Merge branch 'work.csum_and_copy' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull copy_and_csum cleanups from Al Viro:
 "Saner calling conventions for csum_and_copy_..._user() and friends"

[ Removing 800+ lines of code and cleaning stuff up is good  - Linus ]

* 'work.csum_and_copy' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  ppc: propagate the calling conventions change down to csum_partial_copy_generic()
  amd64: switch csum_partial_copy_generic() to new calling conventions
  sparc64: propagate the calling convention changes down to __csum_partial_copy_...()
  xtensa: propagate the calling conventions change down into csum_partial_copy_generic()
  mips: propagate the calling convention change down into __csum_partial_copy_..._user()
  mips: __csum_partial_copy_kernel() has no users left
  mips: csum_and_copy_{to,from}_user() are never called under KERNEL_DS
  sparc32: propagate the calling conventions change down to __csum_partial_copy_sparc_generic()
  i386: propagate the calling conventions change down to csum_partial_copy_generic()
  sh: propage the calling conventions change down to csum_partial_copy_generic()
  m68k: get rid of zeroing destination on error in csum_and_copy_from_user()
  arm: propagate the calling convention changes down to csum_partial_copy_from_user()
  alpha: propagate the calling convention changes down to csum_partial_copy.c helpers
  saner calling conventions for csum_and_copy_..._user()
  csum_and_copy_..._user(): pass 0xffffffff instead of 0 as initial sum
  csum_partial_copy_nocheck(): drop the last argument
  unify generic instances of csum_partial_copy_nocheck()
  icmp_push_reply(): reorder adding the checksum up
  skb_copy_and_csum_bits(): don't bother with the last argument

44 files changed, 566 insertions, 1399 deletions

diff --git a/arch/alpha/include/asm/checksum.h b/arch/alpha/include/asm/checksum.h
index 0eac81624d01..99d631e146b2 100644
--- a/arch/alpha/include/asm/checksum.h
+++ b/arch/alpha/include/asm/checksum.h
@@ -42,9 +42,10 @@ extern __wsum csum_partial(const void *buff, int len, __wsum sum);
  * better 64-bit) boundary
  */
 #define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
-__wsum csum_and_copy_from_user(const void __user *src, void *dst, int len, __wsum sum, int *errp);
+#define _HAVE_ARCH_CSUM_AND_COPY
+__wsum csum_and_copy_from_user(const void __user *src, void *dst, int len);
 
-__wsum csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum);
+__wsum csum_partial_copy_nocheck(const void *src, void *dst, int len);
 
 
 /*
diff --git a/arch/alpha/lib/csum_partial_copy.c b/arch/alpha/lib/csum_partial_copy.c
index af1dad74e933..dc68efbe9367 100644
--- a/arch/alpha/lib/csum_partial_copy.c
+++ b/arch/alpha/lib/csum_partial_copy.c
@@ -39,12 +39,11 @@ __asm__ __volatile__("insql %1,%2,%0":"=r" (z):"r" (x),"r" (y))
 #define insqh(x,y,z) \
 __asm__ __volatile__("insqh %1,%2,%0":"=r" (z):"r" (x),"r" (y))
 
-
-#define __get_user_u(x,ptr)				\
+#define __get_word(insn,x,ptr)				\
 ({							\
 	long __guu_err;					\
 	__asm__ __volatile__(				\
-	"1:	ldq_u %0,%2\n"				\
+	"1:	"#insn" %0,%2\n"			\
 	"2:\n"						\
 	EXC(1b,2b,%0,%1)				\
 		: "=r"(x), "=r"(__guu_err)		\
@@ -52,19 +51,6 @@ __asm__ __volatile__("insqh %1,%2,%0":"=r" (z):"r" (x),"r" (y))
 	__guu_err;					\
 })
 
-#define __put_user_u(x,ptr)				\
-({							\
-	long __puu_err;					\
-	__asm__ __volatile__(				\
-	"1:	stq_u %2,%1\n"				\
-	"2:\n"						\
-	EXC(1b,2b,$31,%0)				\
-		: "=r"(__puu_err)			\
-		: "m"(__m(addr)), "rJ"(x), "0"(0));	\
-	__puu_err;					\
-})
-
-
 static inline unsigned short from64to16(unsigned long x)
 {
 	/* Using extract instructions is a bit more efficient
@@ -95,15 +81,15 @@ static inline unsigned short from64to16(unsigned long x)
  */
 static inline unsigned long
 csum_partial_cfu_aligned(const unsigned long __user *src, unsigned long *dst,
-			 long len, unsigned long checksum,
-			 int *errp)
+			 long len)
 {
+	unsigned long checksum = ~0U;
 	unsigned long carry = 0;
-	int err = 0;
 
 	while (len >= 0) {
 		unsigned long word;
-		err |= __get_user(word, src);
+		if (__get_word(ldq, word, src))
+			return 0;
 		checksum += carry;
 		src++;
 		checksum += word;
@@ -116,7 +102,8 @@ csum_partial_cfu_aligned(const unsigned long __user *src, unsigned long *dst,
 	checksum += carry;
 	if (len) {
 		unsigned long word, tmp;
-		err |= __get_user(word, src);
+		if (__get_word(ldq, word, src))
+			return 0;
 		tmp = *dst;
 		mskql(word, len, word);
 		checksum += word;
@@ -125,7 +112,6 @@ csum_partial_cfu_aligned(const unsigned long __user *src, unsigned long *dst,
 		*dst = word | tmp;
 		checksum += carry;
 	}
-	if (err && errp) *errp = err;
 	return checksum;
 }
 
@@ -137,20 +123,21 @@ static inline unsigned long
 csum_partial_cfu_dest_aligned(const unsigned long __user *src,
 			      unsigned long *dst,
 			      unsigned long soff,
-			      long len, unsigned long checksum,
-			      int *errp)
+			      long len)
 {
 	unsigned long first;
 	unsigned long word, carry;
 	unsigned long lastsrc = 7+len+(unsigned long)src;
-	int err = 0;
+	unsigned long checksum = ~0U;
 
-	err |= __get_user_u(first,src);
+	if (__get_word(ldq_u, first,src))
+		return 0;
 	carry = 0;
 	while (len >= 0) {
 		unsigned long second;
 
-		err |= __get_user_u(second, src+1);
+		if (__get_word(ldq_u, second, src+1))
+			return 0;
 		extql(first, soff, word);
 		len -= 8;
 		src++;
@@ -168,7 +155,8 @@ csum_partial_cfu_dest_aligned(const unsigned long __user *src,
 	if (len) {
 		unsigned long tmp;
 		unsigned long second;
-		err |= __get_user_u(second, lastsrc);
+		if (__get_word(ldq_u, second, lastsrc))
+			return 0;
 		tmp = *dst;
 		extql(first, soff, word);
 		extqh(second, soff, first);
@@ -180,7 +168,6 @@ csum_partial_cfu_dest_aligned(const unsigned long __user *src,
 		*dst = word | tmp;
 		checksum += carry;
 	}
-	if (err && errp) *errp = err;
 	return checksum;
 }
 
@@ -191,18 +178,18 @@ static inline unsigned long
 csum_partial_cfu_src_aligned(const unsigned long __user *src,
 			     unsigned long *dst,
 			     unsigned long doff,
-			     long len, unsigned long checksum,
-			     unsigned long partial_dest,
-			     int *errp)
+			     long len,
+			     unsigned long partial_dest)
 {
 	unsigned long carry = 0;
 	unsigned long word;
 	unsigned long second_dest;
-	int err = 0;
+	unsigned long checksum = ~0U;
 
 	mskql(partial_dest, doff, partial_dest);
 	while (len >= 0) {
-		err |= __get_user(word, src);
+		if (__get_word(ldq, word, src))
+			return 0;
 		len -= 8;
 		insql(word, doff, second_dest);
 		checksum += carry;
@@ -216,7 +203,8 @@ csum_partial_cfu_src_aligned(const unsigned long __user *src,
 	len += 8;
 	if (len) {
 		checksum += carry;
-		err |= __get_user(word, src);
+		if (__get_word(ldq, word, src))
+			return 0;
 		mskql(word, len, word);
 		len -= 8;
 		checksum += word;
@@ -237,7 +225,6 @@ csum_partial_cfu_src_aligned(const unsigned long __user *src,
 	stq_u(partial_dest | second_dest, dst);
 out:
 	checksum += carry;
-	if (err && errp) *errp = err;
 	return checksum;
 }
 
@@ -249,23 +236,23 @@ static inline unsigned long
 csum_partial_cfu_unaligned(const unsigned long __user * src,
 			   unsigned long * dst,
 			   unsigned long soff, unsigned long doff,
-			   long len, unsigned long checksum,
-			   unsigned long partial_dest,
-			   int *errp)
+			   long len, unsigned long partial_dest)
 {
 	unsigned long carry = 0;
 	unsigned long first;
 	unsigned long lastsrc;
-	int err = 0;
+	unsigned long checksum = ~0U;
 
-	err |= __get_user_u(first, src);
+	if (__get_word(ldq_u, first, src))
+		return 0;
 	lastsrc = 7+len+(unsigned long)src;
 	mskql(partial_dest, doff, partial_dest);
 	while (len >= 0) {
 		unsigned long second, word;
 		unsigned long second_dest;
 
-		err |= __get_user_u(second, src+1);
+		if (__get_word(ldq_u, second, src+1))
+			return 0;
 		extql(first, soff, word);
 		checksum += carry;
 		len -= 8;
@@ -286,7 +273,8 @@ csum_partial_cfu_unaligned(const unsigned long __user * src,
 		unsigned long second, word;
 		unsigned long second_dest;
 
-		err |= __get_user_u(second, lastsrc);
+		if (__get_word(ldq_u, second, lastsrc))
+			return 0;
 		extql(first, soff, word);
 		extqh(second, soff, first);
 		word |= first;
@@ -307,7 +295,8 @@ csum_partial_cfu_unaligned(const unsigned long __user * src,
 		unsigned long second, word;
 		unsigned long second_dest;
 
-		err |= __get_user_u(second, lastsrc);
+		if (__get_word(ldq_u, second, lastsrc))
+			return 0;
 		extql(first, soff, word);
 		extqh(second, soff, first);
 		word |= first;
@@ -320,66 +309,55 @@ csum_partial_cfu_unaligned(const unsigned long __user * src,
 		stq_u(partial_dest | word | second_dest, dst);
 		checksum += carry;
 	}
-	if (err && errp) *errp = err;
 	return checksum;
 }
 
-__wsum
-csum_and_copy_from_user(const void __user *src, void *dst, int len,
-			       __wsum sum, int *errp)
+static __wsum __csum_and_copy(const void __user *src, void *dst, int len)
 {
-	unsigned long checksum = (__force u32) sum;
 	unsigned long soff = 7 & (unsigned long) src;
 	unsigned long doff = 7 & (unsigned long) dst;
-
-	if (len) {
-		if (!access_ok(src, len)) {
-			if (errp) *errp = -EFAULT;
-			memset(dst, 0, len);
-			return sum;
-		}
-		if (!doff) {
-			if (!soff)
-				checksum = csum_partial_cfu_aligned(
-					(const unsigned long __user *) src,
-					(unsigned long *) dst,
-					len-8, checksum, errp);
-			else
-				checksum = csum_partial_cfu_dest_aligned(
-					(const unsigned long __user *) src,
-					(unsigned long *) dst,
-					soff, len-8, checksum, errp);
-		} else {
-			unsigned long partial_dest;
-			ldq_u(partial_dest, dst);
-			if (!soff)
-				checksum = csum_partial_cfu_src_aligned(
-					(const unsigned long __user *) src,
-					(unsigned long *) dst,
-					doff, len-8, checksum,
-					partial_dest, errp);
-			else
-				checksum = csum_partial_cfu_unaligned(
-					(const unsigned long __user *) src,
-					(unsigned long *) dst,
-					soff, doff, len-8, checksum,
-					partial_dest, errp);
-		}
-		checksum = from64to16 (checksum);
+	unsigned long checksum;
+
+	if (!doff) {
+		if (!soff)
+			checksum = csum_partial_cfu_aligned(
+				(const unsigned long __user *) src,
+				(unsigned long *) dst, len-8);
+		else
+			checksum = csum_partial_cfu_dest_aligned(
+				(const unsigned long __user *) src,
+				(unsigned long *) dst,
+				soff, len-8);
+	} else {
+		unsigned long partial_dest;
+		ldq_u(partial_dest, dst);
+		if (!soff)
+			checksum = csum_partial_cfu_src_aligned(
+				(const unsigned long __user *) src,
+				(unsigned long *) dst,
+				doff, len-8, partial_dest);
+		else
+			checksum = csum_partial_cfu_unaligned(
+				(const unsigned long __user *) src,
+				(unsigned long *) dst,
+				soff, doff, len-8, partial_dest);
 	}
-	return (__force __wsum)checksum;
+	return (__force __wsum)from64to16 (checksum);
+}
+
+__wsum
+csum_and_copy_from_user(const void __user *src, void *dst, int len)
+{
+	if (!access_ok(src, len))
+		return 0;
+	return __csum_and_copy(src, dst, len);
 }
 EXPORT_SYMBOL(csum_and_copy_from_user);
 
 __wsum
-csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
+csum_partial_copy_nocheck(const void *src, void *dst, int len)
 {
-	__wsum checksum;
-	mm_segment_t oldfs = get_fs();
-	set_fs(KERNEL_DS);
-	checksum = csum_and_copy_from_user((__force const void __user *)src,
-						dst, len, sum, NULL);
-	set_fs(oldfs);
-	return checksum;
+	return __csum_and_copy((__force const void __user *)src,
+						dst, len);
 }
 EXPORT_SYMBOL(csum_partial_copy_nocheck);
diff --git a/arch/arm/include/asm/checksum.h b/arch/arm/include/asm/checksum.h
index ed6073fee338..f0f54aef3724 100644
--- a/arch/arm/include/asm/checksum.h
+++ b/arch/arm/include/asm/checksum.h
@@ -35,23 +35,20 @@ __wsum csum_partial(const void *buff, int len, __wsum sum);
  */
 
 __wsum
-csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum);
+csum_partial_copy_nocheck(const void *src, void *dst, int len);
 
 __wsum
-csum_partial_copy_from_user(const void __user *src, void *dst, int len, __wsum sum, int *err_ptr);
+csum_partial_copy_from_user(const void __user *src, void *dst, int len);
 
 #define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
+#define _HAVE_ARCH_CSUM_AND_COPY
 static inline
-__wsum csum_and_copy_from_user (const void __user *src, void *dst,
-				      int len, __wsum sum, int *err_ptr)
+__wsum csum_and_copy_from_user(const void __user *src, void *dst, int len)
 {
-	if (access_ok(src, len))
-		return csum_partial_copy_from_user(src, dst, len, sum, err_ptr);
+	if (!access_ok(src, len))
+		return 0;
 
-	if (len)
-		*err_ptr = -EFAULT;
-
-	return sum;
+	return csum_partial_copy_from_user(src, dst, len);
 }
 
 /*
diff --git a/arch/arm/lib/csumpartialcopy.S b/arch/arm/lib/csumpartialcopy.S
index 184d97254a7a..1ca6aadd649c 100644
--- a/arch/arm/lib/csumpartialcopy.S
+++ b/arch/arm/lib/csumpartialcopy.S
@@ -9,8 +9,8 @@
 
