android_kernel_oneplus_msm8998/arch/arm64/kernel/entry.S

/*
 * Low-level exception handling code
 *
 * Copyright (C) 2012 ARM Ltd.
 * Authors:	Catalin Marinas <catalin.marinas@arm.com>
 *		Will Deacon <will.deacon@arm.com>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */

#include <linux/init.h>
#include <linux/linkage.h>

#include <asm/alternative.h>
#include <asm/assembler.h>
#include <asm/asm-offsets.h>
#include <asm/cpufeature.h>
#include <asm/errno.h>
#include <asm/esr.h>
#include <asm/irq.h>
#include <asm/memory.h>
#include <asm/ptrace.h>
#include <asm/thread_info.h>
#include <asm/uaccess.h>
#include <asm/asm-uaccess.h>
#include <asm/unistd.h>

/*
 * Context tracking subsystem.  Used to instrument transitions
 * between user and kernel mode.
 */
	.macro ct_user_exit, syscall = 0
#ifdef CONFIG_CONTEXT_TRACKING
	bl	context_tracking_user_exit
	.if \syscall == 1
	/*
	 * Save/restore needed during syscalls.  Restore syscall arguments from
	 * the values already saved on stack during kernel_entry.
	 */
	ldp	x0, x1, [sp]
	ldp	x2, x3, [sp, #S_X2]
	ldp	x4, x5, [sp, #S_X4]
	ldp	x6, x7, [sp, #S_X6]
	.endif
#endif
	.endm

	.macro ct_user_enter
#ifdef CONFIG_CONTEXT_TRACKING
	bl	context_tracking_user_enter
#endif
	.endm

/*
 * Bad Abort numbers
 *-----------------
 */
#define BAD_SYNC	0
#define BAD_IRQ		1
#define BAD_FIQ		2
#define BAD_ERROR	3

	.macro	kernel_entry, el, regsize = 64
	sub	sp, sp, #S_FRAME_SIZE
	.if	\regsize == 32
	mov	w0, w0				// zero upper 32 bits of x0
	.endif
	stp	x0, x1, [sp, #16 * 0]
	stp	x2, x3, [sp, #16 * 1]
	stp	x4, x5, [sp, #16 * 2]
	stp	x6, x7, [sp, #16 * 3]
	stp	x8, x9, [sp, #16 * 4]
	stp	x10, x11, [sp, #16 * 5]
	stp	x12, x13, [sp, #16 * 6]
	stp	x14, x15, [sp, #16 * 7]
	stp	x16, x17, [sp, #16 * 8]
	stp	x18, x19, [sp, #16 * 9]
	stp	x20, x21, [sp, #16 * 10]
	stp	x22, x23, [sp, #16 * 11]
	stp	x24, x25, [sp, #16 * 12]
	stp	x26, x27, [sp, #16 * 13]
	stp	x28, x29, [sp, #16 * 14]

	.if	\el == 0
	mrs	x21, sp_el0
	mov	tsk, sp
	and	tsk, tsk, #~(THREAD_SIZE - 1)	// Ensure MDSCR_EL1.SS is clear,
	ldr	x19, [tsk, #TI_FLAGS]		// since we can unmask debug
	disable_step_tsk x19, x20		// exceptions when scheduling.

	mov	x29, xzr			// fp pointed to user-space
	.else
	add	x21, sp, #S_FRAME_SIZE
	get_thread_info tsk
	/* Save the task's original addr_limit and set USER_DS (TASK_SIZE_64) */
	ldr	x20, [tsk, #TI_ADDR_LIMIT]
	str	x20, [sp, #S_ORIG_ADDR_LIMIT]
	mov	x20, #TASK_SIZE_64
	str	x20, [tsk, #TI_ADDR_LIMIT]
	ALTERNATIVE(nop, SET_PSTATE_UAO(0), ARM64_HAS_UAO, CONFIG_ARM64_UAO)
	.endif /* \el == 0 */
	mrs	x22, elr_el1
	mrs	x23, spsr_el1
	stp	lr, x21, [sp, #S_LR]

