Merge tag 'x86-asm-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 assembly code updates from Ingo Molnar:

 - Micro-optimize the x86 bitops code

 - Define target-specific {raw,this}_cpu_try_cmpxchg{64,128}() to
   improve code generation

 - Define and use raw_cpu_try_cmpxchg() preempt_count_set()

 - Do not clobber %rsi in percpu_{try_,}cmpxchg{64,128}_op

 - Remove the unused __sw_hweight64() implementation on x86-32

 - Misc fixes and cleanups

* tag 'x86-asm-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/lib: Address kernel-doc warnings
  x86/entry: Fix typos in comments
  x86/entry: Remove unused argument %rsi passed to exc_nmi()
  x86/bitops: Remove unused __sw_hweight64() assembly implementation on x86-32
  x86/percpu: Do not clobber %rsi in percpu_{try_,}cmpxchg{64,128}_op
  x86/percpu: Use raw_cpu_try_cmpxchg() in preempt_count_set()
  x86/percpu: Define raw_cpu_try_cmpxchg and this_cpu_try_cmpxchg()
  x86/percpu: Define {raw,this}_cpu_try_cmpxchg{64,128}
  x86/asm/bitops: Use __builtin_clz{l|ll} to evaluate constant expressions

arch/x86/entry/entry_64.S

@@ -1163,8 +1163,8 @@ SYM_CODE_START(asm_exc_nmi)
 	 * anyway.
 	 *
 	 * To handle this case we do the following:
-	 *  Check the a special location on the stack that contains
-	 *  a variable that is set when NMIs are executing.
+	 *  Check a special location on the stack that contains a
+	 *  variable that is set when NMIs are executing.
 	 *  The interrupted task's stack is also checked to see if it
 	 *  is an NMI stack.
 	 *  If the variable is not set and the stack is not the NMI
@@ -1237,7 +1237,6 @@ SYM_CODE_START(asm_exc_nmi)
 	 */
 
 	movq	%rsp, %rdi
-	movq	$-1, %rsi
 	call	exc_nmi
 
 	/*
@@ -1295,8 +1294,8 @@ SYM_CODE_START(asm_exc_nmi)
 	 * end_repeat_nmi, then we are a nested NMI.  We must not
 	 * modify the "iret" frame because it's being written by
 	 * the outer NMI.  That's okay; the outer NMI handler is
-	 * about to about to call exc_nmi() anyway, so we can just
-	 * resume the outer NMI.
+	 * about to call exc_nmi() anyway, so we can just resume
+	 * the outer NMI.
 	 */
 
 	movq	$repeat_nmi, %rdx
@@ -1451,7 +1450,6 @@ end_repeat_nmi:
 	UNWIND_HINT_REGS
 
 	movq	%rsp, %rdi
-	movq	$-1, %rsi
 	call	exc_nmi
 
 	/* Always restore stashed SPEC_CTRL value (see paranoid_entry) */

arch/x86/include/asm/bitops.h

@@ -293,6 +293,9 @@ static __always_inline unsigned long variable_ffz(unsigned long word)
  */
 static __always_inline unsigned long __fls(unsigned long word)
 {
+	if (__builtin_constant_p(word))
+		return BITS_PER_LONG - 1 - __builtin_clzl(word);
+
 	asm("bsr %1,%0"
 	    : "=r" (word)
 	    : "rm" (word));
@@ -360,6 +363,9 @@ static __always_inline int fls(unsigned int x)
 {
 	int r;
 
+	if (__builtin_constant_p(x))
+		return x ? 32 - __builtin_clz(x) : 0;
+
 #ifdef CONFIG_X86_64
 	/*
 	 * AMD64 says BSRL won't clobber the dest reg if x==0; Intel64 says the
@@ -401,6 +407,9 @@ static __always_inline int fls(unsigned int x)
 static __always_inline int fls64(__u64 x)
 {
 	int bitpos = -1;
+
+	if (__builtin_constant_p(x))
+		return x ? 64 - __builtin_clzll(x) : 0;
 	/*
 	 * AMD64 says BSRQ won't clobber the dest reg if x==0; Intel64 says the
 	 * dest reg is undefined if x==0, but their CPU architect says its

arch/x86/include/asm/percpu.h

@@ -210,6 +210,25 @@ do {									\
 	(typeof(_var))(unsigned long) pco_old__;			\
 })
 