 		.text
 
-/* Function: __u32 csum_partial_copy_nocheck(const char *src, char *dst, int len, __u32 sum)
- * Params  : r0 = src, r1 = dst, r2 = len, r3 = checksum
+/* Function: __u32 csum_partial_copy_nocheck(const char *src, char *dst, int len)
+ * Params  : r0 = src, r1 = dst, r2 = len
  * Returns : r0 = new checksum
  */
 
diff --git a/arch/arm/lib/csumpartialcopygeneric.S b/arch/arm/lib/csumpartialcopygeneric.S
index 0b706a39a677..0fd5c10e90a7 100644
--- a/arch/arm/lib/csumpartialcopygeneric.S
+++ b/arch/arm/lib/csumpartialcopygeneric.S
@@ -86,6 +86,7 @@ sum	.req	r3
 
 FN_ENTRY
 		save_regs
+		mov	sum, #-1
 
 		cmp	len, #8			@ Ensure that we have at least
 		blo	.Lless8			@ 8 bytes to copy.
diff --git a/arch/arm/lib/csumpartialcopyuser.S b/arch/arm/lib/csumpartialcopyuser.S
index 6bd3a93eaa3c..6928781e6bee 100644
--- a/arch/arm/lib/csumpartialcopyuser.S
+++ b/arch/arm/lib/csumpartialcopyuser.S
@@ -62,9 +62,9 @@
 
 /*
  * unsigned int
- * csum_partial_copy_from_user(const char *src, char *dst, int len, int sum, int *err_ptr)
- *  r0 = src, r1 = dst, r2 = len, r3 = sum, [sp] = *err_ptr
- *  Returns : r0 = checksum, [[sp, #0], #0] = 0 or -EFAULT
+ * csum_partial_copy_from_user(const char *src, char *dst, int len)
+ *  r0 = src, r1 = dst, r2 = len
+ *  Returns : r0 = checksum or 0
  */
 
 #define FN_ENTRY	ENTRY(csum_partial_copy_from_user)
@@ -73,25 +73,11 @@
 #include "csumpartialcopygeneric.S"
 
 /*
- * FIXME: minor buglet here
- * We don't return the checksum for the data present in the buffer.  To do
- * so properly, we would have to add in whatever registers were loaded before
- * the fault, which, with the current asm above is not predictable.
+ * We report fault by returning 0 csum - impossible in normal case, since
+ * we start with 0xffffffff for initial sum.
  */
 		.pushsection .text.fixup,"ax"
 		.align	4
-9001:		mov	r4, #-EFAULT
-#ifdef CONFIG_CPU_SW_DOMAIN_PAN
-		ldr	r5, [sp, #9*4]		@ *err_ptr
-#else
-		ldr	r5, [sp, #8*4]		@ *err_ptr
-#endif
-		str	r4, [r5]
-		ldmia	sp, {r1, r2}		@ retrieve dst, len
-		add	r2, r2, r1
-		mov	r0, #0			@ zero the buffer
-9002:		teq	r2, r1
-		strbne	r0, [r1], #1
-		bne	9002b
+9001:		mov	r0, #0
 		load_regs
 		.popsection
diff --git a/arch/c6x/include/asm/checksum.h b/arch/c6x/include/asm/checksum.h
index 36770b8308d9..934918def632 100644
--- a/arch/c6x/include/asm/checksum.h
+++ b/arch/c6x/include/asm/checksum.h
@@ -26,6 +26,9 @@ csum_tcpudp_nofold(__be32 saddr, __be32 daddr, __u32 len,
 }
 #define csum_tcpudp_nofold csum_tcpudp_nofold
 
+#define _HAVE_ARCH_CSUM_AND_COPY
+extern __wsum csum_partial_copy_nocheck(const void *src, void *dst, int len);
+
 #include <asm-generic/checksum.h>
 
 #endif /* _ASM_C6X_CHECKSUM_H */
diff --git a/arch/c6x/lib/csum_64plus.S b/arch/c6x/lib/csum_64plus.S
index 9c07127485d1..57148866d8d3 100644
--- a/arch/c6x/lib/csum_64plus.S
+++ b/arch/c6x/lib/csum_64plus.S
@@ -24,7 +24,6 @@
 ENTRY(csum_partial_copy_nocheck)
 	MVC	.S2	ILC,B30
 
-	MV	.D1X	B6,A31		; given csum
 	ZERO	.D1	A9		; csum (a side)
 ||	ZERO	.D2	B9		; csum (b side)
 ||	SHRU	.S2X	A6,2,B5		; len / 4
@@ -144,8 +143,7 @@ L91:	SHRU	.S2X	A9,16,B4
 	SHRU	.S1	A9,16,A0
    [A0]	BNOP	.S1	L91,5
 
-L10:	ADD	.D1	A31,A9,A9
-	MV	.D1	A9,A4
+L10:	MV	.D1	A9,A4
 
 	BNOP	.S2	B3,4
 	MVC	.S2	B30,ILC
diff --git a/arch/hexagon/include/asm/checksum.h b/arch/hexagon/include/asm/checksum.h
index a5c42f4614c1..4bc6ad96c4c5 100644
--- a/arch/hexagon/include/asm/checksum.h
+++ b/arch/hexagon/include/asm/checksum.h
@@ -10,17 +10,6 @@
 unsigned int do_csum(const void *voidptr, int len);
 
 /*
- * the same as csum_partial, but copies from src while it
- * checksums
- *
- * here even more important to align src and dst on a 32-bit (or even
- * better 64-bit) boundary
- */
-#define csum_partial_copy_nocheck csum_partial_copy_nocheck
-__wsum csum_partial_copy_nocheck(const void *src, void *dst,
-					int len, __wsum sum);
-
-/*
  * computes the checksum of the TCP/UDP pseudo-header
  * returns a 16-bit checksum, already complemented
  */
diff --git a/arch/hexagon/lib/checksum.c b/arch/hexagon/lib/checksum.c
index c4a6b72d97de..ba50822a0800 100644
--- a/arch/hexagon/lib/checksum.c
+++ b/arch/hexagon/lib/checksum.c
@@ -176,14 +176,3 @@ unsigned int do_csum(const void *voidptr, int len)
 
 	return 0xFFFF & sum0;
 }
-
-/*
- * copy from ds while checksumming, otherwise like csum_partial
- */
-__wsum
-csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
-{
-	memcpy(dst, src, len);
-	return csum_partial(dst, len, sum);
-}
-EXPORT_SYMBOL(csum_partial_copy_nocheck);
diff --git a/arch/ia64/include/asm/checksum.h b/arch/ia64/include/asm/checksum.h
index 2a1c64629cdc..f3026213aa32 100644
--- a/arch/ia64/include/asm/checksum.h
+++ b/arch/ia64/include/asm/checksum.h
@@ -37,9 +37,6 @@ extern __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
  */
 extern __wsum csum_partial(const void *buff, int len, __wsum sum);
 
-extern __wsum csum_partial_copy_nocheck(const void *src, void *dst,
-					       int len, __wsum sum);
-
 /*
  * This routine is used for miscellaneous IP-like checksums, mainly in
  * icmp.c
diff --git a/arch/ia64/lib/csum_partial_copy.c b/arch/ia64/lib/csum_partial_copy.c
index 6e82e0be8040..917e3138b277 100644
--- a/arch/ia64/lib/csum_partial_copy.c
+++ b/arch/ia64/lib/csum_partial_copy.c
@@ -96,18 +96,3 @@ unsigned long do_csum_c(const unsigned char * buff, int len, unsigned int psum)
 out:
 	return result;
 }
-
-/*
- * XXX Fixme
- *
- * This is very ugly but temporary. THIS NEEDS SERIOUS ENHANCEMENTS.
- * But it's very tricky to get right even in C.
- */
-__wsum
-csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
-{
-	memcpy(dst, src, len);
-	return csum_partial(dst, len, sum);
-}
-
-EXPORT_SYMBOL(csum_partial_copy_nocheck);
diff --git a/arch/m68k/include/asm/checksum.h b/arch/m68k/include/asm/checksum.h
index 3f2c15d6f18c..692e7b6cc042 100644
--- a/arch/m68k/include/asm/checksum.h
+++ b/arch/m68k/include/asm/checksum.h
@@ -31,14 +31,13 @@ __wsum csum_partial(const void *buff, int len, __wsum sum);
  */
 
 #define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
+#define _HAVE_ARCH_CSUM_AND_COPY
 extern __wsum csum_and_copy_from_user(const void __user *src,
 						void *dst,
-						int len, __wsum sum,
-						int *csum_err);
+						int len);
 
 extern __wsum csum_partial_copy_nocheck(const void *src,
-					      void *dst, int len,
-					      __wsum sum);
+					      void *dst, int len);
 
 /*
  *	This is a version of ip_fast_csum() optimized for IP headers,
diff --git a/arch/m68k/lib/checksum.c b/arch/m68k/lib/checksum.c
index 31797be9a3dc..7e6afeae6217 100644
--- a/arch/m68k/lib/checksum.c
+++ b/arch/m68k/lib/checksum.c
@@ -129,8 +129,7 @@ EXPORT_SYMBOL(csum_partial);
  */
 
 __wsum
-csum_and_copy_from_user(const void __user *src, void *dst,
-			    int len, __wsum sum, int *csum_err)
+csum_and_copy_from_user(const void __user *src, void *dst, int len)
 {
 	/*
 	 * GCC doesn't like more than 10 operands for the asm
@@ -138,6 +137,7 @@ csum_and_copy_from_user(const void __user *src, void *dst,
 	 * code.
 	 */
 	unsigned long tmp1, tmp2;
+	__wsum sum = ~0U;
 
 	__asm__("movel %2,%4\n\t"
 		"btst #1,%4\n\t"	/* Check alignment */
@@ -236,84 +236,33 @@ csum_and_copy_from_user(const void __user *src, void *dst,
 		"clrl %5\n\t"
 		"addxl %5,%0\n\t"	/* add X bit */
 	     "7:\t"
-		"clrl %5\n"		/* no error - clear return value */
-	     "8:\n"
 		".section .fixup,\"ax\"\n"
 		".even\n"
-		/* If any exception occurs zero out the rest.
-		   Similarities with the code above are intentional :-) */
+		/* If any exception occurs, return 0 */
 	     "90:\t"
-		"clrw %3@+\n\t"
-		"movel %1,%4\n\t"
-		"lsrl #5,%1\n\t"
-		"jeq 1f\n\t"
-		"subql #1,%1\n"
-	     "91:\t"
-		"clrl %3@+\n"
-	     "92:\t"
-		"clrl %3@+\n"
-	     "93:\t"
-		"clrl %3@+\n"
-	     "94:\t"
-		"clrl %3@+\n"
-	     "95:\t"
-		"clrl %3@+\n"
-	     "96:\t"
-		"clrl %3@+\n"
-	     "97:\t"
-		"clrl %3@+\n"
-	     "98:\t"
-		"clrl %3@+\n\t"
-		"dbra %1,91b\n\t"
-		"clrw %1\n\t"
-		"subql #1,%1\n\t"
-		"jcc 91b\n"
-	     "1:\t"
-		"movel %4,%1\n\t"
-		"andw #0x1c,%4\n\t"
-		"jeq 1f\n\t"
-		"lsrw #2,%4\n\t"
-		"subqw #1,%4\n"
-	     "99:\t"
-		"clrl %3@+\n\t"
-		"dbra %4,99b\n\t"
-	     "1:\t"
-		"andw #3,%1\n\t"
-		"jeq 9f\n"
-	     "100:\t"
-		"clrw %3@+\n\t"
-		"tstw %1\n\t"
-		"jeq 9f\n"
-	     "101:\t"
-		"clrb %3@+\n"
-	     "9:\t"
-#define STR(X) STR1(X)
-#define STR1(X) #X
-		"moveq #-" STR(EFAULT) ",%5\n\t"
-		"jra 8b\n"
+		"clrl %0\n"
+		"jra 7b\n"
 		".previous\n"
 		".section __ex_table,\"a\"\n"
 		".long 10b,90b\n"
-		".long 11b,91b\n"
-		".long 12b,92b\n"
-		".long 13b,93b\n"
-		".long 14b,94b\n"
-		".long 15b,95b\n"
-		".long 16b,96b\n"
-		".long 17b,97b\n"
-		".long 18b,98b\n"
-		".long 19b,99b\n"
-		".long 20b,100b\n"
-		".long 21b,101b\n"
+		".long 11b,90b\n"
+		".long 12b,90b\n"
+		".long 13b,90b\n"
+		".long 14b,90b\n"
+		".long 15b,90b\n"
+		".long 16b,90b\n"
+		".long 17b,90b\n"
+		".long 18b,90b\n"
+		".long 19b,90b\n"
+		".long 20b,90b\n"
+		".long 21b,90b\n"
 		".previous"
 		: "=d" (sum), "=d" (len), "=a" (src), "=a" (dst),
 		  "=&d" (tmp1), "=d" (tmp2)
 		: "0" (sum), "1" (len), "2" (src), "3" (dst)
 	    );
 
-	*csum_err = tmp2;
-
-	return(sum);
+	return sum;
 }
 
 EXPORT_SYMBOL(csum_and_copy_from_user);
@@ -324,9 +273,10 @@ EXPORT_SYMBOL(csum_and_copy_from_user);
  */
 
 __wsum
-csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
+csum_partial_copy_nocheck(const void *src, void *dst, int len)
 {
 	unsigned long tmp1, tmp2;
+	__wsum sum = 0;
 	__asm__("movel %2,%4\n\t"
 		"btst #1,%4\n\t"	/* Check alignment */
 		"jeq 2f\n\t"
diff --git a/arch/mips/include/asm/checksum.h b/arch/mips/include/asm/checksum.h
index 181f7d14efb9..5f80c28f5253 100644
--- a/arch/mips/include/asm/checksum.h
+++ b/arch/mips/include/asm/checksum.h
@@ -34,42 +34,17 @@
  */
 __wsum csum_partial(const void *buff, int len, __wsum sum);
 
-__wsum __csum_partial_copy_kernel(const void *src, void *dst,
-				  int len, __wsum sum, int *err_ptr);
-
-__wsum __csum_partial_copy_from_user(const void *src, void *dst,
-				     int len, __wsum sum, int *err_ptr);
-__wsum __csum_partial_copy_to_user(const void *src, void *dst,
-				   int len, __wsum sum, int *err_ptr);
-/*
- * this is a new version of the above that records errors it finds in *errp,
- * but continues and zeros the rest of the buffer.
- */
-static inline
-__wsum csum_partial_copy_from_user(const void __user *src, void *dst, int len,
-				   __wsum sum, int *err_ptr)
-{
-	might_fault();
-	if (uaccess_kernel())
-		return __csum_partial_copy_kernel((__force void *)src, dst,
-						  len, sum, err_ptr);
-	else
-		return __csum_partial_copy_from_user((__force void *)src, dst,
-						     len, sum, err_ptr);
-}
+__wsum __csum_partial_copy_from_user(const void __user *src, void *dst, int len);
+__wsum __csum_partial_copy_to_user(const void *src, void __user *dst, int len);
 
 #define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
 static inline
-__wsum csum_and_copy_from_user(const void __user *src, void *dst,
-			       int len, __wsum sum, int *err_ptr)
+__wsum csum_and_copy_from_user(const void __user *src, void *dst, int len)
 {
-	if (access_ok(src, len))
-		return csum_partial_copy_from_user(src, dst, len, sum,
-						   err_ptr);
-	if (len)
-		*err_ptr = -EFAULT;
-
-	return sum;
+	might_fault();
+	if (!access_ok(src, len))
+		return 0;
+	return __csum_partial_copy_from_user(src, dst, len);
 }
 