#ifdef CONFIG_ARM64_SW_TTBR0_PAN
	/*
	 * Set the TTBR0 PAN bit in SPSR. When the exception is taken from
	 * EL0, there is no need to check the state of TTBR0_EL1 since
	 * accesses are always enabled.
	 * Note that the meaning of this bit differs from the ARMv8.1 PAN
	 * feature as all TTBR0_EL1 accesses are disabled, not just those to
	 * user mappings.
	 */
alternative_if ARM64_HAS_PAN
	b	1f				// skip TTBR0 PAN
alternative_else_nop_endif

	.if	\el != 0
	mrs	x21, ttbr0_el1
	tst	x21, #0xffff << 48		// Check for the reserved ASID
	orr	x23, x23, #PSR_PAN_BIT		// Set the emulated PAN in the saved SPSR
	b.eq	1f				// TTBR0 access already disabled
	and	x23, x23, #~PSR_PAN_BIT		// Clear the emulated PAN in the saved SPSR
	.endif

	__uaccess_ttbr0_disable x21
1:
#endif

	stp	x22, x23, [sp, #S_PC]

	/*
	 * Set syscallno to -1 by default (overridden later if real syscall).
	 */
	.if	\el == 0
	mvn	x21, xzr
	str	x21, [sp, #S_SYSCALLNO]
	.endif

	/*
	 * Set sp_el0 to current thread_info.
	 */
	.if	\el == 0
	msr	sp_el0, tsk
	.endif

	/*
	 * Registers that may be useful after this macro is invoked:
	 *
	 * x21 - aborted SP
	 * x22 - aborted PC
	 * x23 - aborted PSTATE
	*/
	.endm

	.macro	kernel_exit, el
	.if	\el != 0
	/* Restore the task's original addr_limit. */
	ldr	x20, [sp, #S_ORIG_ADDR_LIMIT]
	str	x20, [tsk, #TI_ADDR_LIMIT]

	/* No need to restore UAO, it will be restored from SPSR_EL1 */
	.endif

	ldp	x21, x22, [sp, #S_PC]		// load ELR, SPSR
	.if	\el == 0
	ct_user_enter
	.endif

#ifdef CONFIG_ARM64_SW_TTBR0_PAN
	/*
	 * Restore access to TTBR0_EL1. If returning to EL0, no need for SPSR
	 * PAN bit checking.
	 */
alternative_if ARM64_HAS_PAN
	b	2f				// skip TTBR0 PAN
alternative_else_nop_endif

	.if	\el != 0
	tbnz	x22, #22, 1f			// Skip re-enabling TTBR0 access if the PSR_PAN_BIT is set
	.endif

	__uaccess_ttbr0_enable x0

	.if	\el == 0
	/*
	 * Enable errata workarounds only if returning to user. The only
	 * workaround currently required for TTBR0_EL1 changes are for the
	 * Cavium erratum 27456 (broadcast TLBI instructions may cause I-cache
	 * corruption).
	 */
	post_ttbr0_update_workaround
	.endif
1:
	.if	\el != 0
	and	x22, x22, #~PSR_PAN_BIT		// ARMv8.0 CPUs do not understand this bit
	.endif
2:
#endif

	.if	\el == 0
	ldr	x23, [sp, #S_SP]		// load return stack pointer
	msr	sp_el0, x23
#ifdef CONFIG_ARM64_ERRATUM_845719
alternative_if_not ARM64_WORKAROUND_845719
	nop
	nop
#ifdef CONFIG_PID_IN_CONTEXTIDR
	nop
#endif
alternative_else
	tbz	x22, #4, 1f
#ifdef CONFIG_PID_IN_CONTEXTIDR
	mrs	x29, contextidr_el1
	msr	contextidr_el1, x29
#else
	msr contextidr_el1, xzr
#endif
1:
alternative_endif
#endif
	.endif

