path: root/arch/x86/entry/entry_64.S

/* SPDX-License-Identifier: GPL-2.0 */
/*
 *  linux/arch/x86_64/entry.S
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *  Copyright (C) 2000, 2001, 2002  Andi Kleen SuSE Labs
 *  Copyright (C) 2000  Pavel Machek <pavel@suse.cz>
 *
 * entry.S contains the system-call and fault low-level handling routines.
 *
 * Some of this is documented in Documentation/x86/entry_64.rst
 *
 * A note on terminology:
 * - iret frame:	Architecture defined interrupt frame from SS to RIP
 *			at the top of the kernel process stack.
 *
 * Some macro usage:
 * - SYM_FUNC_START/END:Define functions in the symbol table.
 * - idtentry:		Define exception entry points.
 */
#include <linux/linkage.h>
#include <asm/segment.h>
#include <asm/cache.h>
#include <asm/errno.h>
#include <asm/asm-offsets.h>
#include <asm/msr.h>
#include <asm/unistd.h>
#include <asm/thread_info.h>
#include <asm/hw_irq.h>
#include <asm/page_types.h>
#include <asm/irqflags.h>
#include <asm/paravirt.h>
#include <asm/percpu.h>
#include <asm/asm.h>
#include <asm/smap.h>
#include <asm/pgtable_types.h>
#include <asm/export.h>
#include <asm/frame.h>
#include <asm/trapnr.h>
#include <asm/nospec-branch.h>
#include <asm/fsgsbase.h>
#include <linux/err.h>

#include "calling.h"

.code64
.section .entry.text, "ax"

/*
 * 64-bit SYSCALL instruction entry. Up to 6 arguments in registers.
 *
 * This is the only entry point used for 64-bit system calls.  The
 * hardware interface is reasonably well designed and the register to
 * argument mapping Linux uses fits well with the registers that are
 * available when SYSCALL is used.
 *
 * SYSCALL instructions can be found inlined in libc implementations as
 * well as some other programs and libraries.  There are also a handful
 * of SYSCALL instructions in the vDSO used, for example, as a
 * clock_gettimeofday fallback.
 *
 * 64-bit SYSCALL saves rip to rcx, clears rflags.RF, then saves rflags to r11,
 * then loads new ss, cs, and rip from previously programmed MSRs.
 * rflags gets masked by a value from another MSR (so CLD and CLAC
 * are not needed). SYSCALL does not save anything on the stack
 * and does not change rsp.
 *
 * Registers on entry:
 * rax  system call number
 * rcx  return address
 * r11  saved rflags (note: r11 is callee-clobbered register in C ABI)
 * rdi  arg0
 * rsi  arg1
 * rdx  arg2
 * r10  arg3 (needs to be moved to rcx to conform to C ABI)
 * r8   arg4
 * r9   arg5
 * (note: r12-r15, rbp, rbx are callee-preserved in C ABI)
 *
 * Only called from user space.
 *
 * When user can change pt_regs->foo always force IRET. That is because
 * it deals with uncanonical addresses better. SYSRET has trouble
 * with them due to bugs in both AMD and Intel CPUs.
 */

SYM_CODE_START(entry_SYSCALL_64)
	UNWIND_HINT_ENTRY
	ENDBR

	swapgs
	/* tss.sp2 is scratch space. */
	movq	%rsp, PER_CPU_VAR(cpu_tss_rw + TSS_sp2)
	SWITCH_TO_KERNEL_CR3 scratch_reg=%rsp
	movq	PER_CPU_VAR(pcpu_hot + X86_top_of_stack), %rsp

SYM_INNER_LABEL(entry_SYSCALL_64_safe_stack, SYM_L_GLOBAL)
	ANNOTATE_NOENDBR

	/* Construct struct pt_regs on stack */
	pushq	$__USER_DS				/* pt_regs->ss */
	pushq	PER_CPU_VAR(cpu_tss_rw + TSS_sp2)	/* pt_regs->sp */
	pushq	%r11					/* pt_regs->flags */
	pushq	$__USER_CS				/* pt_regs->cs */
	pushq	%rcx					/* pt_regs->ip */
SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL)
	pushq	%rax					/* pt_regs->orig_ax */

	PUSH_AND_CLEAR_REGS rax=$-ENOSYS

	/* IRQs are off. */
	movq	%rsp, %rdi
	/* Sign extend the lower 32bit as syscall numbers are treated as int */
	movslq	%eax, %rsi

