit EL0
	kernel_ventry	0, fiq_invalid_compat, 32	// FIQ 32-bit EL0
	kernel_ventry	0, error_compat, 32		// Error 32-bit EL0
#else
	kernel_ventry	0, sync_invalid, 32		// Synchronous 32-bit EL0
	kernel_ventry	0, irq_invalid, 32		// IRQ 32-bit EL0
	kernel_ventry	0, fiq_invalid, 32		// FIQ 32-bit EL0
	kernel_ventry	0, error_invalid, 32		// Error 32-bit EL0
#endif
SYM_CODE_END(vectors)

我们再来看看kernel_ventry宏，它是用于定义向量表offset的宏，，从代码中我们可以知道以下信息：

• kernel_ventry定义的offset以“.align 7”方式对齐的，即2^8=0x80方式对齐，与ARMV8中的向量表offset一致
• 该宏定义最终调用了“b el()\el()_\label”，即：
  – kernel_ventry 1, sync //调用了 el1_sync
  – kernel_ventry 1, irq //调用了 el1_irq
  – kernel_ventry 1, error //调用了 el1_error
  – kernel_ventry 0, sync //调用了 el0_sync
  – kernel_ventry 0, irq //调用了 el0_irq
  – kernel_ventry 0, error //调用了 el0_error

(linux_5.9/arch/arm64/kernel/entry.S)

.macro kernel_ventry, el, label, regsize = 64
	.align 7
#ifdef CONFIG_UNMAP_KERNEL_AT_EL0
	.if	\el == 0
alternative_if ARM64_UNMAP_KERNEL_AT_EL0
	.if	\regsize == 64
	mrs	x30, tpidrro_el0
	msr	tpidrro_el0, xzr
	.else
	mov	x30, xzr
	.endif
alternative_else_nop_endif
	.endif
#endif

	sub	sp, sp, #S_FRAME_SIZE
#ifdef CONFIG_VMAP_STACK
	/*
	 * Test whether the SP has overflowed, without corrupting a GPR.
	 * Task and IRQ stacks are aligned so that SP & (1 << THREAD_SHIFT)
	 * should always be zero.
	 */
	add	sp, sp, x0			// sp' = sp + x0
	sub	x0, sp, x0			// x0' = sp' - x0 = (sp + x0) - x0 = sp
	tbnz	x0, #THREAD_SHIFT, 0f
	sub	x0, sp, x0			// x0'' = sp' - x0' = (sp + x0) - sp = x0
	sub	sp, sp, x0			// sp'' = sp' - x0 = (sp + x0) - x0 = sp
	b	el\()\el\()_\label

0:
	/*
	 * Either we've just detected an overflow, or we've taken an exception
	 * while on the overflow stack. Either way, we won't return to
	 * userspace, and can clobber EL0 registers to free up GPRs.
	 */

	/* Stash the original SP (minus S_FRAME_SIZE) in tpidr_el0. */
 	msr	tpidr_el0, x0
 
 	/* Recover the original x0 value and stash it in tpidrro_el0 */
 	sub	x0, sp, x0
 	msr	tpidrro_el0, x0
 
 	/* Switch to the overflow stack */
 	adr_this_cpu sp, overflow_stack + OVERFLOW_STACK_SIZE, x0
 
 	/*
 	 * Check whether we were already on the overflow stack. This may happen
 	 * after panic() re-enables interrupts.
 	 */
 	mrs	x0, tpidr_el0			// sp of interrupted context
 	sub	x0, sp, x0			// delta with top of overflow stack
 	tst	x0, #~(OVERFLOW_STACK_SIZE - 1)	// within range?
 	b.ne	__bad_stack			// no? -> bad stack pointer
 
 	/* We were already on the overflow stack. Restore sp/x0 and carry on. */
 	sub	sp, sp, x0
 	mrs	x0, tpidrro_el0
 #endif
 	b	el\()\el\()_\label
 	.endm

在__primary_switched函数中，将向量表的基地址vectors写入到了vbar_el1中.

(linux_5.9/arch/arm64/kernel/entry.S)

SYM_FUNC_START_LOCAL(__primary_switched)
	adrp	x4, init_thread_union
	add	sp, x4, #THREAD_SIZE
	adr_l	x5, init_task
	msr	sp_el0, x5			// Save thread_info

#ifdef CONFIG_ARM64_PTR_AUTH
	__ptrauth_keys_init_cpu	x5, x6, x7, x8
#endif

	adr_l	x8, vectors			// load VBAR_EL1 with virtual
	msr	vbar_el1, x8			// vector table address
	isb

	stp	xzr, x30, [sp, #-16]!
	mov	x29, sp

#ifdef CONFIG_SHADOW_CALL_STACK
	adr_l	scs_sp, init_shadow_call_stack	// Set shadow call stack
#endif

	str_l	x21, __fdt_pointer, x5		// Save FDT pointer

	ldr_l	x4, kimage_vaddr		// Save the offset between
	sub	x4, x4, x0			// the kernel virtual and
	str_l	x4, kimage_voffset, x5		// physical mappings

	// Clear BSS
	adr_l	x0, __bss_start
	mov	x1, xzr
	adr_l	x2, __bss_stop
	sub	x2, x2, x0
	bl	__pi_memset
	dsb	ishst				// Make zero page visible to PTW

#ifdef CONFIG_KASAN
	bl	kasan_early_init
#endif
#ifdef CONFIG_RANDOMIZE_BASE
	tst	x23, ~(MIN_KIMG_ALIGN - 1)	// already running randomized?
	b.ne	0f
	mov	x0, x21				// pass FDT address in x0
	bl	kaslr_early_init		// parse FDT for KASLR options
	cbz	x0, 0f				// KASLR disabled? just proceed
	orr	x23, x23, x0			// record KASLR offset
	ldp	x29, x30, [sp], #16		// we must enable KASLR, return
	ret					// to __primary_switch()
0:
#endif
	add	sp, sp, #16
	mov	x29, #0
	mov	x30, #0
	b	start_kernel
SYM_FUNC_END(__primary_switched)

而在开机时的在__primary_switched函数中被调用的流程如下所示

_head —> primary_entry —> __primary_switch —> __primary_switched —> 将向量表基地址vectors写入到vbar_el1寄存器

相关代码：

(linux_5.9/arch/arm64/kernel/head.S)

SYM_CODE_START(primary_entry)
	bl	preserve_boot_args
	bl	el2_setup			// Drop to EL1, w0=cpu_boot_mode
	adrp	x23, __PHYS_OFFSET
	and	x23, x23, MIN_KIMG_ALIGN - 1	// KASLR offset, defaults to 0
	bl	set_cpu_boot_mode_flag
	bl	__create_page_tables
	/*
	 * The following calls CPU setup code, see arch/arm64/mm/proc.S for
	 * details.
	 * On return, the CPU will be ready for the MMU to be turned on and
	 * the TCR will have been set.
	 */
	bl	__cpu_setup			// initialise processor
	b	__primary_switch
SYM_CODE_END(primary_entry)


	__HEAD
_head:
	/*
	 * DO NOT MODIFY. Image header expected by Linux boot-loaders.
	 */
#ifdef CONFIG_EFI
	/*
	 * This add instruction has no meaningful effect except that
	 * its opcode forms the magic "MZ" signature required by UEFI.
	 */
	add	x13, x18, #0x16
	b	primary_entry
#else
	b	primary_entry			// branch to kernel start, magic
	.long	0				// reserved
#endif
......