	msr	elr_el1, x21			// set up the return data
	msr	spsr_el1, x22
	ldp	x0, x1, [sp, #16 * 0]
	ldp	x2, x3, [sp, #16 * 1]
	ldp	x4, x5, [sp, #16 * 2]
	ldp	x6, x7, [sp, #16 * 3]
	ldp	x8, x9, [sp, #16 * 4]
	ldp	x10, x11, [sp, #16 * 5]
	ldp	x12, x13, [sp, #16 * 6]
	ldp	x14, x15, [sp, #16 * 7]
	ldp	x16, x17, [sp, #16 * 8]
	ldp	x18, x19, [sp, #16 * 9]
	ldp	x20, x21, [sp, #16 * 10]
	ldp	x22, x23, [sp, #16 * 11]
	ldp	x24, x25, [sp, #16 * 12]
	ldp	x26, x27, [sp, #16 * 13]
	ldp	x28, x29, [sp, #16 * 14]
	ldr	lr, [sp, #S_LR]
	add	sp, sp, #S_FRAME_SIZE		// restore sp
	eret					// return to kernel
	.endm

	.macro	irq_stack_entry
	mov	x19, sp			// preserve the original sp

	/*
	 * Compare sp with the current thread_info, if the top
	 * ~(THREAD_SIZE - 1) bits match, we are on a task stack, and
	 * should switch to the irq stack.
	 */
	and	x25, x19, #~(THREAD_SIZE - 1)
	cmp	x25, tsk
	b.ne	9998f

	this_cpu_ptr irq_stack, x25, x26
	mov	x26, #IRQ_STACK_START_SP
	add	x26, x25, x26

	/* switch to the irq stack */
	mov	sp, x26

	/*
	 * Add a dummy stack frame, this non-standard format is fixed up
	 * by unwind_frame()
	 */
	stp     x29, x19, [sp, #-16]!
	mov	x29, sp

9998:
	.endm

	/*
	 * x19 should be preserved between irq_stack_entry and
	 * irq_stack_exit.
	 */
	.macro	irq_stack_exit
	mov	sp, x19
	.endm

/*
 * These are the registers used in the syscall handler, and allow us to
 * have in theory up to 7 arguments to a function - x0 to x6.
 *
 * x7 is reserved for the system call number in 32-bit mode.
 */
sc_nr	.req	x25		// number of system calls
scno	.req	x26		// syscall number
stbl	.req	x27		// syscall table pointer
tsk	.req	x28		// current thread_info

/*
 * Interrupt handling.
 */
	.macro	irq_handler
	ldr_l	x1, handle_arch_irq
	mov	x0, sp
	irq_stack_entry
	blr	x1
	irq_stack_exit
	.endm

	.text

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

	.align	11
ENTRY(vectors)
	ventry	el1_sync_invalid		// Synchronous EL1t
	ventry	el1_irq_invalid			// IRQ EL1t
	ventry	el1_fiq_invalid			// FIQ EL1t
	ventry	el1_error_invalid		// Error EL1t

	ventry	el1_sync			// Synchronous EL1h
	ventry	el1_irq				// IRQ EL1h
	ventry	el1_fiq_invalid			// FIQ EL1h
	ventry	el1_error_invalid		// Error EL1h

	ventry	el0_sync			// Synchronous 64-bit EL0
	ventry	el0_irq				// IRQ 64-bit EL0
	ventry	el0_fiq_invalid			// FIQ 64-bit EL0
	ventry	el0_error_invalid		// Error 64-bit EL0

#ifdef CONFIG_COMPAT
	ventry	el0_sync_compat			// Synchronous 32-bit EL0
	ventry	el0_irq_compat			// IRQ 32-bit EL0
	ventry	el0_fiq_invalid_compat		// FIQ 32-bit EL0
	ventry	el0_error_invalid_compat	// Error 32-bit EL0
#else
	ventry	el0_sync_invalid		// Synchronous 32-bit EL0
	ventry	el0_irq_invalid			// IRQ 32-bit EL0
	ventry	el0_fiq_invalid			// FIQ 32-bit EL0
	ventry	el0_error_invalid		// Error 32-bit EL0
#endif
END(vectors)