	/* clobbers %rax, make sure it is after saving the syscall nr */
	IBRS_ENTER
	UNTRAIN_RET

	call	do_syscall_64		/* returns with IRQs disabled */

	/*
	 * Try to use SYSRET instead of IRET if we're returning to
	 * a completely clean 64-bit userspace context.  If we're not,
	 * go to the slow exit path.
	 * In the Xen PV case we must use iret anyway.
	 */

	ALTERNATIVE "", "jmp	swapgs_restore_regs_and_return_to_usermode", \
		X86_FEATURE_XENPV

	movq	RCX(%rsp), %rcx
	movq	RIP(%rsp), %r11

	cmpq	%rcx, %r11	/* SYSRET requires RCX == RIP */
	jne	swapgs_restore_regs_and_return_to_usermode

	/*
	 * On Intel CPUs, SYSRET with non-canonical RCX/RIP will #GP
	 * in kernel space.  This essentially lets the user take over
	 * the kernel, since userspace controls RSP.
	 *
	 * If width of "canonical tail" ever becomes variable, this will need
	 * to be updated to remain correct on both old and new CPUs.
	 *
	 * Change top bits to match most significant bit (47th or 56th bit
	 * depending on paging mode) in the address.
	 */
#ifdef CONFIG_X86_5LEVEL
	ALTERNATIVE "shl $(64 - 48), %rcx; sar $(64 - 48), %rcx", \
		"shl $(64 - 57), %rcx; sar $(64 - 57), %rcx", X86_FEATURE_LA57
#else
	shl	$(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
	sar	$(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
#endif

	/* If this changed %rcx, it was not canonical */
	cmpq	%rcx, %r11
	jne	swapgs_restore_regs_and_return_to_usermode

	cmpq	$__USER_CS, CS(%rsp)		/* CS must match SYSRET */
	jne	swapgs_restore_regs_and_return_to_usermode

	movq	R11(%rsp), %r11
	cmpq	%r11, EFLAGS(%rsp)		/* R11 == RFLAGS */
	jne	swapgs_restore_regs_and_return_to_usermode

	/*
	 * SYSCALL clears RF when it saves RFLAGS in R11 and SYSRET cannot
	 * restore RF properly. If the slowpath sets it for whatever reason, we
	 * need to restore it correctly.
	 *
	 * SYSRET can restore TF, but unlike IRET, restoring TF results in a
	 * trap from userspace immediately after SYSRET.  This would cause an
	 * infinite loop whenever #DB happens with register state that satisfies
	 * the opportunistic SYSRET conditions.  For example, single-stepping
	 * this user code:
	 *
	 *           movq	$stuck_here, %rcx
	 *           pushfq
	 *           popq %r11
	 *   stuck_here:
	 *
	 * would never get past 'stuck_here'.
	 */
	testq	$(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11
	jnz	swapgs_restore_regs_and_return_to_usermode

	/* nothing to check for RSP */

	cmpq	$__USER_DS, SS(%rsp)		/* SS must match SYSRET */
	jne	swapgs_restore_regs_and_return_to_usermode

	/*
	 * We win! This label is here just for ease of understanding
	 * perf profiles. Nothing jumps here.
	 */
syscall_return_via_sysret:
	IBRS_EXIT
	POP_REGS pop_rdi=0

	/*
	 * Now all regs are restored except RSP and RDI.
	 * Save old stack pointer and switch to trampoline stack.
	 */
	movq	%rsp, %rdi
	movq	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %rsp
	UNWIND_HINT_EMPTY

	pushq	RSP-RDI(%rdi)	/* RSP */
	pushq	(%rdi)		/* RDI */

	/*
	 * We are on the trampoline stack.  All regs except RDI are live.
	 * We can do future final exit work right here.
	 */
	STACKLEAK_ERASE_NOCLOBBER

	SWITCH_TO_USER_CR3_STACK scratch_reg=%rdi

	popq	%rdi
	popq	%rsp
SYM_INNER_LABEL(entry_SYSRETQ_unsafe_stack, SYM_L_GLOBAL)
	ANNOTATE_NOENDBR
	swapgs
	sysretq
SYM_INNER_LABEL(entry_SYSRETQ_end, SYM_L_GLOBAL)
	ANNOTATE_NOENDBR
	int3
SYM_CODE_END(entry_SYSCALL_64)

/*
 * %rdi: