[PATCH v2 12/18] x86: merge ip_fast_csum() for 32bit and 64bit

[Al Viro]

Identical, except that 32bit version uses asm volatile where 64bit
one uses plain asm.  The former had become pointless when memory
clobber got added to both versions...

Signed-off-by: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
---
 arch/x86/include/asm/checksum.h    | 43 ++++++++++++++++++++++++++++++
 arch/x86/include/asm/checksum_32.h | 37 -------------------------
 arch/x86/include/asm/checksum_64.h | 43 ------------------------------
 3 files changed, 43 insertions(+), 80 deletions(-)

diff --git a/arch/x86/include/asm/checksum.h b/arch/x86/include/asm/checksum.h
index eaa5dda09bee..5e617a380537 100644
--- a/arch/x86/include/asm/checksum.h
+++ b/arch/x86/include/asm/checksum.h
@@ -26,6 +26,49 @@ static inline __sum16 csum_fold(__wsum sum)
 	return (__force __sum16)(~(__force u32)sum >> 16);
 }
 
+/*
+ *	This is a version of ip_compute_csum() optimized for IP headers,
+ *	which always checksum on 4 octet boundaries.
+ *
+ *	By Jorge Cwik <jorge@xxxxxxxxxxxxxxxxx>, adapted for linux by
+ *	Arnt Gulbrandsen.
+ */
+
+/**
+ * ip_fast_csum - Compute the IPv4 header checksum efficiently.
+ * iph: ipv4 header
+ * ihl: length of header / 4
+ */
+static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
+{
+	unsigned int sum;
+
+	asm("  movl (%1), %0\n"
+	    "  subl $4, %2\n"
+	    "  jbe 2f\n"
+	    "  addl 4(%1), %0\n"
+	    "  adcl 8(%1), %0\n"
+	    "  adcl 12(%1), %0\n"
+	    "1: adcl 16(%1), %0\n"
+	    "  lea 4(%1), %1\n"
+	    "  decl %2\n"
+	    "  jne	1b\n"
+	    "  adcl $0, %0\n"
+	    "  movl %0, %2\n"
+	    "  shrl $16, %0\n"
+	    "  addw %w2, %w0\n"
+	    "  adcl $0, %0\n"
+	    "  notl %0\n"
+	    "2:"
+	/* Since the input registers which are loaded with iph and ihl
+	   are modified, we must also specify them as outputs, or gcc
+	   will assume they contain their original values. */
+	    : "=r" (sum), "=r" (iph), "=r" (ihl)
+	    : "1" (iph), "2" (ihl)
+	    : "memory");
+	return (__force __sum16)sum;
+}
+
 # ifdef CONFIG_X86_32
 #  include <asm/checksum_32.h>
 # else
diff --git a/arch/x86/include/asm/checksum_32.h b/arch/x86/include/asm/checksum_32.h
index 4e96d0473f88..d920e6c335bc 100644
--- a/arch/x86/include/asm/checksum_32.h
+++ b/arch/x86/include/asm/checksum_32.h
@@ -55,43 +55,6 @@ static inline __wsum_fault csum_and_copy_from_user(const void __user *src,
 	return ret;
 }
 
-/*
- *	This is a version of ip_compute_csum() optimized for IP headers,
- *	which always checksum on 4 octet boundaries.
- *
- *	By Jorge Cwik <jorge@xxxxxxxxxxxxxxxxx>, adapted for linux by
- *	Arnt Gulbrandsen.
- */
-static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
-{
-	unsigned int sum;
-
-	asm volatile("movl (%1), %0	;\n"
-		     "subl $4, %2	;\n"
-		     "jbe 2f		;\n"
-		     "addl 4(%1), %0	;\n"
-		     "adcl 8(%1), %0	;\n"
-		     "adcl 12(%1), %0;\n"
-		     "1:	adcl 16(%1), %0	;\n"
-		     "lea 4(%1), %1	;\n"
-		     "decl %2	;\n"
-		     "jne 1b		;\n"
-		     "adcl $0, %0	;\n"
-		     "movl %0, %2	;\n"
-		     "shrl $16, %0	;\n"
-		     "addw %w2, %w0	;\n"
-		     "adcl $0, %0	;\n"
-		     "notl %0	;\n"
-		     "2:		;\n"
-	/* Since the input registers which are loaded with iph and ihl
-	   are modified, we must also specify them as outputs, or gcc
-	   will assume they contain their original values. */
-		     : "=r" (sum), "=r" (iph), "=r" (ihl)
-		     : "1" (iph), "2" (ihl)
-		     : "memory");
-	return (__force __sum16)sum;
-}
-
 static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
 					__u32 len, __u8 proto,
 					__wsum sum)
diff --git a/arch/x86/include/asm/checksum_64.h b/arch/x86/include/asm/checksum_64.h
index d261b4124ca6..b80c82590d8d 100644
--- a/arch/x86/include/asm/checksum_64.h
+++ b/arch/x86/include/asm/checksum_64.h
@@ -11,49 +11,6 @@
 #include <linux/compiler.h>
 #include <asm/byteorder.h>
 
-/*
- *	This is a version of ip_compute_csum() optimized for IP headers,
- *	which always checksum on 4 octet boundaries.
- *
- *	By Jorge Cwik <jorge@xxxxxxxxxxxxxxxxx>, adapted for linux by
- *	Arnt Gulbrandsen.
- */
-
-/**
- * ip_fast_csum - Compute the IPv4 header checksum efficiently.
- * iph: ipv4 header
- * ihl: length of header / 4
- */
-static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
-{
-	unsigned int sum;
-
-	asm("  movl (%1), %0\n"
-	    "  subl $4, %2\n"
-	    "  jbe 2f\n"
-	    "  addl 4(%1), %0\n"
-	    "  adcl 8(%1), %0\n"
-	    "  adcl 12(%1), %0\n"
-	    "1: adcl 16(%1), %0\n"
-	    "  lea 4(%1), %1\n"
-	    "  decl %2\n"
-	    "  jne	1b\n"
-	    "  adcl $0, %0\n"
-	    "  movl %0, %2\n"
-	    "  shrl $16, %0\n"
-	    "  addw %w2, %w0\n"
-	    "  adcl $0, %0\n"
-	    "  notl %0\n"
-	    "2:"
-	/* Since the input registers which are loaded with iph and ihl
-	   are modified, we must also specify them as outputs, or gcc
-	   will assume they contain their original values. */
-	    : "=r" (sum), "=r" (iph), "=r" (ihl)
-	    : "1" (iph), "2" (ihl)
-	    : "memory");
-	return (__force __sum16)sum;
-}
-
 /**
  * csum_tcpup_nofold - Compute an IPv4 pseudo header checksum.
  * @saddr: source address
-- 
2.39.2