/*
 * Invalid mode handlers
 */
	.macro	inv_entry, el, reason, regsize = 64
	kernel_entry \el, \regsize
	mov	x0, sp
	mov	x1, #\reason
	mrs	x2, esr_el1
	b	bad_mode
	.endm

el0_sync_invalid:
	inv_entry 0, BAD_SYNC
ENDPROC(el0_sync_invalid)

el0_irq_invalid:
	inv_entry 0, BAD_IRQ
ENDPROC(el0_irq_invalid)

el0_fiq_invalid:
	inv_entry 0, BAD_FIQ
ENDPROC(el0_fiq_invalid)

el0_error_invalid:
	inv_entry 0, BAD_ERROR
ENDPROC(el0_error_invalid)

#ifdef CONFIG_COMPAT
el0_fiq_invalid_compat:
	inv_entry 0, BAD_FIQ, 32
ENDPROC(el0_fiq_invalid_compat)

el0_error_invalid_compat:
	inv_entry 0, BAD_ERROR, 32
ENDPROC(el0_error_invalid_compat)
#endif

el1_sync_invalid:
	inv_entry 1, BAD_SYNC
ENDPROC(el1_sync_invalid)

el1_irq_invalid:
	inv_entry 1, BAD_IRQ
ENDPROC(el1_irq_invalid)

el1_fiq_invalid:
	inv_entry 1, BAD_FIQ
ENDPROC(el1_fiq_invalid)

el1_error_invalid:
	inv_entry 1, BAD_ERROR
ENDPROC(el1_error_invalid)

/*
 * EL1 mode handlers.
 */
	.align	6
el1_sync:
#ifdef CONFIG_QCOM_TLB_EL2_HANDLER
	smc #0xffff
#endif
	kernel_entry 1
	mrs	x1, esr_el1			// read the syndrome register
	lsr	x24, x1, #ESR_ELx_EC_SHIFT	// exception class
	cmp	x24, #ESR_ELx_EC_DABT_CUR	// data abort in EL1
	b.eq	el1_da
	cmp	x24, #ESR_ELx_EC_IABT_CUR	// instruction abort in EL1
	b.eq	el1_ia
	cmp	x24, #ESR_ELx_EC_SYS64		// configurable trap
	b.eq	el1_undef
	cmp	x24, #ESR_ELx_EC_SP_ALIGN	// stack alignment exception
	b.eq	el1_sp_pc
	cmp	x24, #ESR_ELx_EC_PC_ALIGN	// pc alignment exception
	b.eq	el1_sp_pc
	cmp	x24, #ESR_ELx_EC_UNKNOWN	// unknown exception in EL1
	b.eq	el1_undef
	cmp	x24, #ESR_ELx_EC_BREAKPT_CUR	// debug exception in EL1
	b.ge	el1_dbg
	b	el1_inv

el1_ia:
	/*
	 * Fall through to the Data abort case
	 */
el1_da:
	/*
	 * Data abort handling
	 */
	mrs	x3, far_el1
	enable_dbg
	// re-enable interrupts if they were enabled in the aborted context
	tbnz	x23, #7, 1f			// PSR_I_BIT
	enable_irq
1:
	clear_address_tag x0, x3
	mov	x2, sp				// struct pt_regs
	bl	do_mem_abort