 /*
@@ -77,33 +52,24 @@ __wsum csum_and_copy_from_user(const void __user *src, void *dst,
  */
 #define HAVE_CSUM_COPY_USER
 static inline
-__wsum csum_and_copy_to_user(const void *src, void __user *dst, int len,
-			     __wsum sum, int *err_ptr)
+__wsum csum_and_copy_to_user(const void *src, void __user *dst, int len)
 {
 	might_fault();
-	if (access_ok(dst, len)) {
-		if (uaccess_kernel())
-			return __csum_partial_copy_kernel(src,
-							  (__force void *)dst,
-							  len, sum, err_ptr);
-		else
-			return __csum_partial_copy_to_user(src,
-							   (__force void *)dst,
-							   len, sum, err_ptr);
-	}
-	if (len)
-		*err_ptr = -EFAULT;
-
-	return (__force __wsum)-1; /* invalid checksum */
+	if (!access_ok(dst, len))
+		return 0;
+	return __csum_partial_copy_to_user(src, dst, len);
 }
 
 /*
  * the same as csum_partial, but copies from user space (but on MIPS
  * we have just one address space, so this is identical to the above)
  */
-__wsum csum_partial_copy_nocheck(const void *src, void *dst,
-				       int len, __wsum sum);
-#define csum_partial_copy_nocheck csum_partial_copy_nocheck
+#define _HAVE_ARCH_CSUM_AND_COPY
+__wsum __csum_partial_copy_nocheck(const void *src, void *dst, int len);
+static inline __wsum csum_partial_copy_nocheck(const void *src, void *dst, int len)
+{
+	return __csum_partial_copy_nocheck(src, dst, len);
+}
 
 /*
  *	Fold a partial checksum without adding pseudo headers
diff --git a/arch/mips/lib/csum_partial.S b/arch/mips/lib/csum_partial.S
index 87fda0713b84..a46db0807195 100644
--- a/arch/mips/lib/csum_partial.S
+++ b/arch/mips/lib/csum_partial.S
@@ -308,8 +308,8 @@ EXPORT_SYMBOL(csum_partial)
 /*
  * checksum and copy routines based on memcpy.S
  *
- *	csum_partial_copy_nocheck(src, dst, len, sum)
- *	__csum_partial_copy_kernel(src, dst, len, sum, errp)
+ *	csum_partial_copy_nocheck(src, dst, len)
+ *	__csum_partial_copy_kernel(src, dst, len)
  *
  * See "Spec" in memcpy.S for details.	Unlike __copy_user, all
  * function in this file use the standard calling convention.
@@ -318,26 +318,11 @@ EXPORT_SYMBOL(csum_partial)
 #define src a0
 #define dst a1
 #define len a2
-#define psum a3
 #define sum v0
 #define odd t8
-#define errptr t9
 
 /*
- * The exception handler for loads requires that:
- *  1- AT contain the address of the byte just past the end of the source
- *     of the copy,
- *  2- src_entry <= src < AT, and
- *  3- (dst - src) == (dst_entry - src_entry),
- * The _entry suffix denotes values when __copy_user was called.
- *
- * (1) is set up up by __csum_partial_copy_from_user and maintained by
- *	not writing AT in __csum_partial_copy
- * (2) is met by incrementing src by the number of bytes copied
- * (3) is met by not doing loads between a pair of increments of dst and src
- *
- * The exception handlers for stores stores -EFAULT to errptr and return.
- * These handlers do not need to overwrite any data.
+ * All exception handlers simply return 0.
  */
 
 /* Instruction type */
@@ -358,11 +343,11 @@ EXPORT_SYMBOL(csum_partial)
  * addr    : Address
  * handler : Exception handler
  */
-#define EXC(insn, type, reg, addr, handler)	\
+#define EXC(insn, type, reg, addr)		\
 	.if \mode == LEGACY_MODE;		\
 9:		insn reg, addr;			\
 		.section __ex_table,"a";	\
-		PTR	9b, handler;		\
+		PTR	9b, .L_exc;		\
 		.previous;			\
 	/* This is enabled in EVA mode */	\
 	.else;					\
@@ -371,7 +356,7 @@ EXPORT_SYMBOL(csum_partial)
 		    ((\to == USEROP) && (type == ST_INSN));	\
 9:			__BUILD_EVA_INSN(insn##e, reg, addr);	\
 			.section __ex_table,"a";		\
-			PTR	9b, handler;			\
+			PTR	9b, .L_exc;			\
 			.previous;				\
 		.else;						\
 			/* EVA without exception */		\
@@ -384,14 +369,14 @@ EXPORT_SYMBOL(csum_partial)
 #ifdef USE_DOUBLE
 
 #define LOADK	ld /* No exception */
-#define LOAD(reg, addr, handler)	EXC(ld, LD_INSN, reg, addr, handler)
-#define LOADBU(reg, addr, handler)	EXC(lbu, LD_INSN, reg, addr, handler)
-#define LOADL(reg, addr, handler)	EXC(ldl, LD_INSN, reg, addr, handler)
-#define LOADR(reg, addr, handler)	EXC(ldr, LD_INSN, reg, addr, handler)
-#define STOREB(reg, addr, handler)	EXC(sb, ST_INSN, reg, addr, handler)
-#define STOREL(reg, addr, handler)	EXC(sdl, ST_INSN, reg, addr, handler)
-#define STORER(reg, addr, handler)	EXC(sdr, ST_INSN, reg, addr, handler)
-#define STORE(reg, addr, handler)	EXC(sd, ST_INSN, reg, addr, handler)
+#define LOAD(reg, addr)		EXC(ld, LD_INSN, reg, addr)
+#define LOADBU(reg, addr)	EXC(lbu, LD_INSN, reg, addr)
+#define LOADL(reg, addr)	EXC(ldl, LD_INSN, reg, addr)
+#define LOADR(reg, addr)	EXC(ldr, LD_INSN, reg, addr)
+#define STOREB(reg, addr)	EXC(sb, ST_INSN, reg, addr)
+#define STOREL(reg, addr)	EXC(sdl, ST_INSN, reg, addr)
+#define STORER(reg, addr)	EXC(sdr, ST_INSN, reg, addr)
+#define STORE(reg, addr)	EXC(sd, ST_INSN, reg, addr)
 #define ADD    daddu
 #define SUB    dsubu
 #define SRL    dsrl
@@ -404,14 +389,14 @@ EXPORT_SYMBOL(csum_partial)
 #else
 
 #define LOADK	lw /* No exception */
-#define LOAD(reg, addr, handler)	EXC(lw, LD_INSN, reg, addr, handler)
-#define LOADBU(reg, addr, handler)	EXC(lbu, LD_INSN, reg, addr, handler)
-#define LOADL(reg, addr, handler)	EXC(lwl, LD_INSN, reg, addr, handler)
-#define LOADR(reg, addr, handler)	EXC(lwr, LD_INSN, reg, addr, handler)
-#define STOREB(reg, addr, handler)	EXC(sb, ST_INSN, reg, addr, handler)
-#define STOREL(reg, addr, handler)	EXC(swl, ST_INSN, reg, addr, handler)
-#define STORER(reg, addr, handler)	EXC(swr, ST_INSN, reg, addr, handler)
-#define STORE(reg, addr, handler)	EXC(sw, ST_INSN, reg, addr, handler)
+#define LOAD(reg, addr)		EXC(lw, LD_INSN, reg, addr)
+#define LOADBU(reg, addr)	EXC(lbu, LD_INSN, reg, addr)
+#define LOADL(reg, addr)	EXC(lwl, LD_INSN, reg, addr)
+#define LOADR(reg, addr)	EXC(lwr, LD_INSN, reg, addr)
+#define STOREB(reg, addr)	EXC(sb, ST_INSN, reg, addr)
+#define STOREL(reg, addr)	EXC(swl, ST_INSN, reg, addr)
+#define STORER(reg, addr)	EXC(swr, ST_INSN, reg, addr)
+#define STORE(reg, addr)	EXC(sw, ST_INSN, reg, addr)
 #define ADD    addu
 #define SUB    subu
 #define SRL    srl
@@ -450,22 +435,9 @@ EXPORT_SYMBOL(csum_partial)
 	.set	at=v1
 #endif
 
-	.macro __BUILD_CSUM_PARTIAL_COPY_USER mode, from, to, __nocheck
+	.macro __BUILD_CSUM_PARTIAL_COPY_USER mode, from, to
 
-	PTR_ADDU	AT, src, len	/* See (1) above. */
-	/* initialize __nocheck if this the first time we execute this
-	 * macro
-	 */
-#ifdef CONFIG_64BIT
-	move	errptr, a4
-#else
-	lw	errptr, 16(sp)
-#endif
-	.if \__nocheck == 1
-	FEXPORT(csum_partial_copy_nocheck)
-	EXPORT_SYMBOL(csum_partial_copy_nocheck)
-	.endif
-	move	sum, zero
+	li	sum, -1
 	move	odd, zero
 	/*
 	 * Note: dst & src may be unaligned, len may be 0
@@ -497,31 +469,31 @@ EXPORT_SYMBOL(csum_partial)
 	SUB	len, 8*NBYTES		# subtract here for bgez loop
 	.align	4
 1:
-	LOAD(t0, UNIT(0)(src), .Ll_exc\@)
-	LOAD(t1, UNIT(1)(src), .Ll_exc_copy\@)
-	LOAD(t2, UNIT(2)(src), .Ll_exc_copy\@)
-	LOAD(t3, UNIT(3)(src), .Ll_exc_copy\@)
-	LOAD(t4, UNIT(4)(src), .Ll_exc_copy\@)
-	LOAD(t5, UNIT(5)(src), .Ll_exc_copy\@)
-	LOAD(t6, UNIT(6)(src), .Ll_exc_copy\@)
-	LOAD(t7, UNIT(7)(src), .Ll_exc_copy\@)
+	LOAD(t0, UNIT(0)(src))
+	LOAD(t1, UNIT(1)(src))
+	LOAD(t2, UNIT(2)(src))
+	LOAD(t3, UNIT(3)(src))
+	LOAD(t4, UNIT(4)(src))
+	LOAD(t5, UNIT(5)(src))
+	LOAD(t6, UNIT(6)(src))
+	LOAD(t7, UNIT(7)(src))
 	SUB	len, len, 8*NBYTES
 	ADD	src, src, 8*NBYTES
-	STORE(t0, UNIT(0)(dst),	.Ls_exc\@)
+	STORE(t0, UNIT(0)(dst))
 	ADDC(t0, t1)
-	STORE(t1, UNIT(1)(dst),	.Ls_exc\@)
+	STORE(t1, UNIT(1)(dst))
 	ADDC(sum, t0)
-	STORE(t2, UNIT(2)(dst),	.Ls_exc\@)
+	STORE(t2, UNIT(2)(dst))
 	ADDC(t2, t3)
-	STORE(t3, UNIT(3)(dst),	.Ls_exc\@)
+	STORE(t3, UNIT(3)(dst))
 	ADDC(sum, t2)
-	STORE(t4, UNIT(4)(dst),	.Ls_exc\@)
+	STORE(t4, UNIT(4)(dst))
 	ADDC(t4, t5)
-	STORE(t5, UNIT(5)(dst),	.Ls_exc\@)
+	STORE(t5, UNIT(5)(dst))
 	ADDC(sum, t4)
-	STORE(t6, UNIT(6)(dst),	.Ls_exc\@)
+	STORE(t6, UNIT(6)(dst))
 	ADDC(t6, t7)
-	STORE(t7, UNIT(7)(dst),	.Ls_exc\@)
+	STORE(t7, UNIT(7)(dst))
 	ADDC(sum, t6)
 	.set	reorder				/* DADDI_WAR */
 	ADD	dst, dst, 8*NBYTES
@@ -541,19 +513,19 @@ EXPORT_SYMBOL(csum_partial)
 	/*
 	 * len >= 4*NBYTES
 	 */
-	LOAD(t0, UNIT(0)(src), .Ll_exc\@)
-	LOAD(t1, UNIT(1)(src), .Ll_exc_copy\@)
-	LOAD(t2, UNIT(2)(src), .Ll_exc_copy\@)
-	LOAD(t3, UNIT(3)(src), .Ll_exc_copy\@)
+	LOAD(t0, UNIT(0)(src))
+	LOAD(t1, UNIT(1)(src))
+	LOAD(t2, UNIT(2)(src))
+	LOAD(t3, UNIT(3)(src))
 	SUB	len, len, 4*NBYTES
 	ADD	src, src, 4*NBYTES
-	STORE(t0, UNIT(0)(dst),	.Ls_exc\@)
+	STORE(t0, UNIT(0)(dst))
 	ADDC(t0, t1)
-	STORE(t1, UNIT(1)(dst),	.Ls_exc\@)
+	STORE(t1, UNIT(1)(dst))
 	ADDC(sum, t0)
-	STORE(t2, UNIT(2)(dst),	.Ls_exc\@)
+	STORE(t2, UNIT(2)(dst))
 	ADDC(t2, t3)
-	STORE(t3, UNIT(3)(dst),	.Ls_exc\@)
+	STORE(t3, UNIT(3)(dst))
 	ADDC(sum, t2)
 	.set	reorder				/* DADDI_WAR */
 	ADD	dst, dst, 4*NBYTES
@@ -566,10 +538,10 @@ EXPORT_SYMBOL(csum_partial)
 	beq	rem, len, .Lcopy_bytes\@
 	 nop
 1:
-	LOAD(t0, 0(src), .Ll_exc\@)
+	LOAD(t0, 0(src))
 	ADD	src, src, NBYTES
 	SUB	len, len, NBYTES
-	STORE(t0, 0(dst), .Ls_exc\@)
+	STORE(t0, 0(dst))
 	ADDC(sum, t0)
 	.set	reorder				/* DADDI_WAR */
 	ADD	dst, dst, NBYTES
@@ -592,10 +564,10 @@ EXPORT_SYMBOL(csum_partial)
 	 ADD	t1, dst, len	# t1 is just past last byte of dst
 	li	bits, 8*NBYTES
 	SLL	rem, len, 3	# rem = number of bits to keep
-	LOAD(t0, 0(src), .Ll_exc\@)
+	LOAD(t0, 0(src))
 	SUB	bits, bits, rem # bits = number of bits to discard
 	SHIFT_DISCARD t0, t0, bits
-	STREST(t0, -1(t1), .Ls_exc\@)
+	STREST(t0, -1(t1))
 	SHIFT_DISCARD_REVERT t0, t0, bits
 	.set reorder
 	ADDC(sum, t0)
@@ -612,12 +584,12 @@ EXPORT_SYMBOL(csum_partial)
 	 * Set match = (src and dst have same alignment)
 	 */
 #define match rem
-	LDFIRST(t3, FIRST(0)(src), .Ll_exc\@)
+	LDFIRST(t3, FIRST(0)(src))
 	ADD	t2, zero, NBYTES
-	LDREST(t3, REST(0)(src), .Ll_exc_copy\@)
+	LDREST(t3, REST(0)(src))
 	SUB	t2, t2, t1	# t2 = number of bytes copied
 	xor	match, t0, t1
-	STFIRST(t3, FIRST(0)(dst), .Ls_exc\@)
+	STFIRST(t3, FIRST(0)(dst))
 	SLL	t4, t1, 3		# t4 = number of bits to discard
 	SHIFT_DISCARD t3, t3, t4
 	/* no SHIFT_DISCARD_REVERT to handle odd buffer properly */
@@ -639,26 +611,26 @@ EXPORT_SYMBOL(csum_partial)
  * It's OK to load FIRST(N+1) before REST(N) because the two addresses
  * are to the same unit (unless src is aligned, but it's not).
  */
-	LDFIRST(t0, FIRST(0)(src), .Ll_exc\@)
-	LDFIRST(t1, FIRST(1)(src), .Ll_exc_copy\@)
+	LDFIRST(t0, FIRST(0)(src))
+	LDFIRST(t1, FIRST(1)(src))
 	SUB	len, len, 4*NBYTES
-	LDREST(t0, REST(0)(src), .Ll_exc_copy\@)
-	LDREST(t1, REST(1)(src), .Ll_exc_copy\@)
-	LDFIRST(t2, FIRST(2)(src), .Ll_exc_copy\@)
-	LDFIRST(t3, FIRST(3)(src), .Ll_exc_copy\@)
-	LDREST(t2, REST(2)(src), .Ll_exc_copy\@)
-	LDREST(t3, REST(3)(src), .Ll_exc_copy\@)
+	LDREST(t0, REST(0)(src))
+	LDREST(t1, REST(1)(src))
+	LDFIRST(t2, FIRST(2)(src))
+	LDFIRST(t3, FIRST(3)(src))
+	LDREST(t2, REST(2)(src))
+	LDREST(t3, REST(3)(src))
 	ADD	src, src, 4*NBYTES
 #ifdef CONFIG_CPU_SB1
 	nop				# improves slotting
 #endif
-	STORE(t0, UNIT(0)(dst),	.Ls_exc\@)
+	STORE(t0, UNIT(0)(dst))
 	ADDC(t0, t1)
-	STORE(t1, UNIT(1)(dst),	.Ls_exc\@)
+	STORE(t1, UNIT(1)(dst))
 	ADDC(sum, t0)
-	STORE(t2, UNIT(2)(dst),	.Ls_exc\@)
+	STORE(t2, UNIT(2)(dst))
 	ADDC(t2, t3)
-	STORE(t3, UNIT(3)(dst),	.Ls_exc\@)
+	STORE(t3, UNIT(3)(dst))
 	ADDC(sum, t2)
 	.set	reorder				/* DADDI_WAR */
 	ADD	dst, dst, 4*NBYTES
@@ -671,11 +643,11 @@ EXPORT_SYMBOL(csum_partial)
 	beq	rem, len, .Lcopy_bytes\@
 	 nop
 1:
-	LDFIRST(t0, FIRST(0)(src), .Ll_exc\@)
-	LDREST(t0, REST(0)(src), .Ll_exc_copy\@)
+	LDFIRST(t0, FIRST(0)(src))
+	LDREST(t0, REST(0)(src))
 	ADD	src, src, NBYTES
 	SUB	len, len, NBYTES
-	STORE(t0, 0(dst), .Ls_exc\@)
+	STORE(t0, 0(dst))
 	ADDC(sum, t0)
 	.set	reorder				/* DADDI_WAR */
 	ADD	dst, dst, NBYTES
@@ -696,11 +668,10 @@ EXPORT_SYMBOL(csum_partial)
 #endif
 	move	t2, zero	# partial word
 	li	t3, SHIFT_START # shift
-/* use .Ll_exc_copy here to return correct sum on fault */
 #define COPY_BYTE(N)			\
-	LOADBU(t0, N(src), .Ll_exc_copy\@);	\
+	LOADBU(t0, N(src));		\
 	SUB	len, len, 1;		\
-	STOREB(t0, N(dst), .Ls_exc\@);	\
+	STOREB(t0, N(dst));		\
 	SLLV	t0, t0, t3;		\
 	addu	t3, SHIFT_INC;		\
 	beqz	len, .Lcopy_bytes_done\@; \
@@ -714,9 +685,9 @@ EXPORT_SYMBOL(csum_partial)
 	COPY_BYTE(4)
 	COPY_BYTE(5)
 #endif
-	LOADBU(t0, NBYTES-2(src), .Ll_exc_copy\@)
+	LOADBU(t0, NBYTES-2(src))
 	SUB	len, len, 1
-	STOREB(t0, NBYTES-2(dst), .Ls_exc\@)
+	STOREB(t0, NBYTES-2(dst))
 	SLLV	t0, t0, t3
 	or	t2, t0
 .Lcopy_bytes_done\@:
@@ -753,97 +724,31 @@ EXPORT_SYMBOL(csum_partial)
 #endif
 	.set	pop
 	.set reorder
-	ADDC32(sum, psum)
 	jr	ra
 	.set noreorder
+	.endm
 
