Merge tag 'x86-asm-2024-05-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 asm updates from Ingo Molnar:

 - Clean up & fix asm() operand modifiers & constraints

 - Misc cleanups

* tag 'x86-asm-2024-05-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/alternatives: Remove a superfluous newline in _static_cpu_has()
  x86/asm/64: Clean up memset16(), memset32(), memset64() assembly constraints in <asm/string_64.h>
  x86/asm: Use "m" operand constraint in WRUSSQ asm template
  x86/asm: Use %a instead of %P operand modifier in asm templates
  x86/asm: Use %c/%n instead of %P operand modifier in asm templates
  x86/asm: Remove %P operand modifier from altinstr asm templates

arch/x86/boot/main.c

@@ -119,8 +119,8 @@ static void init_heap(void)
 	char *stack_end;
 
 	if (boot_params.hdr.loadflags & CAN_USE_HEAP) {
-		asm("leal %P1(%%esp),%0"
-		    : "=r" (stack_end) : "i" (-STACK_SIZE));
+		asm("leal %n1(%%esp),%0"
+		    : "=r" (stack_end) : "i" (STACK_SIZE));
 
 		heap_end = (char *)
 			((size_t)boot_params.hdr.heap_end_ptr + 0x200);

arch/x86/include/asm/alternative.h

@@ -307,7 +307,7 @@ static inline int alternatives_text_reserved(void *start, void *end)
 
 /* Like alternative_io, but for replacing a direct call with another one. */
 #define alternative_call(oldfunc, newfunc, ft_flags, output, input...)	\
-	asm_inline volatile (ALTERNATIVE("call %P[old]", "call %P[new]", ft_flags) \
+	asm_inline volatile (ALTERNATIVE("call %c[old]", "call %c[new]", ft_flags) \
 		: output : [old] "i" (oldfunc), [new] "i" (newfunc), ## input)
 
 /*
@@ -318,8 +318,8 @@ static inline int alternatives_text_reserved(void *start, void *end)
  */
 #define alternative_call_2(oldfunc, newfunc1, ft_flags1, newfunc2, ft_flags2, \
 			   output, input...)				\
-	asm_inline volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", ft_flags1,\
-		"call %P[new2]", ft_flags2)				      \
+	asm_inline volatile (ALTERNATIVE_2("call %c[old]", "call %c[new1]", ft_flags1, \
+		"call %c[new2]", ft_flags2)				\
 		: output, ASM_CALL_CONSTRAINT				\
 		: [old] "i" (oldfunc), [new1] "i" (newfunc1),		\
 		  [new2] "i" (newfunc2), ## input)

arch/x86/include/asm/apic.h

@@ -92,7 +92,7 @@ static inline void native_apic_mem_write(u32 reg, u32 v)
 {
 	volatile u32 *addr = (volatile u32 *)(APIC_BASE + reg);
 
-	alternative_io("movl %0, %P1", "xchgl %0, %P1", X86_BUG_11AP,
+	alternative_io("movl %0, %1", "xchgl %0, %1", X86_BUG_11AP,
 		       ASM_OUTPUT2("=r" (v), "=m" (*addr)),
 		       ASM_OUTPUT2("0" (v), "m" (*addr)));
 }

arch/x86/include/asm/atomic64_32.h

@@ -50,7 +50,7 @@ static __always_inline s64 arch_atomic64_read_nonatomic(const atomic64_t *v)
 
 #ifdef CONFIG_X86_CMPXCHG64
 #define __alternative_atomic64(f, g, out, in...) \
-	asm volatile("call %P[func]" \
+	asm volatile("call %c[func]" \
 		     : out : [func] "i" (atomic64_##g##_cx8), ## in)
 
 #define ATOMIC64_DECL(sym) ATOMIC64_DECL_ONE(sym##_cx8)

arch/x86/include/asm/cpufeature.h

@@ -172,11 +172,10 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
  */
 static __always_inline bool _static_cpu_has(u16 bit)
 {
-	asm goto(
-		ALTERNATIVE_TERNARY("jmp 6f", %P[feature], "", "jmp %l[t_no]")
+	asm goto(ALTERNATIVE_TERNARY("jmp 6f", %c[feature], "", "jmp %l[t_no]")
 		".pushsection .altinstr_aux,\"ax\"\n"
 		"6:\n"
-		" testb %[bitnum]," _ASM_RIP(%P[cap_byte]) "\n"
+		" testb %[bitnum], %a[cap_byte]\n"
 		" jnz %l[t_yes]\n"
 		" jmp %l[t_no]\n"
 		".popsection\n"

arch/x86/include/asm/irq_stack.h

@@ -100,7 +100,7 @@
 }
 
 #define ASM_CALL_ARG0							\
-	"call %P[__func]				\n"		\
+	"call %c[__func]				\n"		\
 	ASM_REACHABLE
 
 #define ASM_CALL_ARG1							\

arch/x86/include/asm/processor.h

@@ -586,7 +586,7 @@ extern char			ignore_fpu_irq;
 # define BASE_PREFETCH		""
 # define ARCH_HAS_PREFETCH
 #else
-# define BASE_PREFETCH		"prefetcht0 %P1"
+# define BASE_PREFETCH		"prefetcht0 %1"
 #endif
 