+#define percpu_try_cmpxchg_op(size, qual, _var, _ovalp, _nval)		\
+({									\
+	bool success;							\
+	__pcpu_type_##size *pco_oval__ = (__pcpu_type_##size *)(_ovalp); \
+	__pcpu_type_##size pco_old__ = *pco_oval__;			\
+	__pcpu_type_##size pco_new__ = __pcpu_cast_##size(_nval);	\
+	asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]",		\
+				    __percpu_arg([var]))		\
+		  CC_SET(z)						\
+		  : CC_OUT(z) (success),				\
+		    [oval] "+a" (pco_old__),				\
+		    [var] "+m" (_var)					\
+		  : [nval] __pcpu_reg_##size(, pco_new__)		\
+		  : "memory");						\
+	if (unlikely(!success))						\
+		*pco_oval__ = pco_old__;				\
+	likely(success);						\
+})
+
 #if defined(CONFIG_X86_32) && !defined(CONFIG_UML)
 #define percpu_cmpxchg64_op(size, qual, _var, _oval, _nval)		\
 ({									\
@@ -223,26 +242,63 @@ do {									\
 	old__.var = _oval;						\
 	new__.var = _nval;						\
 									\
-	asm qual (ALTERNATIVE("leal %P[var], %%esi; call this_cpu_cmpxchg8b_emu", \
+	asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
 			      "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
 		  : [var] "+m" (_var),					\
 		    "+a" (old__.low),					\
 		    "+d" (old__.high)					\
 		  : "b" (new__.low),					\
-		    "c" (new__.high)					\
-		  : "memory", "esi");					\
+		    "c" (new__.high),					\
+		    "S" (&(_var))					\
+		  : "memory");						\
 									\
 	old__.var;							\
 })
 
 #define raw_cpu_cmpxchg64(pcp, oval, nval)	percpu_cmpxchg64_op(8,         , pcp, oval, nval)
 #define this_cpu_cmpxchg64(pcp, oval, nval)	percpu_cmpxchg64_op(8, volatile, pcp, oval, nval)
+
+#define percpu_try_cmpxchg64_op(size, qual, _var, _ovalp, _nval)	\
+({									\
+	bool success;							\
+	u64 *_oval = (u64 *)(_ovalp);					\
+	union {								\
+		u64 var;						\
+		struct {						\
+			u32 low, high;					\
+		};							\
+	} old__, new__;							\
+									\
+	old__.var = *_oval;						\
+	new__.var = _nval;						\
+									\
+	asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
+			      "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
+		  CC_SET(z)						\
+		  : CC_OUT(z) (success),				\
+		    [var] "+m" (_var),					\
+		    "+a" (old__.low),					\
+		    "+d" (old__.high)					\
+		  : "b" (new__.low),					\
+		    "c" (new__.high),					\
+		    "S" (&(_var))					\
+		  : "memory");						\
+	if (unlikely(!success))						\
+		*_oval = old__.var;					\
+	likely(success);						\
+})
+
+#define raw_cpu_try_cmpxchg64(pcp, ovalp, nval)		percpu_try_cmpxchg64_op(8,         , pcp, ovalp, nval)
+#define this_cpu_try_cmpxchg64(pcp, ovalp, nval)	percpu_try_cmpxchg64_op(8, volatile, pcp, ovalp, nval)
 #endif
 
 #ifdef CONFIG_X86_64
 #define raw_cpu_cmpxchg64(pcp, oval, nval)	percpu_cmpxchg_op(8,         , pcp, oval, nval);
 #define this_cpu_cmpxchg64(pcp, oval, nval)	percpu_cmpxchg_op(8, volatile, pcp, oval, nval);
 
+#define raw_cpu_try_cmpxchg64(pcp, ovalp, nval)		percpu_try_cmpxchg_op(8,         , pcp, ovalp, nval);
+#define this_cpu_try_cmpxchg64(pcp, ovalp, nval)	percpu_try_cmpxchg_op(8, volatile, pcp, ovalp, nval);
+
 #define percpu_cmpxchg128_op(size, qual, _var, _oval, _nval)		\
 ({									\
 	union {								\
@@ -255,20 +311,54 @@ do {									\
 	old__.var = _oval;						\
 	new__.var = _nval;						\
 									\
-	asm qual (ALTERNATIVE("leaq %P[var], %%rsi; call this_cpu_cmpxchg16b_emu", \
+	asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
 			      "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
 		  : [var] "+m" (_var),					\
 		    "+a" (old__.low),					\
 		    "+d" (old__.high)					\
 		  : "b" (new__.low),					\
-		    "c" (new__.high)					\
-		  : "memory", "rsi");					\
+		    "c" (new__.high),					\
+		    "S" (&(_var))					\
+		  : "memory");						\
 									\
 	old__.var;							\
 })
 