-.Ll_exc_copy\@:
-	/*
-	 * Copy bytes from src until faulting load address (or until a
-	 * lb faults)
-	 *
-	 * When reached by a faulting LDFIRST/LDREST, THREAD_BUADDR($28)
-	 * may be more than a byte beyond the last address.
-	 * Hence, the lb below may get an exception.
-	 *
-	 * Assumes src < THREAD_BUADDR($28)
-	 */
-	LOADK	t0, TI_TASK($28)
-	 li	t2, SHIFT_START
-	LOADK	t0, THREAD_BUADDR(t0)
-1:
-	LOADBU(t1, 0(src), .Ll_exc\@)
-	ADD	src, src, 1
-	sb	t1, 0(dst)	# can't fault -- we're copy_from_user
-	SLLV	t1, t1, t2
-	addu	t2, SHIFT_INC
-	ADDC(sum, t1)
-	.set	reorder				/* DADDI_WAR */
-	ADD	dst, dst, 1
-	bne	src, t0, 1b
-	.set	noreorder
-.Ll_exc\@:
-	LOADK	t0, TI_TASK($28)
-	 nop
-	LOADK	t0, THREAD_BUADDR(t0)	# t0 is just past last good address
-	 nop
-	SUB	len, AT, t0		# len number of uncopied bytes
-	/*
-	 * Here's where we rely on src and dst being incremented in tandem,
-	 *   See (3) above.
-	 * dst += (fault addr - src) to put dst at first byte to clear
-	 */
-	ADD	dst, t0			# compute start address in a1
-	SUB	dst, src
-	/*
-	 * Clear len bytes starting at dst.  Can't call __bzero because it
-	 * might modify len.  An inefficient loop for these rare times...
-	 */
-	.set	reorder				/* DADDI_WAR */
-	SUB	src, len, 1
-	beqz	len, .Ldone\@
-	.set	noreorder
-1:	sb	zero, 0(dst)
-	ADD	dst, dst, 1
-	.set	push
-	.set	noat
-#ifndef CONFIG_CPU_DADDI_WORKAROUNDS
-	bnez	src, 1b
-	 SUB	src, src, 1
-#else
-	li	v1, 1
-	bnez	src, 1b
-	 SUB	src, src, v1
-#endif
-	li	v1, -EFAULT
-	b	.Ldone\@
-	 sw	v1, (errptr)
-
-.Ls_exc\@:
-	li	v0, -1 /* invalid checksum */
-	li	v1, -EFAULT
+	.set noreorder
+.L_exc:
 	jr	ra
-	 sw	v1, (errptr)
-	.set	pop
-	.endm
+	 li	v0, 0
 
-LEAF(__csum_partial_copy_kernel)
-EXPORT_SYMBOL(__csum_partial_copy_kernel)
+FEXPORT(__csum_partial_copy_nocheck)
+EXPORT_SYMBOL(__csum_partial_copy_nocheck)
 #ifndef CONFIG_EVA
 FEXPORT(__csum_partial_copy_to_user)
 EXPORT_SYMBOL(__csum_partial_copy_to_user)
 FEXPORT(__csum_partial_copy_from_user)
 EXPORT_SYMBOL(__csum_partial_copy_from_user)
 #endif
-__BUILD_CSUM_PARTIAL_COPY_USER LEGACY_MODE USEROP USEROP 1
-END(__csum_partial_copy_kernel)
+__BUILD_CSUM_PARTIAL_COPY_USER LEGACY_MODE USEROP USEROP
 
 #ifdef CONFIG_EVA
 LEAF(__csum_partial_copy_to_user)
-__BUILD_CSUM_PARTIAL_COPY_USER EVA_MODE KERNELOP USEROP 0
+__BUILD_CSUM_PARTIAL_COPY_USER EVA_MODE KERNELOP USEROP
 END(__csum_partial_copy_to_user)
 
 LEAF(__csum_partial_copy_from_user)
-__BUILD_CSUM_PARTIAL_COPY_USER EVA_MODE USEROP KERNELOP 0
+__BUILD_CSUM_PARTIAL_COPY_USER EVA_MODE USEROP KERNELOP
 END(__csum_partial_copy_from_user)
 #endif
diff --git a/arch/nios2/include/asm/checksum.h b/arch/nios2/include/asm/checksum.h
index b4316c361729..69004e07a1ba 100644
--- a/arch/nios2/include/asm/checksum.h
+++ b/arch/nios2/include/asm/checksum.h
@@ -12,10 +12,6 @@
 
 /* Take these from lib/checksum.c */
 extern __wsum csum_partial(const void *buff, int len, __wsum sum);
-__wsum csum_partial_copy_nocheck(const void *src, void *dst, int len,
-				__wsum sum);
-#define csum_partial_copy_nocheck csum_partial_copy_nocheck
-
 extern __sum16 ip_fast_csum(const void *iph, unsigned int ihl);
 extern __sum16 ip_compute_csum(const void *buff, int len);
 
diff --git a/arch/parisc/include/asm/checksum.h b/arch/parisc/include/asm/checksum.h
index fe8c63b2d2c3..3c43baca7b39 100644
--- a/arch/parisc/include/asm/checksum.h
+++ b/arch/parisc/include/asm/checksum.h
@@ -19,14 +19,6 @@
 extern __wsum csum_partial(const void *, int, __wsum);
 
 /*
- * The same as csum_partial, but copies from src while it checksums.
- *
- * Here even more important to align src and dst on a 32-bit (or even
- * better 64-bit) boundary
- */
-extern __wsum csum_partial_copy_nocheck(const void *, void *, int, __wsum);
-
-/*
  *	Optimized for IP headers, which always checksum on 4 octet boundaries.
  *
  *	Written by Randolph Chung <tausq@debian.org>, and then mucked with by
@@ -181,25 +173,5 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 	return csum_fold(sum);
 }
 
-/* 
- *	Copy and checksum to user
- */
-#define HAVE_CSUM_COPY_USER
-static __inline__ __wsum csum_and_copy_to_user(const void *src,
-						      void __user *dst,
-						      int len, __wsum sum,
-						      int *err_ptr)
-{
-	/* code stolen from include/asm-mips64 */
-	sum = csum_partial(src, len, sum);
-	 
-	if (copy_to_user(dst, src, len)) {
-		*err_ptr = -EFAULT;
-		return (__force __wsum)-1;
-	}
-
-	return sum;
-}
-
 #endif
 
diff --git a/arch/parisc/lib/checksum.c b/arch/parisc/lib/checksum.c
index c6f161583549..4818f3db84a5 100644
--- a/arch/parisc/lib/checksum.c
+++ b/arch/parisc/lib/checksum.c
@@ -106,20 +106,3 @@ __wsum csum_partial(const void *buff, int len, __wsum sum)
 }
 
 EXPORT_SYMBOL(csum_partial);
-
-/*
- * copy while checksumming, otherwise like csum_partial
- */
-__wsum csum_partial_copy_nocheck(const void *src, void *dst,
-				       int len, __wsum sum)
-{
-	/*
-	 * It's 2:30 am and I don't feel like doing it real ...
-	 * This is lots slower than the real thing (tm)
-	 */
-	sum = csum_partial(src, len, sum);
-	memcpy(dst, src, len);
-
-	return sum;
-}
-EXPORT_SYMBOL(csum_partial_copy_nocheck);
diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h
index 9cce06194dcc..82f099ba2411 100644
--- a/arch/powerpc/include/asm/checksum.h
+++ b/arch/powerpc/include/asm/checksum.h
@@ -18,19 +18,18 @@
  * Like csum_partial, this must be called with even lengths,
  * except for the last fragment.
  */
-extern __wsum csum_partial_copy_generic(const void *src, void *dst,
-					      int len, __wsum sum,
-					      int *src_err, int *dst_err);
+extern __wsum csum_partial_copy_generic(const void *src, void *dst, int len);
 
 #define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
 extern __wsum csum_and_copy_from_user(const void __user *src, void *dst,
-				      int len, __wsum sum, int *err_ptr);
+				      int len);
 #define HAVE_CSUM_COPY_USER
 extern __wsum csum_and_copy_to_user(const void *src, void __user *dst,
-				    int len, __wsum sum, int *err_ptr);
+				    int len);
 
-#define csum_partial_copy_nocheck(src, dst, len, sum)   \
-        csum_partial_copy_generic((src), (dst), (len), (sum), NULL, NULL)
+#define _HAVE_ARCH_CSUM_AND_COPY
+#define csum_partial_copy_nocheck(src, dst, len)   \
+        csum_partial_copy_generic((src), (dst), (len))
 
 
 /*
diff --git a/arch/powerpc/lib/checksum_32.S b/arch/powerpc/lib/checksum_32.S
index ecd150dc3ed9..ec5cd2dede35 100644
--- a/arch/powerpc/lib/checksum_32.S
+++ b/arch/powerpc/lib/checksum_32.S
@@ -78,12 +78,10 @@ EXPORT_SYMBOL(__csum_partial)
 
 /*
  * Computes the checksum of a memory block at src, length len,
- * and adds in "sum" (32-bit), while copying the block to dst.
- * If an access exception occurs on src or dst, it stores -EFAULT
- * to *src_err or *dst_err respectively, and (for an error on
- * src) zeroes the rest of dst.
+ * and adds in 0xffffffff, while copying the block to dst.
+ * If an access exception occurs it returns zero.
  *
- * csum_partial_copy_generic(src, dst, len, sum, src_err, dst_err)
+ * csum_partial_copy_generic(src, dst, len)
  */
 #define CSUM_COPY_16_BYTES_WITHEX(n)	\
 8 ## n ## 0:			\
@@ -108,14 +106,14 @@ EXPORT_SYMBOL(__csum_partial)
 	adde	r12,r12,r10
 
 #define CSUM_COPY_16_BYTES_EXCODE(n)		\
-	EX_TABLE(8 ## n ## 0b, src_error);	\
-	EX_TABLE(8 ## n ## 1b, src_error);	\
-	EX_TABLE(8 ## n ## 2b, src_error);	\
-	EX_TABLE(8 ## n ## 3b, src_error);	\
-	EX_TABLE(8 ## n ## 4b, dst_error);	\
-	EX_TABLE(8 ## n ## 5b, dst_error);	\
-	EX_TABLE(8 ## n ## 6b, dst_error);	\
-	EX_TABLE(8 ## n ## 7b, dst_error);
+	EX_TABLE(8 ## n ## 0b, fault);	\
+	EX_TABLE(8 ## n ## 1b, fault);	\
+	EX_TABLE(8 ## n ## 2b, fault);	\
+	EX_TABLE(8 ## n ## 3b, fault);	\
+	EX_TABLE(8 ## n ## 4b, fault);	\
+	EX_TABLE(8 ## n ## 5b, fault);	\
+	EX_TABLE(8 ## n ## 6b, fault);	\
+	EX_TABLE(8 ## n ## 7b, fault);
 