	// disable interrupts before pulling preserved data off the stack
	disable_irq
	kernel_exit 1
el1_sp_pc:
	/*
	 * Stack or PC alignment exception handling
	 */
	mrs	x0, far_el1
	enable_dbg
	mov	x2, sp
	b	do_sp_pc_abort
el1_undef:
	/*
	 * Undefined instruction
	 */
	enable_dbg
	mov	x0, sp
	b	do_undefinstr
el1_dbg:
	/*
	 * Debug exception handling
	 */
	cmp	x24, #ESR_ELx_EC_BRK64		// if BRK64
	cinc	x24, x24, eq			// set bit '0'
	tbz	x24, #0, el1_inv		// EL1 only
	mrs	x0, far_el1
	mov	x2, sp				// struct pt_regs
	bl	do_debug_exception
	kernel_exit 1
el1_inv:
	// TODO: add support for undefined instructions in kernel mode
	enable_dbg
	mov	x0, sp
	mov	x2, x1
	mov	x1, #BAD_SYNC
	b	bad_mode
ENDPROC(el1_sync)

	.align	6
el1_irq:
	kernel_entry 1
	enable_dbg
#ifdef CONFIG_TRACE_IRQFLAGS
	bl	trace_hardirqs_off
#endif

	get_thread_info tsk
	irq_handler

#ifdef CONFIG_PREEMPT
	ldr	w24, [tsk, #TI_PREEMPT]		// get preempt count
	cbnz	w24, 1f				// preempt count != 0
	ldr	x0, [tsk, #TI_FLAGS]		// get flags
	tbz	x0, #TIF_NEED_RESCHED, 1f	// needs rescheduling?
	bl	el1_preempt
1:
#endif
#ifdef CONFIG_TRACE_IRQFLAGS
	bl	trace_hardirqs_on
#endif
	kernel_exit 1
ENDPROC(el1_irq)

#ifdef CONFIG_PREEMPT
el1_preempt:
	mov	x24, lr
1:	bl	preempt_schedule_irq		// irq en/disable is done inside
	ldr	x0, [tsk, #TI_FLAGS]		// get new tasks TI_FLAGS
	tbnz	x0, #TIF_NEED_RESCHED, 1b	// needs rescheduling?
	ret	x24
#endif

/*
 * EL0 mode handlers.
 */
	.align	6
el0_sync:
	kernel_entry 0
	mrs	x25, esr_el1			// read the syndrome register
	lsr	x24, x25, #ESR_ELx_EC_SHIFT	// exception class
	cmp	x24, #ESR_ELx_EC_SVC64		// SVC in 64-bit state
	b.eq	el0_svc
	cmp	x24, #ESR_ELx_EC_DABT_LOW	// data abort in EL0
	b.eq	el0_da
	cmp	x24, #ESR_ELx_EC_IABT_LOW	// instruction abort in EL0
	b.eq	el0_ia
	cmp	x24, #ESR_ELx_EC_FP_ASIMD	// FP/ASIMD access
	b.eq	el0_fpsimd_acc
	cmp	x24, #ESR_ELx_EC_FP_EXC64	// FP/ASIMD exception
	b.eq	el0_fpsimd_exc
	cmp	x24, #ESR_ELx_EC_SYS64		// configurable trap
	b.eq	el0_undef
	cmp	x24, #ESR_ELx_EC_SP_ALIGN	// stack alignment exception
	b.eq	el0_sp_pc
	cmp	x24, #ESR_ELx_EC_PC_ALIGN	// pc alignment exception
	b.eq	el0_sp_pc
	cmp	x24, #ESR_ELx_EC_UNKNOWN	// unknown exception in EL0
	b.eq	el0_undef
	cmp	x24, #ESR_ELx_EC_BREAKPT_LOW	// debug exception in EL0
	b.ge	el0_dbg
	b	el0_inv