 #define raw_cpu_cmpxchg128(pcp, oval, nval)	percpu_cmpxchg128_op(16,         , pcp, oval, nval)
 #define this_cpu_cmpxchg128(pcp, oval, nval)	percpu_cmpxchg128_op(16, volatile, pcp, oval, nval)
+
+#define percpu_try_cmpxchg128_op(size, qual, _var, _ovalp, _nval)	\
+({									\
+	bool success;							\
+	u128 *_oval = (u128 *)(_ovalp);					\
+	union {								\
+		u128 var;						\
+		struct {						\
+			u64 low, high;					\
+		};							\
+	} old__, new__;							\
+									\
+	old__.var = *_oval;						\
+	new__.var = _nval;						\
+									\
+	asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
+			      "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
+		  CC_SET(z)						\
+		  : CC_OUT(z) (success),				\
+		    [var] "+m" (_var),					\
+		    "+a" (old__.low),					\
+		    "+d" (old__.high)					\
+		  : "b" (new__.low),					\
+		    "c" (new__.high),					\
+		    "S" (&(_var))					\
+		  : "memory");						\
+	if (unlikely(!success))						\
+		*_oval = old__.var;					\
+	likely(success);						\
+})
+
+#define raw_cpu_try_cmpxchg128(pcp, ovalp, nval)	percpu_try_cmpxchg128_op(16,         , pcp, ovalp, nval)
+#define this_cpu_try_cmpxchg128(pcp, ovalp, nval)	percpu_try_cmpxchg128_op(16, volatile, pcp, ovalp, nval)
 #endif
 
 /*
@@ -343,6 +433,9 @@ do {									\
 #define raw_cpu_cmpxchg_1(pcp, oval, nval)	percpu_cmpxchg_op(1, , pcp, oval, nval)
 #define raw_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(2, , pcp, oval, nval)
 #define raw_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(4, , pcp, oval, nval)
+#define raw_cpu_try_cmpxchg_1(pcp, ovalp, nval)	percpu_try_cmpxchg_op(1, , pcp, ovalp, nval)
+#define raw_cpu_try_cmpxchg_2(pcp, ovalp, nval)	percpu_try_cmpxchg_op(2, , pcp, ovalp, nval)
+#define raw_cpu_try_cmpxchg_4(pcp, ovalp, nval)	percpu_try_cmpxchg_op(4, , pcp, ovalp, nval)
 
 #define this_cpu_add_return_1(pcp, val)		percpu_add_return_op(1, volatile, pcp, val)
 #define this_cpu_add_return_2(pcp, val)		percpu_add_return_op(2, volatile, pcp, val)
@@ -350,6 +443,9 @@ do {									\
 #define this_cpu_cmpxchg_1(pcp, oval, nval)	percpu_cmpxchg_op(1, volatile, pcp, oval, nval)
 #define this_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(2, volatile, pcp, oval, nval)
 #define this_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(4, volatile, pcp, oval, nval)
+#define this_cpu_try_cmpxchg_1(pcp, ovalp, nval)	percpu_try_cmpxchg_op(1, volatile, pcp, ovalp, nval)
+#define this_cpu_try_cmpxchg_2(pcp, ovalp, nval)	percpu_try_cmpxchg_op(2, volatile, pcp, ovalp, nval)
+#define this_cpu_try_cmpxchg_4(pcp, ovalp, nval)	percpu_try_cmpxchg_op(4, volatile, pcp, ovalp, nval)
 
 /*
  * Per cpu atomic 64 bit operations are only available under 64 bit.
@@ -364,6 +460,7 @@ do {									\
 #define raw_cpu_add_return_8(pcp, val)		percpu_add_return_op(8, , pcp, val)
 #define raw_cpu_xchg_8(pcp, nval)		raw_percpu_xchg_op(pcp, nval)
 #define raw_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(8, , pcp, oval, nval)
+#define raw_cpu_try_cmpxchg_8(pcp, ovalp, nval)	percpu_try_cmpxchg_op(8, , pcp, ovalp, nval)
 