 	.text
 	.stabs	"arch/powerpc/lib/",N_SO,0,0,0f
@@ -127,11 +125,8 @@ LG_CACHELINE_BYTES = L1_CACHE_SHIFT
 CACHELINE_MASK = (L1_CACHE_BYTES-1)
 
 _GLOBAL(csum_partial_copy_generic)
-	stwu	r1,-16(r1)
-	stw	r7,12(r1)
-	stw	r8,8(r1)
-
-	addic	r12,r6,0
+	li	r12,-1
+	addic	r0,r0,0			/* clear carry */
 	addi	r6,r4,-4
 	neg	r0,r4
 	addi	r4,r3,-4
@@ -246,34 +241,19 @@ _GLOBAL(csum_partial_copy_generic)
 	rlwinm	r3,r3,8,0,31	/* odd destination address: rotate one byte */
 	blr
 
-/* read fault */
-src_error:
-	lwz	r7,12(r1)
-	addi	r1,r1,16
-	cmpwi	cr0,r7,0
-	beqlr
-	li	r0,-EFAULT
-	stw	r0,0(r7)
-	blr
-/* write fault */
-dst_error:
-	lwz	r8,8(r1)
-	addi	r1,r1,16
-	cmpwi	cr0,r8,0
-	beqlr
-	li	r0,-EFAULT
-	stw	r0,0(r8)
+fault:
+	li	r3,0
 	blr
 
-	EX_TABLE(70b, src_error);
-	EX_TABLE(71b, dst_error);
-	EX_TABLE(72b, src_error);
-	EX_TABLE(73b, dst_error);
-	EX_TABLE(54b, dst_error);
+	EX_TABLE(70b, fault);
+	EX_TABLE(71b, fault);
+	EX_TABLE(72b, fault);
+	EX_TABLE(73b, fault);
+	EX_TABLE(54b, fault);
 
 /*
  * this stuff handles faults in the cacheline loop and branches to either
- * src_error (if in read part) or dst_error (if in write part)
+ * fault (if in read part) or fault (if in write part)
  */
 	CSUM_COPY_16_BYTES_EXCODE(0)
 #if L1_CACHE_BYTES >= 32
@@ -290,12 +270,12 @@ dst_error:
 #endif
 #endif
 
-	EX_TABLE(30b, src_error);
-	EX_TABLE(31b, dst_error);
-	EX_TABLE(40b, src_error);
-	EX_TABLE(41b, dst_error);
-	EX_TABLE(50b, src_error);
-	EX_TABLE(51b, dst_error);
+	EX_TABLE(30b, fault);
+	EX_TABLE(31b, fault);
+	EX_TABLE(40b, fault);
+	EX_TABLE(41b, fault);
+	EX_TABLE(50b, fault);
+	EX_TABLE(51b, fault);
 
 EXPORT_SYMBOL(csum_partial_copy_generic)
 
diff --git a/arch/powerpc/lib/checksum_64.S b/arch/powerpc/lib/checksum_64.S
index 514978f908d4..98ff51bd2f7d 100644
--- a/arch/powerpc/lib/checksum_64.S
+++ b/arch/powerpc/lib/checksum_64.S
@@ -182,34 +182,33 @@ EXPORT_SYMBOL(__csum_partial)
 
 	.macro srcnr
 100:
-	EX_TABLE(100b,.Lsrc_error_nr)
+	EX_TABLE(100b,.Lerror_nr)
 	.endm
 
 	.macro source
 150:
-	EX_TABLE(150b,.Lsrc_error)
+	EX_TABLE(150b,.Lerror)
 	.endm
 
 	.macro dstnr
 200:
-	EX_TABLE(200b,.Ldest_error_nr)
+	EX_TABLE(200b,.Lerror_nr)
 	.endm
 
 	.macro dest
 250:
-	EX_TABLE(250b,.Ldest_error)
+	EX_TABLE(250b,.Lerror)
 	.endm
 
 /*
  * Computes the checksum of a memory block at src, length len,
- * and adds in "sum" (32-bit), while copying the block to dst.
- * If an access exception occurs on src or dst, it stores -EFAULT
- * to *src_err or *dst_err respectively. The caller must take any action
- * required in this case (zeroing memory, recalculating partial checksum etc).
+ * and adds in 0xffffffff (32-bit), while copying the block to dst.
+ * If an access exception occurs, it returns 0.
  *
- * csum_partial_copy_generic(r3=src, r4=dst, r5=len, r6=sum, r7=src_err, r8=dst_err)
+ * csum_partial_copy_generic(r3=src, r4=dst, r5=len)
  */
 _GLOBAL(csum_partial_copy_generic)
+	li	r6,-1
 	addic	r0,r6,0			/* clear carry */
 
 	srdi.	r6,r5,3			/* less than 8 bytes? */
@@ -401,29 +400,15 @@ dstnr;	stb	r6,0(r4)
 	srdi	r3,r3,32
 	blr
 
-.Lsrc_error:
+.Lerror:
 	ld	r14,STK_REG(R14)(r1)
 	ld	r15,STK_REG(R15)(r1)
 	ld	r16,STK_REG(R16)(r1)
 	addi	r1,r1,STACKFRAMESIZE
-.Lsrc_error_nr:
-	cmpdi	0,r7,0
-	beqlr
-	li	r6,-EFAULT
-	stw	r6,0(r7)
+.Lerror_nr:
+	li	r3,0
 	blr
 
-.Ldest_error:
-	ld	r14,STK_REG(R14)(r1)
-	ld	r15,STK_REG(R15)(r1)
-	ld	r16,STK_REG(R16)(r1)
-	addi	r1,r1,STACKFRAMESIZE
-.Ldest_error_nr:
-	cmpdi	0,r8,0
-	beqlr
-	li	r6,-EFAULT
-	stw	r6,0(r8)
-	blr
 EXPORT_SYMBOL(csum_partial_copy_generic)
 
 /*
diff --git a/arch/powerpc/lib/checksum_wrappers.c b/arch/powerpc/lib/checksum_wrappers.c
index fabe4db28726..b895166afc82 100644
--- a/arch/powerpc/lib/checksum_wrappers.c
+++ b/arch/powerpc/lib/checksum_wrappers.c
@@ -12,83 +12,37 @@
 #include <linux/uaccess.h>
 
 __wsum csum_and_copy_from_user(const void __user *src, void *dst,
-			       int len, __wsum sum, int *err_ptr)
+			       int len)
 {
-	unsigned int csum;
+	__wsum csum;
 
 	might_sleep();
-	allow_read_from_user(src, len);
-
-	*err_ptr = 0;
-
-	if (!len) {
-		csum = 0;
-		goto out;
-	}
 
-	if (unlikely((len < 0) || !access_ok(src, len))) {
-		*err_ptr = -EFAULT;
-		csum = (__force unsigned int)sum;
-		goto out;
-	}
+	if (unlikely(!access_ok(src, len)))
+		return 0;
 
-	csum = csum_partial_copy_generic((void __force *)src, dst,
-					 len, sum, err_ptr, NULL);
-
-	if (unlikely(*err_ptr)) {
-		int missing = __copy_from_user(dst, src, len);
-
-		if (missing) {
-			memset(dst + len - missing, 0, missing);
-			*err_ptr = -EFAULT;
-		} else {
-			*err_ptr = 0;
-		}
+	allow_read_from_user(src, len);
 
-		csum = csum_partial(dst, len, sum);
-	}
+	csum = csum_partial_copy_generic((void __force *)src, dst, len);
 
-out:
 	prevent_read_from_user(src, len);
-	return (__force __wsum)csum;
+	return csum;
 }
 EXPORT_SYMBOL(csum_and_copy_from_user);
 
-__wsum csum_and_copy_to_user(const void *src, void __user *dst, int len,
-			     __wsum sum, int *err_ptr)
+__wsum csum_and_copy_to_user(const void *src, void __user *dst, int len)
 {
-	unsigned int csum;
+	__wsum csum;
 
 	might_sleep();
-	allow_write_to_user(dst, len);
-
-	*err_ptr = 0;
-
-	if (!len) {
-		csum = 0;
-		goto out;
-	}
+	if (unlikely(!access_ok(dst, len)))
+		return 0;
 
-	if (unlikely((len < 0) || !access_ok(dst, len))) {
-		*err_ptr = -EFAULT;
-		csum = -1; /* invalid checksum */
-		goto out;
-	}
-
-	csum = csum_partial_copy_generic(src, (void __force *)dst,
-					 len, sum, NULL, err_ptr);
-
-	if (unlikely(*err_ptr)) {
-		csum = csum_partial(src, len, sum);
+	allow_write_to_user(dst, len);
 
-		if (copy_to_user(dst, src, len)) {
-			*err_ptr = -EFAULT;
-			csum = -1; /* invalid checksum */
-		}
-	}
+	csum = csum_partial_copy_generic(src, (void __force *)dst, len);
 
-out:
 	prevent_write_to_user(dst, len);
-	return (__force __wsum)csum;
+	return csum;
 }
 EXPORT_SYMBOL(csum_and_copy_to_user);
diff --git a/arch/s390/include/asm/checksum.h b/arch/s390/include/asm/checksum.h
index 6d01c96aeb5c..6813bfa1eeb7 100644
--- a/arch/s390/include/asm/checksum.h
+++ b/arch/s390/include/asm/checksum.h
@@ -39,13 +39,6 @@ csum_partial(const void *buff, int len, __wsum sum)
 	return sum;
 }
 
-static inline __wsum
-csum_partial_copy_nocheck (const void *src, void *dst, int len, __wsum sum)
-{
-        memcpy(dst,src,len);
-	return csum_partial(dst, len, sum);
-}
-
 /*
  *      Fold a partial checksum without adding pseudo headers
  */
diff --git a/arch/sh/include/asm/checksum_32.h b/arch/sh/include/asm/checksum_32.h
index 91571a42e44e..1a391e3a7659 100644
--- a/arch/sh/include/asm/checksum_32.h
+++ b/arch/sh/include/asm/checksum_32.h
@@ -30,10 +30,9 @@ asmlinkage __wsum csum_partial(const void *buff, int len, __wsum sum);
  * better 64-bit) boundary
  */
 
-asmlinkage __wsum csum_partial_copy_generic(const void *src, void *dst,
-					    int len, __wsum sum,
-					    int *src_err_ptr, int *dst_err_ptr);
+asmlinkage __wsum csum_partial_copy_generic(const void *src, void *dst, int len);
 
+#define _HAVE_ARCH_CSUM_AND_COPY
 /*
  *	Note: when you get a NULL pointer exception here this means someone
  *	passed in an incorrect kernel address to one of these functions.
@@ -42,23 +41,18 @@ asmlinkage __wsum csum_partial_copy_generic(const void *src, void *dst,
  *	access_ok().
  */
 static inline
-__wsum csum_partial_copy_nocheck(const void *src, void *dst,
-				 int len, __wsum sum)
+__wsum csum_partial_copy_nocheck(const void *src, void *dst, int len)
 {
-	return csum_partial_copy_generic(src, dst, len, sum, NULL, NULL);
+	return csum_partial_copy_generic(src, dst, len);
 }
 
 #define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
 static inline
-__wsum csum_and_copy_from_user(const void __user *src, void *dst,
-				   int len, __wsum sum, int *err_ptr)
+__wsum csum_and_copy_from_user(const void __user *src, void *dst, int len)
 {
-	if (access_ok(src, len))
-		return csum_partial_copy_generic((__force const void *)src, dst,
-					len, sum, err_ptr, NULL);
-	if (len)
-		*err_ptr = -EFAULT;
-	return sum;
+	if (!access_ok(src, len))
+		return 0;
+	return csum_partial_copy_generic((__force const void *)src, dst, len);
 }
 
 /*
@@ -199,16 +193,10 @@ static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 #define HAVE_CSUM_COPY_USER
 static inline __wsum csum_and_copy_to_user(const void *src,
 					   void __user *dst,
-					   int len, __wsum sum,
-					   int *err_ptr)
+					   int len)
 {
-	if (access_ok(dst, len))
-		return csum_partial_copy_generic((__force const void *)src,
-						dst, len, sum, NULL, err_ptr);
-
-	if (len)
-		*err_ptr = -EFAULT;
-
-	return (__force __wsum)-1; /* invalid checksum */
+	if (!access_ok(dst, len))
+		return 0;
+	return csum_partial_copy_generic((__force const void *)src, dst, len);
 }
 #endif /* __ASM_SH_CHECKSUM_H */
diff --git a/arch/sh/lib/checksum.S b/arch/sh/lib/checksum.S
index 97b5c2d9fec4..3e07074e0098 100644
--- a/arch/sh/lib/checksum.S
+++ b/arch/sh/lib/checksum.S
@@ -173,47 +173,27 @@ ENTRY(csum_partial)
 	 mov	r6, r0
 
 /*
-unsigned int csum_partial_copy_generic (const char *src, char *dst, int len, 
-					int sum, int *src_err_ptr, int *dst_err_ptr)
+unsigned int csum_partial_copy_generic (const char *src, char *dst, int len)
  */ 
 
 /*
- * Copy from ds while checksumming, otherwise like csum_partial
- *
- * The macros SRC and DST specify the type of access for the instruction.
- * thus we can call a custom exception handler for all access types.
- *
- * FIXME: could someone double-check whether I haven't mixed up some SRC and
- *	  DST definitions? It's damn hard to trigger all cases.  I hope I got
- *	  them all but there's no guarantee.
+ * Copy from ds while checksumming, otherwise like csum_partial with initial
+ * sum being ~0U
  */
 
-#define SRC(...)			\
+#define EXC(...)			\
 	9999: __VA_ARGS__ ;		\
 	.section __ex_table, "a";	\
 	.long 9999b, 6001f	;	\
 	.previous
 
-#define DST(...)			\
-	9999: __VA_ARGS__ ;		\
-	.section __ex_table, "a";	\
-	.long 9999b, 6002f	;	\
-	.previous
-
 !
 ! r4:	const char *SRC
 ! r5:	char *DST
 ! r6:	int LEN
-! r7:	int SUM
-!
-! on stack:
-! int *SRC_ERR_PTR
-! int *DST_ERR_PTR
 !
 ENTRY(csum_partial_copy_generic)
-	mov.l	r5,@-r15
-	mov.l	r6,@-r15
-
+	mov	#-1,r7
 	mov	#3,r0		! Check src and dest are equally aligned
 	mov	r4,r1
 	and	r0,r1
@@ -243,11 +223,11 @@ ENTRY(csum_partial_copy_generic)
 	clrt
 	.align	2
 5:
-SRC(	mov.b	@r4+,r1 	)
-SRC(	mov.b	@r4+,r0		)
+EXC(	mov.b	@r4+,r1 	)
+EXC(	mov.b	@r4+,r0		)
 	extu.b	r1,r1
-DST(	mov.b	r1,@r5		)
-DST(	mov.b	r0,@(1,r5)	)
+EXC(	mov.b	r1,@r5		)
+EXC(	mov.b	r0,@(1,r5)	)
 	extu.b	r0,r0
 	add	#2,r5
 