#ifdef CONFIG_COMPAT
	.align	6
el0_sync_compat:
	kernel_entry 0, 32
	mrs	x25, esr_el1			// read the syndrome register
	lsr	x24, x25, #ESR_ELx_EC_SHIFT	// exception class
	cmp	x24, #ESR_ELx_EC_SVC32		// SVC in 32-bit state
	b.eq	el0_svc_compat
	cmp	x24, #ESR_ELx_EC_DABT_LOW	// data abort in EL0
	b.eq	el0_da
	cmp	x24, #ESR_ELx_EC_IABT_LOW	// instruction abort in EL0
	b.eq	el0_ia
	cmp	x24, #ESR_ELx_EC_FP_ASIMD	// FP/ASIMD access
	b.eq	el0_fpsimd_acc_compat
	cmp	x24, #ESR_ELx_EC_FP_EXC32	// FP/ASIMD exception
	b.eq	el0_fpsimd_exc
	cmp	x24, #ESR_ELx_EC_PC_ALIGN	// pc alignment exception
	b.eq	el0_sp_pc
	cmp	x24, #ESR_ELx_EC_UNKNOWN	// unknown exception in EL0
	b.eq	el0_undef
	cmp	x24, #ESR_ELx_EC_CP15_32	// CP15 MRC/MCR trap
	b.eq	el0_undef
	cmp	x24, #ESR_ELx_EC_CP15_64	// CP15 MRRC/MCRR trap
	b.eq	el0_undef
	cmp	x24, #ESR_ELx_EC_CP14_MR	// CP14 MRC/MCR trap
	b.eq	el0_undef
	cmp	x24, #ESR_ELx_EC_CP14_LS	// CP14 LDC/STC trap
	b.eq	el0_undef
	cmp	x24, #ESR_ELx_EC_CP14_64	// CP14 MRRC/MCRR trap
	b.eq	el0_undef
	cmp	x24, #ESR_ELx_EC_BREAKPT_LOW	// debug exception in EL0
	b.ge	el0_dbg
	b	el0_inv
el0_svc_compat:
	/*
	 * AArch32 syscall handling
	 */
	adrp	stbl, compat_sys_call_table	// load compat syscall table pointer
	uxtw	scno, w7			// syscall number in w7 (r7)
	mov     sc_nr, #__NR_compat_syscalls
	b	el0_svc_naked

	.align	6
el0_irq_compat:
	kernel_entry 0, 32
	b	el0_irq_naked
#endif

el0_da:
	/*
	 * Data abort handling
	 */
	mrs	x26, far_el1
	// enable interrupts before calling the main handler
	enable_dbg_and_irq
	ct_user_exit
	clear_address_tag x0, x26
	mov	x1, x25
	mov	x2, sp
	bl	do_mem_abort
	b	ret_to_user
el0_ia:
	/*
	 * Instruction abort handling
	 */
	mrs	x26, far_el1
	// enable interrupts before calling the main handler
	enable_dbg_and_irq
	ct_user_exit
	mov	x0, x26
	mov	x1, x25
	mov	x2, sp
	bl	do_mem_abort
	b	ret_to_user
el0_fpsimd_acc:
	/*
	 * Floating Point or Advanced SIMD access
	 */
	enable_dbg
	ct_user_exit
	mov	x0, x25
	mov	x1, sp
	bl	do_fpsimd_acc
	b	ret_to_user
el0_fpsimd_acc_compat:
	/*
	 * Floating Point or Advanced SIMD access
	 */
	enable_dbg
	ct_user_exit
	mov	x0, x25
	mov	x1, sp
	bl	do_fpsimd_acc_compat
	b	ret_to_user

el0_fpsimd_exc:
	/*
	 * Floating Point or Advanced SIMD exception
	 */
	enable_dbg
	ct_user_exit
	mov	x0, x25
	mov	x1, sp
	bl	do_fpsimd_exc
	b	ret_to_user
el0_sp_pc:
	/*
	 * Stack or PC alignment exception handling
	 */
	mrs	x26, far_el1
	// enable interrupts before calling the main handler
	enable_dbg_and_irq
	ct_user_exit
	mov	x0, x26
	mov	x1, x25
	mov	x2, sp
	bl	do_sp_pc_abort
	b	ret_to_user
el0_undef:
	/*
	 * Undefined instruction
	 */
	// enable interrupts before calling the main handler
	enable_dbg_and_irq
	ct_user_exit
	mov	x0, sp
	bl	do_undefinstr
	b	ret_to_user
el0_dbg:
	/*
	 * Debug exception handling
	 */
	tbnz	x24, #0, el0_inv		// EL0 only
	mrs	x0, far_el1
	mov	x1, x25
	mov	x2, sp
	bl	do_debug_exception
	enable_dbg
	ct_user_exit
	b	ret_to_user
el0_inv:
	enable_dbg
	ct_user_exit
	mov	x0, sp
	mov	x1, #BAD_SYNC
	mov	x2, x25
	bl	bad_el0_sync
	b	ret_to_user
ENDPROC(el0_sync)

	.align	6
el0_irq:
	kernel_entry 0
el0_irq_naked:
	enable_dbg
#ifdef CONFIG_TRACE_IRQFLAGS
	bl	trace_hardirqs_off
#endif

	ct_user_exit
	irq_handler

#ifdef CONFIG_TRACE_IRQFLAGS
	bl	trace_hardirqs_on
#endif
	b	ret_to_user
ENDPROC(el0_irq)

/*
 * Register switch for AArch64. The callee-saved registers need to be saved
 * and restored. On entry:
 *   x0 = previous task_struct (must be preserved across the switch)
 *   x1 = next task_struct
 * Previous and next are guaranteed not to be the same.
 *
 */
ENTRY(cpu_switch_to)
	mov	x10, #THREAD_CPU_CONTEXT
	add	x8, x0, x10
	mov	x9, sp
	stp	x19, x20, [x8], #16		// store callee-saved registers
	stp	x21, x22, [x8], #16
	stp	x23, x24, [x8], #16
	stp	x25, x26, [x8], #16
	stp	x27, x28, [x8], #16
	stp	x29, x9, [x8], #16
	str	lr, [x8]
	add	x8, x1, x10
	ldp	x19, x20, [x8], #16		// restore callee-saved registers
	ldp	x21, x22, [x8], #16
	ldp	x23, x24, [x8], #16
	ldp	x25, x26, [x8], #16
	ldp	x27, x28, [x8], #16
	ldp	x29, x9, [x8], #16
	ldr	lr, [x8]
#ifdef CONFIG_ARM64_REG_REBALANCE_ON_CTX_SW
	orr	x13, x13, x13
	orr	x14, x14, x14
	orr	x15, x15, x15
	orr	x16, x16, x16
	orr	x17, x17, x17
	orr	x18, x18, x18
	orr	x19, x19, x19
	orr	x20, x20, x20
	orr	x21, x21, x21
	mov	v0.16b, v0.16b
	mov	v1.16b, v1.16b
	mov	v2.16b, v2.16b
	mov	v3.16b, v3.16b
	mov	v4.16b, v4.16b
	mov	v5.16b, v5.16b
	mov	v6.16b, v6.16b
	mov	v7.16b, v7.16b
	mov	v8.16b, v8.16b
	mov	v9.16b, v9.16b
	mov	v10.16b, v10.16b
	mov	v11.16b, v11.16b
	mov	v12.16b, v12.16b
	mov	v13.16b, v13.16b
	mov	v14.16b, v14.16b
	mov	v15.16b, v15.16b
#endif
	mov	sp, x9
	and	x9, x9, #~(THREAD_SIZE - 1)
	msr	sp_el0, x9
	ret
ENDPROC(cpu_switch_to)

/*
 * This is the fast syscall return path.  We do as little as possible here,
 * and this includes saving x0 back into the kernel stack.
 */
ret_fast_syscall:
	disable_irq				// disable interrupts
	str	x0, [sp, #S_X0]			// returned x0
	ldr	x1, [tsk, #TI_FLAGS]		// re-check for syscall tracing
	and	x2, x1, #_TIF_SYSCALL_WORK
	cbnz	x2, ret_fast_syscall_trace
	and	x2, x1, #_TIF_WORK_MASK
	cbnz	x2, work_pending
	enable_step_tsk x1, x2
	kernel_exit 0
ret_fast_syscall_trace:
	enable_irq				// enable interrupts
	b	__sys_trace_return_skipped	// we already saved x0

/*
 * Ok, we need to do extra processing, enter the slow path.
 */
work_pending:
	tbnz	x1, #TIF_NEED_RESCHED, work_resched
	/* TIF_SIGPENDING, TIF_NOTIFY_RESUME or TIF_FOREIGN_FPSTATE case */
	mov	x0, sp				// 'regs'
	enable_irq				// enable interrupts for do_notify_resume()
	bl	do_notify_resume
	b	ret_to_user
work_resched:
#ifdef CONFIG_TRACE_IRQFLAGS
	bl	trace_hardirqs_off		// the IRQs are off here, inform the tracing code
#endif
	bl	schedule

/*
 * "slow" syscall return path.
 */
ret_to_user:
	disable_irq				// disable interrupts
	ldr	x1, [tsk, #TI_FLAGS]
	and	x2, x1, #_TIF_WORK_MASK
	cbnz	x2, work_pending
	enable_step_tsk x1, x2
	kernel_exit 0
ENDPROC(ret_to_user)

/*
 * This is how we return from a fork.
 */
ENTRY(ret_from_fork)
	bl	schedule_tail
	cbz	x19, 1f				// not a kernel thread
	mov	x0, x20
	blr	x19
1:	get_thread_info tsk
	b	ret_to_user
ENDPROC(ret_from_fork)

/*
 * SVC handler.
 */
	.align	6
el0_svc:
	adrp	stbl, sys_call_table		// load syscall table pointer
	uxtw	scno, w8			// syscall number in w8
	mov	sc_nr, #__NR_syscalls
el0_svc_naked:					// compat entry point
	stp	x0, scno, [sp, #S_ORIG_X0]	// save the original x0 and syscall number
	enable_dbg_and_irq
	ct_user_exit 1

	ldr	x16, [tsk, #TI_FLAGS]		// check for syscall hooks
	tst	x16, #_TIF_SYSCALL_WORK
	b.ne	__sys_trace
	cmp     scno, sc_nr                     // check upper syscall limit
	b.hs	ni_sys
	ldr	x16, [stbl, scno, lsl #3]	// address in the syscall table
	blr	x16				// call sys_* routine
	b	ret_fast_syscall
ni_sys:
	mov	x0, sp
	bl	do_ni_syscall
	b	ret_fast_syscall
ENDPROC(el0_svc)

	/*
	 * This is the really slow path.  We're going to be doing context
	 * switches, and waiting for our parent to respond.
	 */
__sys_trace:
	mov	w0, #-1				// set default errno for
	cmp     scno, x0			// user-issued syscall(-1)
	b.ne	1f
	mov	x0, #-ENOSYS
	str	x0, [sp, #S_X0]
1:	mov	x0, sp
	bl	syscall_trace_enter
	cmp	w0, #-1				// skip the syscall?
	b.eq	__sys_trace_return_skipped
	uxtw	scno, w0			// syscall number (possibly new)
	mov	x1, sp				// pointer to regs
	cmp	scno, sc_nr			// check upper syscall limit
	b.hs	__ni_sys_trace
	ldp	x0, x1, [sp]			// restore the syscall args
	ldp	x2, x3, [sp, #S_X2]
	ldp	x4, x5, [sp, #S_X4]
	ldp	x6, x7, [sp, #S_X6]
	ldr	x16, [stbl, scno, lsl #3]	// address in the syscall table
	blr	x16				// call sys_* routine

__sys_trace_return:
	str	x0, [sp, #S_X0]			// save returned x0
__sys_trace_return_skipped:
	mov	x0, sp
	bl	syscall_trace_exit
	b	ret_to_user

__ni_sys_trace:
	mov	x0, sp
	bl	do_ni_syscall
	b	__sys_trace_return

	.popsection				// .entry.text

/*
 * Special system call wrappers.
 */
ENTRY(sys_rt_sigreturn_wrapper)
	mov	x0, sp
	b	sys_rt_sigreturn
ENDPROC(sys_rt_sigreturn_wrapper)