Merge tag 'x86-asm-2021-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 asm updates from Ingo Molnar:

 - Micro-optimize and standardize the do_syscall_64() calling convention

 - Make syscall entry flags clearing more conservative

 - Clean up syscall table handling

 - Clean up & standardize assembly macros, in preparation of FRED

 - Misc cleanups and fixes

* tag 'x86-asm-2021-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/asm: Make <asm/asm.h> valid on cross-builds as well
  x86/regs: Syscall_get_nr() returns -1 for a non-system call
  x86/entry: Split PUSH_AND_CLEAR_REGS into two submacros
  x86/syscall: Maximize MSR_SYSCALL_MASK
  x86/syscall: Unconditionally prototype {ia32,x32}_sys_call_table[]
  x86/entry: Reverse arguments to do_syscall_64()
  x86/entry: Unify definitions from <asm/calling.h> and <asm/ptrace-abi.h>
  x86/asm: Use _ASM_BYTES() in <asm/nops.h>
  x86/asm: Add _ASM_BYTES() macro for a .byte ... opcode sequence
  x86/asm: Have the __ASM_FORM macros handle commas in arguments

arch/x86/entry/calling.h

@@ -6,6 +6,7 @@
 #include <asm/percpu.h>
 #include <asm/asm-offsets.h>
 #include <asm/processor-flags.h>
+#include <asm/ptrace-abi.h>
 
 /*
 
@@ -62,42 +63,7 @@ For 32-bit we have the following conventions - kernel is built with
  * for assembly code:
  */
 
-/* The layout forms the "struct pt_regs" on the stack: */
-/*
- * C ABI says these regs are callee-preserved. They aren't saved on kernel entry
- * unless syscall needs a complete, fully filled "struct pt_regs".
- */
-#define R15		0*8
-#define R14		1*8
-#define R13		2*8
-#define R12		3*8
-#define RBP		4*8
-#define RBX		5*8
-/* These regs are callee-clobbered. Always saved on kernel entry. */
-#define R11		6*8
-#define R10		7*8
-#define R9		8*8
-#define R8		9*8
-#define RAX		10*8
-#define RCX		11*8
-#define RDX		12*8
-#define RSI		13*8
-#define RDI		14*8
-/*
- * On syscall entry, this is syscall#. On CPU exception, this is error code.
- * On hw interrupt, it's IRQ number:
- */
-#define ORIG_RAX	15*8
-/* Return frame for iretq */
-#define RIP		16*8
-#define CS		17*8
-#define EFLAGS		18*8
-#define RSP		19*8
-#define SS		20*8
-
-#define SIZEOF_PTREGS	21*8
-
-.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0
+.macro PUSH_REGS rdx=%rdx rax=%rax save_ret=0
 	.if \save_ret
 	pushq	%rsi		/* pt_regs->si */
 	movq	8(%rsp), %rsi	/* temporarily store the return address in %rsi */
@@ -124,7 +90,9 @@ For 32-bit we have the following conventions - kernel is built with
 	.if \save_ret
 	pushq	%rsi		/* return address on top of stack */
 	.endif
+.endm
 
+.macro CLEAR_REGS
 	/*
 	 * Sanitize registers of values that a speculation attack might
 	 * otherwise want to exploit. The lower registers are likely clobbered
@@ -146,6 +114,11 @@ For 32-bit we have the following conventions - kernel is built with
 
 .endm
 
+.macro PUSH_AND_CLEAR_REGS rdx=%rdx rax=%rax save_ret=0
+	PUSH_REGS rdx=\rdx, rax=\rax, save_ret=\save_ret
+	CLEAR_REGS
+.endm
+
 .macro POP_REGS pop_rdi=1 skip_r11rcx=0
 	popq %r15
 	popq %r14

arch/x86/entry/common.c

@@ -36,7 +36,7 @@
 #include <asm/irq_stack.h>
 
 #ifdef CONFIG_X86_64
-__visible noinstr void do_syscall_64(unsigned long nr, struct pt_regs *regs)
+__visible noinstr void do_syscall_64(struct pt_regs *regs, unsigned long nr)
 {
 	add_random_kstack_offset();
 	nr = syscall_enter_from_user_mode(regs, nr);

arch/x86/entry/entry_64.S

@@ -107,8 +107,8 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL)
 	PUSH_AND_CLEAR_REGS rax=$-ENOSYS
 
 	/* IRQs are off. */
-	movq	%rax, %rdi
-	movq	%rsp, %rsi
+	movq	%rsp, %rdi
+	movq	%rax, %rsi
 	call	do_syscall_64		/* returns with IRQs disabled */
 
 	/*

arch/x86/include/asm/asm.h

@@ -3,17 +3,18 @@
 #define _ASM_X86_ASM_H
 
 #ifdef __ASSEMBLY__
-# define __ASM_FORM(x)	x
-# define __ASM_FORM_RAW(x)     x
-# define __ASM_FORM_COMMA(x) x,
+# define __ASM_FORM(x, ...)		x,## __VA_ARGS__
+# define __ASM_FORM_RAW(x, ...)		x,## __VA_ARGS__
+# define __ASM_FORM_COMMA(x, ...)	x,## __VA_ARGS__,
 #else
 #include <linux/stringify.h>
-
-# define __ASM_FORM(x)	" " __stringify(x) " "
-# define __ASM_FORM_RAW(x)     __stringify(x)
-# define __ASM_FORM_COMMA(x) " " __stringify(x) ","
+# define __ASM_FORM(x, ...)		" " __stringify(x,##__VA_ARGS__) " "
+# define __ASM_FORM_RAW(x, ...)		    __stringify(x,##__VA_ARGS__)
+# define __ASM_FORM_COMMA(x, ...)	" " __stringify(x,##__VA_ARGS__) ","
 #endif
 
+#define _ASM_BYTES(x, ...)	__ASM_FORM(.byte x,##__VA_ARGS__ ;)
+
 #ifndef __x86_64__
 /* 32 bit */
 # define __ASM_SEL(a,b)		__ASM_FORM(a)
@@ -119,6 +120,8 @@
 # define CC_OUT(c) [_cc_ ## c] "=qm"
 #endif
 
+#ifdef __KERNEL__
+
 /* Exception table entry */
 #ifdef __ASSEMBLY__
 # define _ASM_EXTABLE_HANDLE(from, to, handler)			\
@@ -185,4 +188,6 @@ register unsigned long current_stack_pointer asm(_ASM_SP);
 #define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer)
 #endif /* __ASSEMBLY__ */
 
+#endif /* __KERNEL__ */
+
 #endif /* _ASM_X86_ASM_H */

arch/x86/include/asm/nops.h

@@ -2,6 +2,8 @@
 #ifndef _ASM_X86_NOPS_H
 #define _ASM_X86_NOPS_H
 
+#include <asm/asm.h>
+
 /*
  * Define nops for use with alternative() and for tracing.
  */
@@ -57,20 +59,14 @@
 
 #endif /* CONFIG_64BIT */
 
-#ifdef __ASSEMBLY__
-#define _ASM_MK_NOP(x) .byte x
-#else
-#define _ASM_MK_NOP(x) ".byte " __stringify(x) "\n"
-#endif
-
-#define ASM_NOP1 _ASM_MK_NOP(BYTES_NOP1)
-#define ASM_NOP2 _ASM_MK_NOP(BYTES_NOP2)
-#define ASM_NOP3 _ASM_MK_NOP(BYTES_NOP3)
-#define ASM_NOP4 _ASM_MK_NOP(BYTES_NOP4)
-#define ASM_NOP5 _ASM_MK_NOP(BYTES_NOP5)
-#define ASM_NOP6 _ASM_MK_NOP(BYTES_NOP6)
-#define ASM_NOP7 _ASM_MK_NOP(BYTES_NOP7)
-#define ASM_NOP8 _ASM_MK_NOP(BYTES_NOP8)
+#define ASM_NOP1 _ASM_BYTES(BYTES_NOP1)
+#define ASM_NOP2 _ASM_BYTES(BYTES_NOP2)
+#define ASM_NOP3 _ASM_BYTES(BYTES_NOP3)
+#define ASM_NOP4 _ASM_BYTES(BYTES_NOP4)
+#define ASM_NOP5 _ASM_BYTES(BYTES_NOP5)
+#define ASM_NOP6 _ASM_BYTES(BYTES_NOP6)
+#define ASM_NOP7 _ASM_BYTES(BYTES_NOP7)
+#define ASM_NOP8 _ASM_BYTES(BYTES_NOP8)
 
 #define ASM_NOP_MAX 8
 

arch/x86/include/asm/syscall.h

@@ -21,13 +21,12 @@ extern const sys_call_ptr_t sys_call_table[];
 
 #if defined(CONFIG_X86_32)
 #define ia32_sys_call_table sys_call_table
-#endif
-
-#if defined(CONFIG_IA32_EMULATION)
+#else
+/*
+ * These may not exist, but still put the prototypes in so we
+ * can use IS_ENABLED().
+ */
 extern const sys_call_ptr_t ia32_sys_call_table[];
-#endif
-
-#ifdef CONFIG_X86_X32_ABI
 extern const sys_call_ptr_t x32_sys_call_table[];
 #endif
 
@@ -160,7 +159,7 @@ static inline int syscall_get_arch(struct task_struct *task)
 		? AUDIT_ARCH_I386 : AUDIT_ARCH_X86_64;
 }
 
-void do_syscall_64(unsigned long nr, struct pt_regs *regs);
+void do_syscall_64(struct pt_regs *regs, unsigned long nr);
 void do_int80_syscall_32(struct pt_regs *regs);
 long do_fast_syscall_32(struct pt_regs *regs);
 

arch/x86/kernel/cpu/common.c

@@ -1773,10 +1773,16 @@ void syscall_init(void)
 	wrmsrl_safe(MSR_IA32_SYSENTER_EIP, 0ULL);
 #endif
 
-	/* Flags to clear on syscall */
+	/*
+	 * Flags to clear on syscall; clear as much as possible
+	 * to minimize user space-kernel interference.
+	 */
 	wrmsrl(MSR_SYSCALL_MASK,
-	       X86_EFLAGS_TF|X86_EFLAGS_DF|X86_EFLAGS_IF|
-	       X86_EFLAGS_IOPL|X86_EFLAGS_AC|X86_EFLAGS_NT);
+	       X86_EFLAGS_CF|X86_EFLAGS_PF|X86_EFLAGS_AF|
+	       X86_EFLAGS_ZF|X86_EFLAGS_SF|X86_EFLAGS_TF|
+	       X86_EFLAGS_IF|X86_EFLAGS_DF|X86_EFLAGS_OF|
+	       X86_EFLAGS_IOPL|X86_EFLAGS_NT|X86_EFLAGS_RF|
+	       X86_EFLAGS_AC|X86_EFLAGS_ID);
 }
 
 #else	/* CONFIG_X86_64 */

arch/x86/kernel/head_64.S

@@ -62,7 +62,7 @@ SYM_CODE_START_NOALIGN(startup_64)
 	 */
 
 	/* Set up the stack for verify_cpu(), similar to initial_stack below */
-	leaq	(__end_init_task - SIZEOF_PTREGS)(%rip), %rsp
+	leaq	(__end_init_task - FRAME_SIZE)(%rip), %rsp
 
 	leaq	_text(%rip), %rdi
 	pushq	%rsi
@@ -343,10 +343,10 @@ SYM_DATA(initial_vc_handler,	.quad handle_vc_boot_ghcb)
 #endif
 
 /*
- * The SIZEOF_PTREGS gap is a convention which helps the in-kernel unwinder
+ * The FRAME_SIZE gap is a convention which helps the in-kernel unwinder
  * reliably detect the end of the stack.
  */
-SYM_DATA(initial_stack, .quad init_thread_union + THREAD_SIZE - SIZEOF_PTREGS)
+SYM_DATA(initial_stack, .quad init_thread_union + THREAD_SIZE - FRAME_SIZE)
 	__FINITDATA
 
 	__INIT

arch/x86/kernel/ptrace.c

@@ -911,7 +911,7 @@ static int putreg32(struct task_struct *child, unsigned regno, u32 value)
 		 * syscall with TS_COMPAT still set.
 		 */
 		regs->orig_ax = value;
-		if (syscall_get_nr(child, regs) >= 0)
+		if (syscall_get_nr(child, regs) != -1)
 			child->thread_info.status |= TS_I386_REGS_POKED;
 		break;
 

arch/x86/kernel/signal.c

@@ -713,7 +713,7 @@ handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 		save_v86_state((struct kernel_vm86_regs *) regs, VM86_SIGNAL);
 
 	/* Are we from a system call? */
-	if (syscall_get_nr(current, regs) >= 0) {
+	if (syscall_get_nr(current, regs) != -1) {
 		/* If so, check system call restarting.. */
 		switch (syscall_get_error(current, regs)) {
 		case -ERESTART_RESTARTBLOCK:
@@ -793,7 +793,7 @@ void arch_do_signal_or_restart(struct pt_regs *regs, bool has_signal)
 	}
 
 	/* Did we come from a system call? */
-	if (syscall_get_nr(current, regs) >= 0) {
+	if (syscall_get_nr(current, regs) != -1) {
 		/* Restart the system call - no handlers present */
 		switch (syscall_get_error(current, regs)) {
 		case -ERESTARTNOHAND:

tools/arch/x86/include/asm/asm.h

+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_ASM_H
+#define _ASM_X86_ASM_H
+
+#ifdef __ASSEMBLY__
+# define __ASM_FORM(x, ...)		x,## __VA_ARGS__
+# define __ASM_FORM_RAW(x, ...)		x,## __VA_ARGS__
+# define __ASM_FORM_COMMA(x, ...)	x,## __VA_ARGS__,
+#else
+#include <linux/stringify.h>
+# define __ASM_FORM(x, ...)		" " __stringify(x,##__VA_ARGS__) " "
+# define __ASM_FORM_RAW(x, ...)		    __stringify(x,##__VA_ARGS__)
+# define __ASM_FORM_COMMA(x, ...)	" " __stringify(x,##__VA_ARGS__) ","
+#endif
+
+#define _ASM_BYTES(x, ...)	__ASM_FORM(.byte x,##__VA_ARGS__ ;)
+
+#ifndef __x86_64__
+/* 32 bit */
+# define __ASM_SEL(a,b)		__ASM_FORM(a)
+# define __ASM_SEL_RAW(a,b)	__ASM_FORM_RAW(a)
+#else
+/* 64 bit */
+# define __ASM_SEL(a,b)		__ASM_FORM(b)
+# define __ASM_SEL_RAW(a,b)	__ASM_FORM_RAW(b)
+#endif
+
+#define __ASM_SIZE(inst, ...)	__ASM_SEL(inst##l##__VA_ARGS__, \
+					  inst##q##__VA_ARGS__)
+#define __ASM_REG(reg)         __ASM_SEL_RAW(e##reg, r##reg)
+
+#define _ASM_PTR	__ASM_SEL(.long, .quad)
+#define _ASM_ALIGN	__ASM_SEL(.balign 4, .balign 8)
+
+#define _ASM_MOV	__ASM_SIZE(mov)
+#define _ASM_INC	__ASM_SIZE(inc)
+#define _ASM_DEC	__ASM_SIZE(dec)
+#define _ASM_ADD	__ASM_SIZE(add)
+#define _ASM_SUB	__ASM_SIZE(sub)
+#define _ASM_XADD	__ASM_SIZE(xadd)
+#define _ASM_MUL	__ASM_SIZE(mul)
+
+#define _ASM_AX		__ASM_REG(ax)
+#define _ASM_BX		__ASM_REG(bx)
+#define _ASM_CX		__ASM_REG(cx)
+#define _ASM_DX		__ASM_REG(dx)
+#define _ASM_SP		__ASM_REG(sp)
+#define _ASM_BP		__ASM_REG(bp)
+#define _ASM_SI		__ASM_REG(si)
+#define _ASM_DI		__ASM_REG(di)
+
+#ifndef __x86_64__
+/* 32 bit */
+
+#define _ASM_ARG1	_ASM_AX
+#define _ASM_ARG2	_ASM_DX
+#define _ASM_ARG3	_ASM_CX
+
+#define _ASM_ARG1L	eax
+#define _ASM_ARG2L	edx
+#define _ASM_ARG3L	ecx
+
+#define _ASM_ARG1W	ax
+#define _ASM_ARG2W	dx
+#define _ASM_ARG3W	cx
+
+#define _ASM_ARG1B	al
+#define _ASM_ARG2B	dl
+#define _ASM_ARG3B	cl
+
+#else
+/* 64 bit */
+
+#define _ASM_ARG1	_ASM_DI
+#define _ASM_ARG2	_ASM_SI
+#define _ASM_ARG3	_ASM_DX
+#define _ASM_ARG4	_ASM_CX
+#define _ASM_ARG5	r8
+#define _ASM_ARG6	r9
+
+#define _ASM_ARG1Q	rdi
+#define _ASM_ARG2Q	rsi
+#define _ASM_ARG3Q	rdx
+#define _ASM_ARG4Q	rcx
+#define _ASM_ARG5Q	r8
+#define _ASM_ARG6Q	r9
+
+#define _ASM_ARG1L	edi
+#define _ASM_ARG2L	esi
+#define _ASM_ARG3L	edx
+#define _ASM_ARG4L	ecx
+#define _ASM_ARG5L	r8d
+#define _ASM_ARG6L	r9d
+
+#define _ASM_ARG1W	di
+#define _ASM_ARG2W	si
+#define _ASM_ARG3W	dx
+#define _ASM_ARG4W	cx
+#define _ASM_ARG5W	r8w
+#define _ASM_ARG6W	r9w
+
+#define _ASM_ARG1B	dil
+#define _ASM_ARG2B	sil
+#define _ASM_ARG3B	dl
+#define _ASM_ARG4B	cl
+#define _ASM_ARG5B	r8b
+#define _ASM_ARG6B	r9b
+
+#endif
+
+/*
+ * Macros to generate condition code outputs from inline assembly,
+ * The output operand must be type "bool".
+ */
+#ifdef __GCC_ASM_FLAG_OUTPUTS__
+# define CC_SET(c) "\n\t/* output condition code " #c "*/\n"
+# define CC_OUT(c) "=@cc" #c
+#else
+# define CC_SET(c) "\n\tset" #c " %[_cc_" #c "]\n"
+# define CC_OUT(c) [_cc_ ## c] "=qm"
+#endif
+
+#ifdef __KERNEL__
+
+/* Exception table entry */
+#ifdef __ASSEMBLY__
+# define _ASM_EXTABLE_HANDLE(from, to, handler)			\
+	.pushsection "__ex_table","a" ;				\
+	.balign 4 ;						\
+	.long (from) - . ;					\
+	.long (to) - . ;					\
+	.long (handler) - . ;					\
+	.popsection
+
+# define _ASM_EXTABLE(from, to)					\
+	_ASM_EXTABLE_HANDLE(from, to, ex_handler_default)
+
+# define _ASM_EXTABLE_UA(from, to)				\
+	_ASM_EXTABLE_HANDLE(from, to, ex_handler_uaccess)
+
+# define _ASM_EXTABLE_CPY(from, to)				\
+	_ASM_EXTABLE_HANDLE(from, to, ex_handler_copy)
+
+# define _ASM_EXTABLE_FAULT(from, to)				\
+	_ASM_EXTABLE_HANDLE(from, to, ex_handler_fault)
+
+# ifdef CONFIG_KPROBES
+#  define _ASM_NOKPROBE(entry)					\
+	.pushsection "_kprobe_blacklist","aw" ;			\
+	_ASM_ALIGN ;						\
+	_ASM_PTR (entry);					\
+	.popsection
+# else
+#  define _ASM_NOKPROBE(entry)
+# endif
+
+#else /* ! __ASSEMBLY__ */
+# define _EXPAND_EXTABLE_HANDLE(x) #x
+# define _ASM_EXTABLE_HANDLE(from, to, handler)			\
+	" .pushsection \"__ex_table\",\"a\"\n"			\
+	" .balign 4\n"						\
+	" .long (" #from ") - .\n"				\
+	" .long (" #to ") - .\n"				\
+	" .long (" _EXPAND_EXTABLE_HANDLE(handler) ") - .\n"	\
+	" .popsection\n"
+
+# define _ASM_EXTABLE(from, to)					\
+	_ASM_EXTABLE_HANDLE(from, to, ex_handler_default)
+
+# define _ASM_EXTABLE_UA(from, to)				\
+	_ASM_EXTABLE_HANDLE(from, to, ex_handler_uaccess)
+
+# define _ASM_EXTABLE_CPY(from, to)				\
+	_ASM_EXTABLE_HANDLE(from, to, ex_handler_copy)
+
+# define _ASM_EXTABLE_FAULT(from, to)				\
+	_ASM_EXTABLE_HANDLE(from, to, ex_handler_fault)
+
+/* For C file, we already have NOKPROBE_SYMBOL macro */
+
+/*
+ * This output constraint should be used for any inline asm which has a "call"
+ * instruction.  Otherwise the asm may be inserted before the frame pointer
+ * gets set up by the containing function.  If you forget to do this, objtool
+ * may print a "call without frame pointer save/setup" warning.
+ */
+register unsigned long current_stack_pointer asm(_ASM_SP);
+#define ASM_CALL_CONSTRAINT "+r" (current_stack_pointer)
+#endif /* __ASSEMBLY__ */
+
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_X86_ASM_H */

tools/arch/x86/include/asm/nops.h

@@ -2,6 +2,8 @@
 #ifndef _ASM_X86_NOPS_H
 #define _ASM_X86_NOPS_H
 
+#include <asm/asm.h>
+
 /*
  * Define nops for use with alternative() and for tracing.
  */
@@ -57,20 +59,14 @@
 
 #endif /* CONFIG_64BIT */
 
-#ifdef __ASSEMBLY__
-#define _ASM_MK_NOP(x) .byte x
-#else
-#define _ASM_MK_NOP(x) ".byte " __stringify(x) "\n"
-#endif
-
-#define ASM_NOP1 _ASM_MK_NOP(BYTES_NOP1)
-#define ASM_NOP2 _ASM_MK_NOP(BYTES_NOP2)
-#define ASM_NOP3 _ASM_MK_NOP(BYTES_NOP3)
-#define ASM_NOP4 _ASM_MK_NOP(BYTES_NOP4)
-#define ASM_NOP5 _ASM_MK_NOP(BYTES_NOP5)
-#define ASM_NOP6 _ASM_MK_NOP(BYTES_NOP6)
-#define ASM_NOP7 _ASM_MK_NOP(BYTES_NOP7)
-#define ASM_NOP8 _ASM_MK_NOP(BYTES_NOP8)
+#define ASM_NOP1 _ASM_BYTES(BYTES_NOP1)
+#define ASM_NOP2 _ASM_BYTES(BYTES_NOP2)
+#define ASM_NOP3 _ASM_BYTES(BYTES_NOP3)
+#define ASM_NOP4 _ASM_BYTES(BYTES_NOP4)
+#define ASM_NOP5 _ASM_BYTES(BYTES_NOP5)
+#define ASM_NOP6 _ASM_BYTES(BYTES_NOP6)
+#define ASM_NOP7 _ASM_BYTES(BYTES_NOP7)
+#define ASM_NOP8 _ASM_BYTES(BYTES_NOP8)
 
 #define ASM_NOP_MAX 8