@@ -276,8 +256,8 @@ DST(	mov.b	r0,@(1,r5)	)
 	! Handle first two bytes as a special case
 	.align	2
 1:	
-SRC(	mov.w	@r4+,r0		)
-DST(	mov.w	r0,@r5		)
+EXC(	mov.w	@r4+,r0		)
+EXC(	mov.w	r0,@r5		)
 	add	#2,r5
 	extu.w	r0,r0
 	addc	r0,r7
@@ -292,32 +272,32 @@ DST(	mov.w	r0,@r5		)
 	 clrt
 	.align	2
 1:	
-SRC(	mov.l	@r4+,r0		)
-SRC(	mov.l	@r4+,r1		)
+EXC(	mov.l	@r4+,r0		)
+EXC(	mov.l	@r4+,r1		)
 	addc	r0,r7
-DST(	mov.l	r0,@r5		)
-DST(	mov.l	r1,@(4,r5)	)
+EXC(	mov.l	r0,@r5		)
+EXC(	mov.l	r1,@(4,r5)	)
 	addc	r1,r7
 
-SRC(	mov.l	@r4+,r0		)
-SRC(	mov.l	@r4+,r1		)
+EXC(	mov.l	@r4+,r0		)
+EXC(	mov.l	@r4+,r1		)
 	addc	r0,r7
-DST(	mov.l	r0,@(8,r5)	)
-DST(	mov.l	r1,@(12,r5)	)
+EXC(	mov.l	r0,@(8,r5)	)
+EXC(	mov.l	r1,@(12,r5)	)
 	addc	r1,r7
 
-SRC(	mov.l	@r4+,r0 	)
-SRC(	mov.l	@r4+,r1		)
+EXC(	mov.l	@r4+,r0 	)
+EXC(	mov.l	@r4+,r1		)
 	addc	r0,r7
-DST(	mov.l	r0,@(16,r5)	)
-DST(	mov.l	r1,@(20,r5)	)
+EXC(	mov.l	r0,@(16,r5)	)
+EXC(	mov.l	r1,@(20,r5)	)
 	addc	r1,r7
 
-SRC(	mov.l	@r4+,r0		)
-SRC(	mov.l	@r4+,r1		)
+EXC(	mov.l	@r4+,r0		)
+EXC(	mov.l	@r4+,r1		)
 	addc	r0,r7
-DST(	mov.l	r0,@(24,r5)	)
-DST(	mov.l	r1,@(28,r5)	)
+EXC(	mov.l	r0,@(24,r5)	)
+EXC(	mov.l	r1,@(28,r5)	)
 	addc	r1,r7
 	add	#32,r5
 	movt	r0
@@ -335,9 +315,9 @@ DST(	mov.l	r1,@(28,r5)	)
 	 clrt
 	shlr2	r6
 3:	
-SRC(	mov.l	@r4+,r0	)
+EXC(	mov.l	@r4+,r0	)
 	addc	r0,r7
-DST(	mov.l	r0,@r5	)
+EXC(	mov.l	r0,@r5	)
 	add	#4,r5
 	movt	r0
 	dt	r6
@@ -353,8 +333,8 @@ DST(	mov.l	r0,@r5	)
 	mov	#2,r1
 	cmp/hs	r1,r6
 	bf	5f
-SRC(	mov.w	@r4+,r0	)
-DST(	mov.w	r0,@r5	)
+EXC(	mov.w	@r4+,r0	)
+EXC(	mov.w	r0,@r5	)
 	extu.w	r0,r0
 	add	#2,r5
 	cmp/eq	r1,r6
@@ -363,8 +343,8 @@ DST(	mov.w	r0,@r5	)
 	shll16	r0
 	addc	r0,r7
 5:	
-SRC(	mov.b	@r4+,r0	)
-DST(	mov.b	r0,@r5	)
+EXC(	mov.b	@r4+,r0	)
+EXC(	mov.b	r0,@r5	)
 	extu.b	r0,r0
 #ifndef	__LITTLE_ENDIAN__
 	shll8	r0
@@ -373,42 +353,13 @@ DST(	mov.b	r0,@r5	)
 	mov	#0,r0
 	addc	r0,r7
 7:
-5000:
 
 # Exception handler:
 .section .fixup, "ax"							
 
 6001:
-	mov.l	@(8,r15),r0			! src_err_ptr
-	mov	#-EFAULT,r1
-	mov.l	r1,@r0
-
-	! zero the complete destination - computing the rest
-	! is too much work 
-	mov.l	@(4,r15),r5		! dst
-	mov.l	@r15,r6			! len
-	mov	#0,r7
-1:	mov.b	r7,@r5
-	dt	r6
-	bf/s	1b
-	 add	#1,r5
-	mov.l	8000f,r0
-	jmp	@r0
-	 nop
-	.align	2
-8000:	.long	5000b
-
-6002:
-	mov.l	@(12,r15),r0			! dst_err_ptr
-	mov	#-EFAULT,r1
-	mov.l	r1,@r0
-	mov.l	8001f,r0
-	jmp	@r0
-	 nop
-	.align	2
-8001:	.long	5000b
-
+	rts
+	 mov	#0,r0
 .previous
-	add	#8,r15
 	rts
 	 mov	r7,r0
diff --git a/arch/sparc/include/asm/checksum.h b/arch/sparc/include/asm/checksum.h
index a6256cb6fc5c..f2ac13323b6d 100644
--- a/arch/sparc/include/asm/checksum.h
+++ b/arch/sparc/include/asm/checksum.h
@@ -1,7 +1,9 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef ___ASM_SPARC_CHECKSUM_H
 #define ___ASM_SPARC_CHECKSUM_H
+#define _HAVE_ARCH_CSUM_AND_COPY
 #define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
+#define HAVE_CSUM_COPY_USER
 #if defined(__sparc__) && defined(__arch64__)
 #include <asm/checksum_64.h>
 #else
diff --git a/arch/sparc/include/asm/checksum_32.h b/arch/sparc/include/asm/checksum_32.h
index 479a0b812af5..ce11e0ad80c7 100644
--- a/arch/sparc/include/asm/checksum_32.h
+++ b/arch/sparc/include/asm/checksum_32.h
@@ -42,7 +42,7 @@ __wsum csum_partial(const void *buff, int len, __wsum sum);
 unsigned int __csum_partial_copy_sparc_generic (const unsigned char *, unsigned char *);
 
 static inline __wsum
-csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
+csum_partial_copy_nocheck(const void *src, void *dst, int len)
 {
 	register unsigned int ret asm("o0") = (unsigned int)src;
 	register char *d asm("o1") = dst;
@@ -50,9 +50,9 @@ csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
 
 	__asm__ __volatile__ (
 		"call __csum_partial_copy_sparc_generic\n\t"
-		" mov %6, %%g7\n"
+		" mov -1, %%g7\n"
 	: "=&r" (ret), "=&r" (d), "=&r" (l)
-	: "0" (ret), "1" (d), "2" (l), "r" (sum)
+	: "0" (ret), "1" (d), "2" (l)
 	: "o2", "o3", "o4", "o5", "o7",
 	  "g2", "g3", "g4", "g5", "g7",
 	  "memory", "cc");
@@ -60,65 +60,19 @@ csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
 }
 
 static inline __wsum
-csum_and_copy_from_user(const void __user *src, void *dst, int len,
-			    __wsum sum, int *err)
-  {
-	register unsigned long ret asm("o0") = (unsigned long)src;
-	register char *d asm("o1") = dst;
-	register int l asm("g1") = len;
-	register __wsum s asm("g7") = sum;
-
-	if (unlikely(!access_ok(src, len))) {
-		if (len)
-			*err = -EFAULT;
-		return sum;
-	}
-
-	__asm__ __volatile__ (
-	".section __ex_table,#alloc\n\t"
-	".align 4\n\t"
-	".word 1f,2\n\t"
-	".previous\n"
-	"1:\n\t"
-	"call __csum_partial_copy_sparc_generic\n\t"
-	" st %8, [%%sp + 64]\n"
-	: "=&r" (ret), "=&r" (d), "=&r" (l), "=&r" (s)
-	: "0" (ret), "1" (d), "2" (l), "3" (s), "r" (err)
-	: "o2", "o3", "o4", "o5", "o7", "g2", "g3", "g4", "g5",
-	  "cc", "memory");
-	return (__force __wsum)ret;
+csum_and_copy_from_user(const void __user *src, void *dst, int len)
+{
+	if (unlikely(!access_ok(src, len)))
+		return 0;
+	return csum_partial_copy_nocheck((__force void *)src, dst, len);
 }
 
-#define HAVE_CSUM_COPY_USER
-
 static inline __wsum
-csum_and_copy_to_user(const void *src, void __user *dst, int len,
-			  __wsum sum, int *err)
+csum_and_copy_to_user(const void *src, void __user *dst, int len)
 {
-	if (!access_ok(dst, len)) {
-		*err = -EFAULT;
-		return sum;
-	} else {
-		register unsigned long ret asm("o0") = (unsigned long)src;
-		register char __user *d asm("o1") = dst;
-		register int l asm("g1") = len;
-		register __wsum s asm("g7") = sum;
-
-		__asm__ __volatile__ (
-		".section __ex_table,#alloc\n\t"
-		".align 4\n\t"
-		".word 1f,1\n\t"
-		".previous\n"
-		"1:\n\t"
-		"call __csum_partial_copy_sparc_generic\n\t"
-		" st %8, [%%sp + 64]\n"
-		: "=&r" (ret), "=&r" (d), "=&r" (l), "=&r" (s)
-		: "0" (ret), "1" (d), "2" (l), "3" (s), "r" (err)
-		: "o2", "o3", "o4", "o5", "o7",
-		  "g2", "g3", "g4", "g5",
-		  "cc", "memory");
-		return (__force __wsum)ret;
-	}
+	if (!access_ok(dst, len))
+		return 0;
+	return csum_partial_copy_nocheck(src, (__force void *)dst, len);
 }
 
 /* ihl is always 5 or greater, almost always is 5, and iph is word aligned
diff --git a/arch/sparc/include/asm/checksum_64.h b/arch/sparc/include/asm/checksum_64.h
index 0fa4433f5662..d6b59461e064 100644
--- a/arch/sparc/include/asm/checksum_64.h
+++ b/arch/sparc/include/asm/checksum_64.h
@@ -38,42 +38,9 @@ __wsum csum_partial(const void * buff, int len, __wsum sum);
  * here even more important to align src and dst on a 32-bit (or even
  * better 64-bit) boundary
  */
-__wsum csum_partial_copy_nocheck(const void *src, void *dst,
-				 int len, __wsum sum);
-
-long __csum_partial_copy_from_user(const void __user *src,
-				   void *dst, int len,
-				   __wsum sum);
-
-static inline __wsum
-csum_and_copy_from_user(const void __user *src,
-			    void *dst, int len,
-			    __wsum sum, int *err)
-{
-	long ret = __csum_partial_copy_from_user(src, dst, len, sum);
-	if (ret < 0)
-		*err = -EFAULT;
-	return (__force __wsum) ret;
-}
-
-/*
- *	Copy and checksum to user
- */
-#define HAVE_CSUM_COPY_USER
-long __csum_partial_copy_to_user(const void *src,
-				 void __user *dst, int len,
-				 __wsum sum);
-
-static inline __wsum
-csum_and_copy_to_user(const void *src,
-		      void __user *dst, int len,
-		      __wsum sum, int *err)
-{
-	long ret = __csum_partial_copy_to_user(src, dst, len, sum);
-	if (ret < 0)
-		*err = -EFAULT;
-	return (__force __wsum) ret;
-}
+__wsum csum_partial_copy_nocheck(const void *src, void *dst, int len);
+__wsum csum_and_copy_from_user(const void __user *src, void *dst, int len);
+__wsum csum_and_copy_to_user(const void *src, void __user *dst, int len);
 
 /* ihl is always 5 or greater, almost always is 5, and iph is word aligned
  * the majority of the time.
diff --git a/arch/sparc/lib/checksum_32.S b/arch/sparc/lib/checksum_32.S
index 6a5469c97246..7488d130faf7 100644
--- a/arch/sparc/lib/checksum_32.S
+++ b/arch/sparc/lib/checksum_32.S
@@ -144,44 +144,21 @@ cpte:	bne	csum_partial_end_cruft			! yep, handle it
 cpout:	retl						! get outta here
 	 mov	%o2, %o0				! return computed csum
 
-	.globl __csum_partial_copy_start, __csum_partial_copy_end
-__csum_partial_copy_start:
-
 /* Work around cpp -rob */
 #define ALLOC #alloc
 #define EXECINSTR #execinstr
-#define EX(x,y,a,b)				\
-98:     x,y;                                    \
-        .section .fixup,ALLOC,EXECINSTR;	\
-        .align  4;                              \
-99:     ba 30f;                                 \
-         a, b, %o3;                             \
-        .section __ex_table,ALLOC;		\
-        .align  4;                              \
-        .word   98b, 99b;                       \
-        .text;                                  \
-        .align  4
-
-#define EX2(x,y)				\
-98:     x,y;                                    \
-        .section __ex_table,ALLOC;		\
-        .align  4;                              \
-        .word   98b, 30f;                       \
-        .text;                                  \
-        .align  4
-
-#define EX3(x,y)				\
+#define EX(x,y)					\
 98:     x,y;                                    \
         .section __ex_table,ALLOC;		\
         .align  4;                              \
-        .word   98b, 96f;                       \
+        .word   98b, cc_fault;                   \
         .text;                                  \
         .align  4
 
-#define EXT(start,end,handler)			\
+#define EXT(start,end)				\
         .section __ex_table,ALLOC;		\
         .align  4;                              \
-        .word   start, 0, end, handler;         \
+        .word   start, 0, end, cc_fault;         \
         .text;                                  \
         .align  4
 