 /*
@@ -597,7 +597,7 @@ extern char			ignore_fpu_irq;
  */
 static inline void prefetch(const void *x)
 {
-	alternative_input(BASE_PREFETCH, "prefetchnta %P1",
+	alternative_input(BASE_PREFETCH, "prefetchnta %1",
 			  X86_FEATURE_XMM,
 			  "m" (*(const char *)x));
 }
@@ -609,7 +609,7 @@ static inline void prefetch(const void *x)
  */
 static __always_inline void prefetchw(const void *x)
 {
-	alternative_input(BASE_PREFETCH, "prefetchw %P1",
+	alternative_input(BASE_PREFETCH, "prefetchw %1",
 			  X86_FEATURE_3DNOWPREFETCH,
 			  "m" (*(const char *)x));
 }

arch/x86/include/asm/special_insns.h

@@ -182,8 +182,8 @@ static __always_inline void clflush(volatile void *__p)
 
 static inline void clflushopt(volatile void *__p)
 {
-	alternative_io(".byte 0x3e; clflush %P0",
-		       ".byte 0x66; clflush %P0",
+	alternative_io(".byte 0x3e; clflush %0",
+		       ".byte 0x66; clflush %0",
 		       X86_FEATURE_CLFLUSHOPT,
 		       "+m" (*(volatile char __force *)__p));
 }
@@ -205,9 +205,9 @@ static inline void clwb(volatile void *__p)
 #ifdef CONFIG_X86_USER_SHADOW_STACK
 static inline int write_user_shstk_64(u64 __user *addr, u64 val)
 {
-	asm goto("1: wrussq %[val], (%[addr])\n"
+	asm goto("1: wrussq %[val], %[addr]\n"
 			  _ASM_EXTABLE(1b, %l[fail])
-			  :: [addr] "r" (addr), [val] "r" (val)
+			  :: [addr] "m" (*addr), [val] "r" (val)
 			  :: fail);
 	return 0;
 fail:

arch/x86/include/asm/string_64.h

@@ -30,37 +30,40 @@ void *__memset(void *s, int c, size_t n);
 #define __HAVE_ARCH_MEMSET16
 static inline void *memset16(uint16_t *s, uint16_t v, size_t n)
 {
-	long d0, d1;
-	asm volatile("rep\n\t"
-		     "stosw"
-		     : "=&c" (d0), "=&D" (d1)
-		     : "a" (v), "1" (s), "0" (n)
-		     : "memory");
-	return s;
+	const __auto_type s0 = s;
+	asm volatile (
+		"rep stosw"
+		: "+D" (s), "+c" (n)
+		: "a" (v)
+		: "memory"
+	);
+	return s0;
 }
 
 #define __HAVE_ARCH_MEMSET32
 static inline void *memset32(uint32_t *s, uint32_t v, size_t n)
 {
-	long d0, d1;
-	asm volatile("rep\n\t"
-		     "stosl"
-		     : "=&c" (d0), "=&D" (d1)
-		     : "a" (v), "1" (s), "0" (n)
-		     : "memory");
-	return s;
+	const __auto_type s0 = s;
+	asm volatile (
+		"rep stosl"
+		: "+D" (s), "+c" (n)
+		: "a" (v)
+		: "memory"
+	);
+	return s0;
 }
 
 #define __HAVE_ARCH_MEMSET64
 static inline void *memset64(uint64_t *s, uint64_t v, size_t n)
 {
-	long d0, d1;
-	asm volatile("rep\n\t"
-		     "stosq"
-		     : "=&c" (d0), "=&D" (d1)
-		     : "a" (v), "1" (s), "0" (n)
-		     : "memory");
-	return s;
+	const __auto_type s0 = s;
+	asm volatile (
+		"rep stosq"
+		: "+D" (s), "+c" (n)
+		: "a" (v)
+		: "memory"
+	);
+	return s0;
 }
 #endif
 

arch/x86/include/asm/uaccess.h

@@ -78,7 +78,7 @@ extern int __get_user_bad(void);
 	int __ret_gu;							\
 	register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX);		\
 	__chk_user_ptr(ptr);						\
-	asm volatile("call __" #fn "_%P4"				\
+	asm volatile("call __" #fn "_%c4"				\
 		     : "=a" (__ret_gu), "=r" (__val_gu),		\
 			ASM_CALL_CONSTRAINT				\
 		     : "0" (ptr), "i" (sizeof(*(ptr))));		\
@@ -177,7 +177,7 @@ extern void __put_user_nocheck_8(void);
 	__chk_user_ptr(__ptr);						\
 	__ptr_pu = __ptr;						\
 	__val_pu = __x;							\
-	asm volatile("call __" #fn "_%P[size]"				\
+	asm volatile("call __" #fn "_%c[size]"				\
 		     : "=c" (__ret_pu),					\
 			ASM_CALL_CONSTRAINT				\
 		     : "0" (__ptr_pu),					\