 #define this_cpu_read_8(pcp)			percpu_from_op(8, volatile, "mov", pcp)
 #define this_cpu_write_8(pcp, val)		percpu_to_op(8, volatile, "mov", (pcp), val)
@@ -373,6 +470,7 @@ do {									\
 #define this_cpu_add_return_8(pcp, val)		percpu_add_return_op(8, volatile, pcp, val)
 #define this_cpu_xchg_8(pcp, nval)		percpu_xchg_op(8, volatile, pcp, nval)
 #define this_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(8, volatile, pcp, oval, nval)
+#define this_cpu_try_cmpxchg_8(pcp, ovalp, nval)	percpu_try_cmpxchg_op(8, volatile, pcp, ovalp, nval)
 #endif
 
 static __always_inline bool x86_this_cpu_constant_test_bit(unsigned int nr,

arch/x86/include/asm/preempt.h

@@ -31,11 +31,11 @@ static __always_inline void preempt_count_set(int pc)
 {
 	int old, new;
 
+	old = raw_cpu_read_4(pcpu_hot.preempt_count);
 	do {
-		old = raw_cpu_read_4(pcpu_hot.preempt_count);
 		new = (old & PREEMPT_NEED_RESCHED) |
 			(pc & ~PREEMPT_NEED_RESCHED);
-	} while (raw_cpu_cmpxchg_4(pcpu_hot.preempt_count, old, new) != old);
+	} while (!raw_cpu_try_cmpxchg_4(pcpu_hot.preempt_count, &old, new));
 }
 
 /*

arch/x86/lib/csum-wrappers_64.c

@@ -14,8 +14,6 @@
  * @src: source address (user space)
  * @dst: destination address
  * @len: number of bytes to be copied.
- * @isum: initial sum that is added into the result (32bit unfolded)
- * @errp: set to -EFAULT for an bad source address.
  *
  * Returns an 32bit unfolded checksum of the buffer.
  * src and dst are best aligned to 64bits.
@@ -38,8 +36,6 @@ csum_and_copy_from_user(const void __user *src, void *dst, int len)
  * @src: source address
  * @dst: destination address (user space)
  * @len: number of bytes to be copied.
- * @isum: initial sum that is added into the result (32bit unfolded)
- * @errp: set to -EFAULT for an bad destination address.
  *
  * Returns an 32bit unfolded checksum of the buffer.
  * src and dst are best aligned to 64bits.
@@ -62,7 +58,6 @@ csum_and_copy_to_user(const void *src, void __user *dst, int len)
  * @src: source address
  * @dst: destination address
  * @len: number of bytes to be copied.
- * @sum: initial sum that is added into the result (32bit unfolded)
  *
  * Returns an 32bit unfolded checksum of the buffer.
  */

arch/x86/lib/hweight.S

@@ -36,8 +36,12 @@ SYM_FUNC_START(__sw_hweight32)
 SYM_FUNC_END(__sw_hweight32)
 EXPORT_SYMBOL(__sw_hweight32)
 
-SYM_FUNC_START(__sw_hweight64)
+/*
+ * No 32-bit variant, because it's implemented as an inline wrapper
+ * on top of __arch_hweight32():
+ */
 #ifdef CONFIG_X86_64
+SYM_FUNC_START(__sw_hweight64)
 	pushq   %rdi
 	pushq   %rdx
 
@@ -66,18 +70,6 @@ SYM_FUNC_START(__sw_hweight64)
 	popq    %rdx
 	popq    %rdi
 	RET
-#else /* CONFIG_X86_32 */
-	/* We're getting an u64 arg in (%eax,%edx): unsigned long hweight64(__u64 w) */
-	pushl   %ecx
-
-	call    __sw_hweight32
-	movl    %eax, %ecx                      # stash away result
-	movl    %edx, %eax                      # second part of input
-	call    __sw_hweight32
-	addl    %ecx, %eax                      # result
-
-	popl    %ecx
-	RET
-#endif
 SYM_FUNC_END(__sw_hweight64)
 EXPORT_SYMBOL(__sw_hweight64)
+#endif