@@ -252,21 +229,21 @@ __csum_partial_copy_start:
 cc_end_cruft:
 	be	1f
 	 andcc	%o3, 4, %g0
-	EX(ldd	[%o0 + 0x00], %g2, and %o3, 0xf)
+	EX(ldd	[%o0 + 0x00], %g2)
 	add	%o1, 8, %o1
 	addcc	%g2, %g7, %g7
 	add	%o0, 8, %o0
 	addxcc	%g3, %g7, %g7
-	EX2(st	%g2, [%o1 - 0x08])
+	EX(st	%g2, [%o1 - 0x08])
 	addx	%g0, %g7, %g7
 	andcc	%o3, 4, %g0
-	EX2(st	%g3, [%o1 - 0x04])
+	EX(st	%g3, [%o1 - 0x04])
 1:	be	1f
 	 andcc	%o3, 3, %o3
-	EX(ld	[%o0 + 0x00], %g2, add %o3, 4)
+	EX(ld	[%o0 + 0x00], %g2)
 	add	%o1, 4, %o1
 	addcc	%g2, %g7, %g7
-	EX2(st	%g2, [%o1 - 0x04])
+	EX(st	%g2, [%o1 - 0x04])
 	addx	%g0, %g7, %g7
 	andcc	%o3, 3, %g0
 	add	%o0, 4, %o0
@@ -276,14 +253,14 @@ cc_end_cruft:
 	 subcc	%o3, 2, %o3
 	b	4f
 	 or	%g0, %g0, %o4
-2:	EX(lduh	[%o0 + 0x00], %o4, add %o3, 2)
+2:	EX(lduh	[%o0 + 0x00], %o4)
 	add	%o0, 2, %o0
-	EX2(sth	%o4, [%o1 + 0x00])
+	EX(sth	%o4, [%o1 + 0x00])
 	be	6f
 	 add	%o1, 2, %o1
 	sll	%o4, 16, %o4
-4:	EX(ldub	[%o0 + 0x00], %o5, add %g0, 1)
-	EX2(stb	%o5, [%o1 + 0x00])
+4:	EX(ldub	[%o0 + 0x00], %o5)
+	EX(stb	%o5, [%o1 + 0x00])
 	sll	%o5, 8, %o5
 	or	%o5, %o4, %o4
 6:	addcc	%o4, %g7, %g7
@@ -306,9 +283,9 @@ cc_dword_align:
 	 andcc	%o0, 0x2, %g0
 	be	1f
 	 andcc	%o0, 0x4, %g0
-	EX(lduh	[%o0 + 0x00], %g4, add %g1, 0)
+	EX(lduh	[%o0 + 0x00], %g4)
 	sub	%g1, 2, %g1
-	EX2(sth	%g4, [%o1 + 0x00])
+	EX(sth	%g4, [%o1 + 0x00])
 	add	%o0, 2, %o0
 	sll	%g4, 16, %g4
 	addcc	%g4, %g7, %g7
@@ -322,9 +299,9 @@ cc_dword_align:
 	or	%g3, %g7, %g7
 1:	be	3f
 	 andcc	%g1, 0xffffff80, %g0
-	EX(ld	[%o0 + 0x00], %g4, add %g1, 0)
+	EX(ld	[%o0 + 0x00], %g4)
 	sub	%g1, 4, %g1
-	EX2(st	%g4, [%o1 + 0x00])
+	EX(st	%g4, [%o1 + 0x00])
 	add	%o0, 4, %o0
 	addcc	%g4, %g7, %g7
 	add	%o1, 4, %o1
@@ -354,7 +331,7 @@ __csum_partial_copy_sparc_generic:
 	CSUMCOPY_BIGCHUNK(%o0,%o1,%g7,0x20,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
 	CSUMCOPY_BIGCHUNK(%o0,%o1,%g7,0x40,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
 	CSUMCOPY_BIGCHUNK(%o0,%o1,%g7,0x60,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
-10:	EXT(5b, 10b, 20f)		! note for exception handling
+10:	EXT(5b, 10b)			! note for exception handling
 	sub	%g1, 128, %g1		! detract from length
 	addx	%g0, %g7, %g7		! add in last carry bit
 	andcc	%g1, 0xffffff80, %g0	! more to csum?
@@ -379,7 +356,7 @@ cctbl:	CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x68,%g2,%g3,%g4,%g5)
 	CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x28,%g2,%g3,%g4,%g5)
 	CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x18,%g2,%g3,%g4,%g5)
 	CSUMCOPY_LASTCHUNK(%o0,%o1,%g7,0x08,%g2,%g3,%g4,%g5)
-12:	EXT(cctbl, 12b, 22f)		! note for exception table handling
+12:	EXT(cctbl, 12b)			! note for exception table handling
 	addx	%g0, %g7, %g7
 	andcc	%o3, 0xf, %g0		! check for low bits set
 ccte:	bne	cc_end_cruft		! something left, handle it out of band
@@ -390,7 +367,7 @@ ccdbl:	CSUMCOPY_BIGCHUNK_ALIGNED(%o0,%o1,%g7,0x00,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o
 	CSUMCOPY_BIGCHUNK_ALIGNED(%o0,%o1,%g7,0x20,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
 	CSUMCOPY_BIGCHUNK_ALIGNED(%o0,%o1,%g7,0x40,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
 	CSUMCOPY_BIGCHUNK_ALIGNED(%o0,%o1,%g7,0x60,%o4,%o5,%g2,%g3,%g4,%g5,%o2,%o3)
-11:	EXT(ccdbl, 11b, 21f)		! note for exception table handling
+11:	EXT(ccdbl, 11b)			! note for exception table handling
 	sub	%g1, 128, %g1		! detract from length
 	addx	%g0, %g7, %g7		! add in last carry bit
 	andcc	%g1, 0xffffff80, %g0	! more to csum?
@@ -407,9 +384,9 @@ ccslow:	cmp	%g1, 0
 	be,a	1f
 	 srl	%g1, 1, %g4		
 	sub	%g1, 1, %g1	
-	EX(ldub	[%o0], %g5, add %g1, 1)
+	EX(ldub	[%o0], %g5)
 	add	%o0, 1, %o0	
-	EX2(stb	%g5, [%o1])
+	EX(stb	%g5, [%o1])
 	srl	%g1, 1, %g4
 	add	%o1, 1, %o1
 1:	cmp	%g4, 0		
@@ -418,34 +395,34 @@ ccslow:	cmp	%g1, 0
 	andcc	%o0, 2, %g0	
 	be,a	1f
 	 srl	%g4, 1, %g4
-	EX(lduh	[%o0], %o4, add %g1, 0)
+	EX(lduh	[%o0], %o4)
 	sub	%g1, 2, %g1	
 	srl	%o4, 8, %g2
 	sub	%g4, 1, %g4	
-	EX2(stb	%g2, [%o1])
+	EX(stb	%g2, [%o1])
 	add	%o4, %g5, %g5
-	EX2(stb	%o4, [%o1 + 1])
+	EX(stb	%o4, [%o1 + 1])
 	add	%o0, 2, %o0	
 	srl	%g4, 1, %g4
 	add	%o1, 2, %o1
 1:	cmp	%g4, 0		
 	be,a	2f
 	 andcc	%g1, 2, %g0
-	EX3(ld	[%o0], %o4)
+	EX(ld	[%o0], %o4)
 5:	srl	%o4, 24, %g2
 	srl	%o4, 16, %g3
-	EX2(stb	%g2, [%o1])
+	EX(stb	%g2, [%o1])
 	srl	%o4, 8, %g2
-	EX2(stb	%g3, [%o1 + 1])
+	EX(stb	%g3, [%o1 + 1])
 	add	%o0, 4, %o0
-	EX2(stb	%g2, [%o1 + 2])
+	EX(stb	%g2, [%o1 + 2])
 	addcc	%o4, %g5, %g5
-	EX2(stb	%o4, [%o1 + 3])
+	EX(stb	%o4, [%o1 + 3])
 	addx	%g5, %g0, %g5	! I am now to lazy to optimize this (question it
 	add	%o1, 4, %o1	! is worthy). Maybe some day - with the sll/srl
 	subcc	%g4, 1, %g4	! tricks
 	bne,a	5b
-	 EX3(ld	[%o0], %o4)
+	 EX(ld	[%o0], %o4)
 	sll	%g5, 16, %g2
 	srl	%g5, 16, %g5
 	srl	%g2, 16, %g2
@@ -453,19 +430,19 @@ ccslow:	cmp	%g1, 0
 	add	%g2, %g5, %g5 
 2:	be,a	3f		
 	 andcc	%g1, 1, %g0
-	EX(lduh	[%o0], %o4, and %g1, 3)
+	EX(lduh	[%o0], %o4)
 	andcc	%g1, 1, %g0
 	srl	%o4, 8, %g2
 	add	%o0, 2, %o0	
-	EX2(stb	%g2, [%o1])
+	EX(stb	%g2, [%o1])
 	add	%g5, %o4, %g5
-	EX2(stb	%o4, [%o1 + 1])
+	EX(stb	%o4, [%o1 + 1])
 	add	%o1, 2, %o1
 3:	be,a	1f		
 	 sll	%g5, 16, %o4
-	EX(ldub	[%o0], %g2, add %g0, 1)
+	EX(ldub	[%o0], %g2)
 	sll	%g2, 8, %o4	
-	EX2(stb	%g2, [%o1])
+	EX(stb	%g2, [%o1])
 	add	%g5, %o4, %g5
 	sll	%g5, 16, %o4
 1:	addcc	%o4, %g5, %g5
@@ -481,113 +458,10 @@ ccslow:	cmp	%g1, 0
 4:	addcc	%g7, %g5, %g7
 	retl	
 	 addx	%g0, %g7, %o0
-__csum_partial_copy_end:
 
 /* We do these strange calculations for the csum_*_from_user case only, ie.
  * we only bother with faults on loads... */
 
-/* o2 = ((g2%20)&3)*8
- * o3 = g1 - (g2/20)*32 - o2 */
-20:
-	cmp	%g2, 20
-	blu,a	1f
-	 and	%g2, 3, %o2
-	sub	%g1, 32, %g1
-	b	20b
-	 sub	%g2, 20, %g2
-1:
-	sll	%o2, 3, %o2
-	b	31f
-	 sub	%g1, %o2, %o3
-
-/* o2 = (!(g2 & 15) ? 0 : (((g2 & 15) + 1) & ~1)*8)
- * o3 = g1 - (g2/16)*32 - o2 */
-21:
-	andcc	%g2, 15, %o3
-	srl	%g2, 4, %g2
-	be,a	1f
-	 clr	%o2
-	add	%o3, 1, %o3
-	and	%o3, 14, %o3
-	sll	%o3, 3, %o2
-1:
-	sll	%g2, 5, %g2
-	sub	%g1, %g2, %o3
-	b	31f
-	 sub	%o3, %o2, %o3
-
-/* o0 += (g2/10)*16 - 0x70
- * 01 += (g2/10)*16 - 0x70
- * o2 = (g2 % 10) ? 8 : 0
- * o3 += 0x70 - (g2/10)*16 - o2 */
-22:
-	cmp	%g2, 10
-	blu,a	1f
-	 sub	%o0, 0x70, %o0
-	add	%o0, 16, %o0
-	add	%o1, 16, %o1
-	sub	%o3, 16, %o3
-	b	22b
-	 sub	%g2, 10, %g2
-1:
-	sub	%o1, 0x70, %o1
-	add	%o3, 0x70, %o3
-	clr	%o2
-	tst	%g2
-	bne,a	1f
-	 mov	8, %o2
-1:
-	b	31f
-	 sub	%o3, %o2, %o3
-96:
-	and	%g1, 3, %g1
-	sll	%g4, 2, %g4
-	add	%g1, %g4, %o3
-30:
-/* %o1 is dst
- * %o3 is # bytes to zero out
- * %o4 is faulting address
- * %o5 is %pc where fault occurred */
-	clr	%o2
-31:
-/* %o0 is src
- * %o1 is dst
- * %o2 is # of bytes to copy from src to dst
- * %o3 is # bytes to zero out
- * %o4 is faulting address
- * %o5 is %pc where fault occurred */
-	save	%sp, -104, %sp
-        mov     %i5, %o0
-        mov     %i7, %o1
-        mov	%i4, %o2
-        call    lookup_fault
-	 mov	%g7, %i4
-	cmp	%o0, 2
-	bne	1f	
-	 add	%g0, -EFAULT, %i5
-	tst	%i2
-	be	2f
-	 mov	%i0, %o1
-	mov	%i1, %o0
-5:
-	call	memcpy
-	 mov	%i2, %o2
-	tst	%o0
-	bne,a	2f
-	 add	%i3, %i2, %i3
-	add	%i1, %i2, %i1
-2:
-	mov	%i1, %o0
-6:
-	call	__bzero
-	 mov	%i3, %o1
-1:
-	ld	[%sp + 168], %o2		! struct_ptr of parent
-	st	%i5, [%o2]
+cc_fault:
 	ret
-	 restore
-
-        .section __ex_table,#alloc
-        .align 4
-        .word 5b,2
-	.word 6b,2
+	 clr	%o0
diff --git a/arch/sparc/lib/csum_copy.S b/arch/sparc/lib/csum_copy.S
index 26c644ba3ecb..0c0268e77155 100644
--- a/arch/sparc/lib/csum_copy.S
+++ b/arch/sparc/lib/csum_copy.S
@@ -68,9 +68,10 @@
 	.globl		FUNC_NAME
 	.type		FUNC_NAME,#function
 	EXPORT_SYMBOL(FUNC_NAME)
-FUNC_NAME:		/* %o0=src, %o1=dst, %o2=len, %o3=sum */
+FUNC_NAME:		/* %o0=src, %o1=dst, %o2=len */
 	LOAD(prefetch, %o0 + 0x000, #n_reads)
 	xor		%o0, %o1, %g1
+	mov		1, %o3
 	clr		%o4
 	andcc		%g1, 0x3, %g0
 	bne,pn		%icc, 95f
diff --git a/arch/sparc/lib/csum_copy_from_user.S b/arch/sparc/lib/csum_copy_from_user.S
index d20b9594f0c7..b0ba8d4dd439 100644
--- a/arch/sparc/lib/csum_copy_from_user.S
+++ b/arch/sparc/lib/csum_copy_from_user.S
@@ -9,14 +9,14 @@
 	.section .fixup, "ax";	\
 	.align 4;		\
 99:	retl;			\
-	 mov	-1, %o0;	\
+	 mov	0, %o0;		\
 	.section __ex_table,"a";\
 	.align 4;		\
 	.word 98b, 99b;		\
 	.text;			\
 	.align 4;
 
-#define FUNC_NAME		__csum_partial_copy_from_user
+#define FUNC_NAME		csum_and_copy_from_user
 #define LOAD(type,addr,dest)	type##a [addr] %asi, dest
 
 #include "csum_copy.S"
diff --git a/arch/sparc/lib/csum_copy_to_user.S b/arch/sparc/lib/csum_copy_to_user.S
index d71c0c81e8ab..91ba36dbf7d2 100644
--- a/arch/sparc/lib/csum_copy_to_user.S
+++ b/arch/sparc/lib/csum_copy_to_user.S
@@ -9,14 +9,14 @@
 	.section .fixup,"ax";	\
 	.align 4;		\
 99:	retl;			\
-	 mov	-1, %o0;	\
+	 mov	0, %o0;		\
 	.section __ex_table,"a";\
 	.align 4;		\
 	.word 98b, 99b;		\
 	.text;			\
 	.align 4;
 
-#define FUNC_NAME		__csum_partial_copy_to_user
+#define FUNC_NAME		csum_and_copy_to_user
 #define STORE(type,src,addr)	type##a src, [addr] %asi
 
 #include "csum_copy.S"
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index 8071bfd72349..40ce087dfecf 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -288,8 +288,6 @@ no_context:
 		if (fixup > 10) {
 			extern const unsigned int __memset_start[];
 			extern const unsigned int __memset_end[];
-			extern const unsigned int __csum_partial_copy_start[];
-			extern const unsigned int __csum_partial_copy_end[];
 
 #ifdef DEBUG_EXCEPTIONS
 			printk("Exception: PC<%08lx> faddr<%08lx>\n",
@@ -298,9 +296,7 @@ no_context:
 				regs->pc, fixup, g2);
 #endif
 			if ((regs->pc >= (unsigned long)__memset_start &&
-			     regs->pc < (unsigned long)__memset_end) ||
-			    (regs->pc >= (unsigned long)__csum_partial_copy_start &&
-			     regs->pc < (unsigned long)__csum_partial_copy_end)) {
+			     regs->pc < (unsigned long)__memset_end)) {
 				regs->u_regs[UREG_I4] = address;
 				regs->u_regs[UREG_I5] = regs->pc;
 			}
diff --git a/arch/x86/include/asm/checksum.h b/arch/x86/include/asm/checksum.h
index 0ada98d5d09f..bca625a60186 100644
--- a/arch/x86/include/asm/checksum.h
+++ b/arch/x86/include/asm/checksum.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #define  _HAVE_ARCH_COPY_AND_CSUM_FROM_USER 1
 #define HAVE_CSUM_COPY_USER
+#define _HAVE_ARCH_CSUM_AND_COPY
 #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 11624c8a9d8d..17da95387997 100644
--- a/arch/x86/include/asm/checksum_32.h
+++ b/arch/x86/include/asm/checksum_32.h
@@ -27,9 +27,7 @@ asmlinkage __wsum csum_partial(const void *buff, int len, __wsum sum);
  * better 64-bit) boundary
  */
 
