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

2 files changed, 6 insertions, 19 deletions

diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c
index 145f9a0bde29..f4df4d241526 100644
--- a/arch/x86/lib/csum-wrappers_64.c
+++ b/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.
  */
diff --git a/arch/x86/lib/hweight.S b/arch/x86/lib/hweight.S
index 5e5e9e3f8fb7..774bdf3e6f0a 100644
--- a/arch/x86/lib/hweight.S
+++ b/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