x86: Change {JMP,CALL}_NOSPEC argument

In order to change the {JMP,CALL}_NOSPEC macros to call out-of-line
versions of the retpoline magic, we need to remove the '%' from the
argument, such that we can paste it onto symbol names.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lkml.kernel.org/r/20200428191700.151623523@infradead.org

arch/x86/crypto/aesni-intel_asm.S

@@ -2758,7 +2758,7 @@ SYM_FUNC_START(aesni_xts_crypt8)
 	pxor INC, STATE4
 	movdqu IV, 0x30(OUTP)
 
-	CALL_NOSPEC %r11
+	CALL_NOSPEC r11
 
 	movdqu 0x00(OUTP), INC
 	pxor INC, STATE1
@@ -2803,7 +2803,7 @@ SYM_FUNC_START(aesni_xts_crypt8)
 	_aesni_gf128mul_x_ble()
 	movups IV, (IVP)
 
-	CALL_NOSPEC %r11
+	CALL_NOSPEC r11
 
 	movdqu 0x40(OUTP), INC
 	pxor INC, STATE1

arch/x86/crypto/camellia-aesni-avx-asm_64.S

@@ -1228,7 +1228,7 @@ SYM_FUNC_START_LOCAL(camellia_xts_crypt_16way)
 	vpxor 14 * 16(%rax), %xmm15, %xmm14;
 	vpxor 15 * 16(%rax), %xmm15, %xmm15;
 
-	CALL_NOSPEC %r9;
+	CALL_NOSPEC r9;
 
 	addq $(16 * 16), %rsp;
 

arch/x86/crypto/camellia-aesni-avx2-asm_64.S

@@ -1339,7 +1339,7 @@ SYM_FUNC_START_LOCAL(camellia_xts_crypt_32way)
 	vpxor 14 * 32(%rax), %ymm15, %ymm14;
 	vpxor 15 * 32(%rax), %ymm15, %ymm15;
 
-	CALL_NOSPEC %r9;
+	CALL_NOSPEC r9;
 
 	addq $(16 * 32), %rsp;
 

arch/x86/crypto/crc32c-pcl-intel-asm_64.S

@@ -75,7 +75,7 @@
 
 .text
 SYM_FUNC_START(crc_pcl)
-#define    bufp		%rdi
+#define    bufp		rdi
 #define    bufp_dw	%edi
 #define    bufp_w	%di
 #define    bufp_b	%dil
@@ -105,9 +105,9 @@ SYM_FUNC_START(crc_pcl)
 	## 1) ALIGN:
 	################################################################
 
-	mov     bufp, bufptmp		# rdi = *buf
-	neg     bufp
-	and     $7, bufp		# calculate the unalignment amount of
+	mov     %bufp, bufptmp		# rdi = *buf
+	neg     %bufp
+	and     $7, %bufp		# calculate the unalignment amount of
 					# the address
 	je      proc_block		# Skip if aligned
 
@@ -123,13 +123,13 @@ SYM_FUNC_START(crc_pcl)
 do_align:
 	#### Calculate CRC of unaligned bytes of the buffer (if any)
 	movq    (bufptmp), tmp		# load a quadward from the buffer
-	add     bufp, bufptmp		# align buffer pointer for quadword
+	add     %bufp, bufptmp		# align buffer pointer for quadword
 					# processing
-	sub     bufp, len		# update buffer length
+	sub     %bufp, len		# update buffer length
 align_loop:
 	crc32b  %bl, crc_init_dw 	# compute crc32 of 1-byte
 	shr     $8, tmp			# get next byte
-	dec     bufp
+	dec     %bufp
 	jne     align_loop
 
 proc_block:
@@ -169,10 +169,10 @@ continue_block:
 	xor     crc2, crc2
 
 	## branch into array
-	lea	jump_table(%rip), bufp
-	movzxw  (bufp, %rax, 2), len
-	lea	crc_array(%rip), bufp
-	lea     (bufp, len, 1), bufp
+	lea	jump_table(%rip), %bufp
+	movzxw  (%bufp, %rax, 2), len
+	lea	crc_array(%rip), %bufp
+	lea     (%bufp, len, 1), %bufp
 	JMP_NOSPEC bufp
 
 	################################################################
@@ -218,9 +218,9 @@ LABEL crc_ %i
 	## 4) Combine three results:
 	################################################################
 
-	lea	(K_table-8)(%rip), bufp		# first entry is for idx 1
+	lea	(K_table-8)(%rip), %bufp		# first entry is for idx 1
 	shlq    $3, %rax			# rax *= 8
-	pmovzxdq (bufp,%rax), %xmm0		# 2 consts: K1:K2
+	pmovzxdq (%bufp,%rax), %xmm0		# 2 consts: K1:K2
 	leal	(%eax,%eax,2), %eax		# rax *= 3 (total *24)
 	subq    %rax, tmp			# tmp -= rax*24