-asmlinkage __wsum csum_partial_copy_generic(const void *src, void *dst,
-					    int len, __wsum sum,
-					    int *src_err_ptr, int *dst_err_ptr);
+asmlinkage __wsum csum_partial_copy_generic(const void *src, void *dst, int len);
 
 /*
  *	Note: when you get a NULL pointer exception here this means someone
@@ -38,26 +36,20 @@ asmlinkage __wsum csum_partial_copy_generic(const void *src, void *dst,
  *	If you use these functions directly please don't forget the
  *	access_ok().
  */
-static inline __wsum csum_partial_copy_nocheck(const void *src, void *dst,
-					       int len, __wsum sum)
+static inline __wsum csum_partial_copy_nocheck(const void *src, void *dst, int len)
 {
-	return csum_partial_copy_generic(src, dst, len, sum, NULL, NULL);
+	return csum_partial_copy_generic(src, dst, len);
 }
 
 static inline __wsum csum_and_copy_from_user(const void __user *src,
-					     void *dst, int len,
-					     __wsum sum, int *err_ptr)
+					     void *dst, int len)
 {
 	__wsum ret;
 
 	might_sleep();
-	if (!user_access_begin(src, len)) {
-		if (len)
-			*err_ptr = -EFAULT;
-		return sum;
-	}
-	ret = csum_partial_copy_generic((__force void *)src, dst,
-					len, sum, err_ptr, NULL);
+	if (!user_access_begin(src, len))
+		return 0;
+	ret = csum_partial_copy_generic((__force void *)src, dst, len);
 	user_access_end();
 
 	return ret;
@@ -178,23 +170,17 @@ static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
  */
 static inline __wsum csum_and_copy_to_user(const void *src,
 					   void __user *dst,
-					   int len, __wsum sum,
-					   int *err_ptr)
+					   int len)
 {
 	__wsum ret;
 
 	might_sleep();
-	if (user_access_begin(dst, len)) {
-		ret = csum_partial_copy_generic(src, (__force void *)dst,
-						len, sum, NULL, err_ptr);
-		user_access_end();
-		return ret;
-	}
+	if (!user_access_begin(dst, len))
+		return 0;
 
-	if (len)
-		*err_ptr = -EFAULT;
-
-	return (__force __wsum)-1; /* invalid checksum */
+	ret = csum_partial_copy_generic(src, (__force void *)dst, len);
+	user_access_end();
+	return ret;
 }
 
 #endif /* _ASM_X86_CHECKSUM_32_H */
diff --git a/arch/x86/include/asm/checksum_64.h b/arch/x86/include/asm/checksum_64.h
index 0a289b87e872..407beebadaf4 100644
--- a/arch/x86/include/asm/checksum_64.h
+++ b/arch/x86/include/asm/checksum_64.h
@@ -130,17 +130,11 @@ static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
 extern __wsum csum_partial(const void *buff, int len, __wsum sum);
 
 /* Do not call this directly. Use the wrappers below */
-extern __visible __wsum csum_partial_copy_generic(const void *src, const void *dst,
-					int len, __wsum sum,
-					int *src_err_ptr, int *dst_err_ptr);
+extern __visible __wsum csum_partial_copy_generic(const void *src, void *dst, int len);
 
-
-extern __wsum csum_and_copy_from_user(const void __user *src, void *dst,
-					  int len, __wsum isum, int *errp);
-extern __wsum csum_and_copy_to_user(const void *src, void __user *dst,
-					int len, __wsum isum, int *errp);
-extern __wsum csum_partial_copy_nocheck(const void *src, void *dst,
-					int len, __wsum sum);
+extern __wsum csum_and_copy_from_user(const void __user *src, void *dst, int len);
+extern __wsum csum_and_copy_to_user(const void *src, void __user *dst, int len);
+extern __wsum csum_partial_copy_nocheck(const void *src, void *dst, int len);
 
 /**
  * ip_compute_csum - Compute an 16bit IP checksum.
diff --git a/arch/x86/lib/checksum_32.S b/arch/x86/lib/checksum_32.S
index d1d768912368..4304320e51f4 100644
--- a/arch/x86/lib/checksum_32.S
+++ b/arch/x86/lib/checksum_32.S
@@ -253,28 +253,17 @@ EXPORT_SYMBOL(csum_partial)
 
 /*
 unsigned int csum_partial_copy_generic (const char *src, char *dst,
-				  int len, int sum, int *src_err_ptr, int *dst_err_ptr)
+				  int len)
  */ 
 
 /*
  * Copy from ds while checksumming, otherwise like csum_partial
- *
- * The macros SRC and DST specify the type of access for the instruction.
- * thus we can call a custom exception handler for all access types.
- *
- * FIXME: could someone double-check whether I haven't mixed up some SRC and
- *	  DST definitions? It's damn hard to trigger all cases.  I hope I got
- *	  them all but there's no guarantee.
  */
 
-#define SRC(y...)			\
+#define EXC(y...)			\
 	9999: y;			\
 	_ASM_EXTABLE_UA(9999b, 6001f)
 
-#define DST(y...)			\
-	9999: y;			\
-	_ASM_EXTABLE_UA(9999b, 6002f)
-
 #ifndef CONFIG_X86_USE_PPRO_CHECKSUM
 
 #define ARGBASE 16		
@@ -285,20 +274,20 @@ SYM_FUNC_START(csum_partial_copy_generic)
 	pushl %edi
 	pushl %esi
 	pushl %ebx
-	movl ARGBASE+16(%esp),%eax	# sum
 	movl ARGBASE+12(%esp),%ecx	# len
 	movl ARGBASE+4(%esp),%esi	# src
 	movl ARGBASE+8(%esp),%edi	# dst
 
+	movl $-1, %eax			# sum
 	testl $2, %edi			# Check alignment. 
 	jz 2f				# Jump if alignment is ok.
 	subl $2, %ecx			# Alignment uses up two bytes.
 	jae 1f				# Jump if we had at least two bytes.
 	addl $2, %ecx			# ecx was < 2.  Deal with it.
 	jmp 4f
-SRC(1:	movw (%esi), %bx	)
+EXC(1:	movw (%esi), %bx	)
 	addl $2, %esi
-DST(	movw %bx, (%edi)	)
+EXC(	movw %bx, (%edi)	)
 	addl $2, %edi
 	addw %bx, %ax	
 	adcl $0, %eax
@@ -306,34 +295,34 @@ DST(	movw %bx, (%edi)	)
 	movl %ecx, FP(%esp)
 	shrl $5, %ecx
 	jz 2f
-	testl %esi, %esi
-SRC(1:	movl (%esi), %ebx	)
-SRC(	movl 4(%esi), %edx	)
+	testl %esi, %esi		# what's wrong with clc?
+EXC(1:	movl (%esi), %ebx	)
+EXC(	movl 4(%esi), %edx	)
 	adcl %ebx, %eax
-DST(	movl %ebx, (%edi)	)
+EXC(	movl %ebx, (%edi)	)
 	adcl %edx, %eax
-DST(	movl %edx, 4(%edi)	)
+EXC(	movl %edx, 4(%edi)	)
 
-SRC(	movl 8(%esi), %ebx	)
-SRC(	movl 12(%esi), %edx	)
+EXC(	movl 8(%esi), %ebx	)
+EXC(	movl 12(%esi), %edx	)
 	adcl %ebx, %eax
-DST(	movl %ebx, 8(%edi)	)
+EXC(	movl %ebx, 8(%edi)	)
 	adcl %edx, %eax
-DST(	movl %edx, 12(%edi)	)
+EXC(	movl %edx, 12(%edi)	)
 
-SRC(	movl 16(%esi), %ebx 	)
-SRC(	movl 20(%esi), %edx	)
+EXC(	movl 16(%esi), %ebx 	)
+EXC(	movl 20(%esi), %edx	)
 	adcl %ebx, %eax
-DST(	movl %ebx, 16(%edi)	)
+EXC(	movl %ebx, 16(%edi)	)
 	adcl %edx, %eax
-DST(	movl %edx, 20(%edi)	)
+EXC(	movl %edx, 20(%edi)	)
 
-SRC(	movl 24(%esi), %ebx	)
-SRC(	movl 28(%esi), %edx	)
+EXC(	movl 24(%esi), %ebx	)
+EXC(	movl 28(%esi), %edx	)
 	adcl %ebx, %eax
-DST(	movl %ebx, 24(%edi)	)
+EXC(	movl %ebx, 24(%edi)	)
 	adcl %edx, %eax
-DST(	movl %edx, 28(%edi)	)
+EXC(	movl %edx, 28(%edi)	)
 
 	lea 32(%esi), %esi
 	lea 32(%edi), %edi
@@ -345,9 +334,9 @@ DST(	movl %edx, 28(%edi)	)
 	andl $0x1c, %edx
 	je 4f
 	shrl $2, %edx			# This clears CF
-SRC(3:	movl (%esi), %ebx	)
+EXC(3:	movl (%esi), %ebx	)
 	adcl %ebx, %eax
-DST(	movl %ebx, (%edi)	)
+EXC(	movl %ebx, (%edi)	)
 	lea 4(%esi), %esi
 	lea 4(%edi), %edi
 	dec %edx
@@ -357,39 +346,24 @@ DST(	movl %ebx, (%edi)	)
 	jz 7f
 	cmpl $2, %ecx
 	jb 5f
-SRC(	movw (%esi), %cx	)
+EXC(	movw (%esi), %cx	)
 	leal 2(%esi), %esi
-DST(	movw %cx, (%edi)	)
+EXC(	movw %cx, (%edi)	)
 	leal 2(%edi), %edi
 	je 6f
 	shll $16,%ecx
-SRC(5:	movb (%esi), %cl	)
-DST(	movb %cl, (%edi)	)
+EXC(5:	movb (%esi), %cl	)
+EXC(	movb %cl, (%edi)	)
 6:	addl %ecx, %eax
 	adcl $0, %eax
 7:
-5000:
 
 # Exception handler:
 .section .fixup, "ax"							
 
 6001:
-	movl ARGBASE+20(%esp), %ebx	# src_err_ptr
-	movl $-EFAULT, (%ebx)
-
-	# zero the complete destination - computing the rest
-	# is too much work 
-	movl ARGBASE+8(%esp), %edi	# dst
-	movl ARGBASE+12(%esp), %ecx	# len
-	xorl %eax,%eax
-	rep ; stosb
-
-	jmp 5000b
-
-6002:
-	movl ARGBASE+24(%esp), %ebx	# dst_err_ptr
-	movl $-EFAULT,(%ebx)
-	jmp 5000b
+	xorl %eax, %eax
+	jmp 7b
 
 .previous
 
@@ -405,14 +379,14 @@ SYM_FUNC_END(csum_partial_copy_generic)
 /* Version for PentiumII/PPro */
 
 #define ROUND1(x) \
-	SRC(movl x(%esi), %ebx	)	;	\
+	EXC(movl x(%esi), %ebx	)	;	\
 	addl %ebx, %eax			;	\
-	DST(movl %ebx, x(%edi)	)	; 
+	EXC(movl %ebx, x(%edi)	)	;
 
 #define ROUND(x) \
-	SRC(movl x(%esi), %ebx	)	;	\
+	EXC(movl x(%esi), %ebx	)	;	\
 	adcl %ebx, %eax			;	\
-	DST(movl %ebx, x(%edi)	)	;
+	EXC(movl %ebx, x(%edi)	)	;
 
 #define ARGBASE 12
 		
@@ -423,7 +397,7 @@ SYM_FUNC_START(csum_partial_copy_generic)
 	movl ARGBASE+4(%esp),%esi	#src
 	movl ARGBASE+8(%esp),%edi	#dst	
 	movl ARGBASE+12(%esp),%ecx	#len
-	movl ARGBASE+16(%esp),%eax	#sum
+	movl $-1, %eax			#sum
 #	movl %ecx, %edx  
 	movl %ecx, %ebx  
 	movl %esi, %edx
@@ -439,7 +413,7 @@ SYM_FUNC_START(csum_partial_copy_generic)
 	JMP_NOSPEC ebx
 1:	addl $64,%esi
 	addl $64,%edi 
-	SRC(movb -32(%edx),%bl)	; SRC(movb (%edx),%bl)
+	EXC(movb -32(%edx),%bl)	; EXC(movb (%edx),%bl)
 	ROUND1(-64) ROUND(-60) ROUND(-56) ROUND(-52)	
 	ROUND (-48) ROUND(-44) ROUND(-40) ROUND(-36)	
 	ROUND (-32) ROUND(-28) ROUND(-24) ROUND(-20)	
@@ -453,29 +427,20 @@ SYM_FUNC_START(csum_partial_copy_generic)
 	jz 7f
 	cmpl $2, %edx
 	jb 5f
-SRC(	movw (%esi), %dx         )
+EXC(	movw (%esi), %dx         )
 	leal 2(%esi), %esi
-DST(	movw %dx, (%edi)         )
+EXC(	movw %dx, (%edi)         )
 	leal 2(%edi), %edi
 	je 6f
 	shll $16,%edx
 5:
-SRC(	movb (%esi), %dl         )
-DST(	movb %dl, (%edi)         )
+EXC(	movb (%esi), %dl         )
+EXC(	movb %dl, (%edi)         )
 6:	addl %edx, %eax
 	adcl $0, %eax
 7:
 .section .fixup, "ax"
-6001:	movl	ARGBASE+20(%esp), %ebx	# src_err_ptr	
-	movl $-EFAULT, (%ebx)
-	# zero the complete destination (computing the rest is too much work)
-	movl ARGBASE+8(%esp),%edi	# dst
-	movl ARGBASE+12(%esp),%ecx	# len
-	xorl %eax,%eax
-	rep; stosb
-	jmp 7b
-6002:	movl ARGBASE+24(%esp), %ebx	# dst_err_ptr
-	movl $-EFAULT, (%ebx)
+6001:	xorl %eax, %eax
 	jmp  7b			
 .previous				
 
diff --git a/arch/x86/lib/csum-copy_64.S b/arch/x86/lib/csum-copy_64.S
index 3394a8ff7fd0..1fbd8ee9642d 100644
--- a/arch/x86/lib/csum-copy_64.S
+++ b/arch/x86/lib/csum-copy_64.S
@@ -18,9 +18,6 @@
  * rdi  source
  * rsi  destination
  * edx  len (32bit)
- * ecx  sum (32bit)
- * r8   src_err_ptr (int)
- * r9   dst_err_ptr (int)
  *
  * Output
  * eax  64bit sum. undefined in case of exception.
@@ -31,44 +28,32 @@
 
 	.macro source
 10:
-	_ASM_EXTABLE_UA(10b, .Lbad_source)
+	_ASM_EXTABLE_UA(10b, .Lfault)
 	.endm
 
 	.macro dest
 20:
-	_ASM_EXTABLE_UA(20b, .Lbad_dest)
+	_ASM_EXTABLE_UA(20b, .Lfault)
 	.endm
 
-	/*
-	 * No _ASM_EXTABLE_UA; this is used for intentional prefetch on a
-	 * potentially unmapped kernel address.
-	 */
-	.macro ignore L=.Lignore
-30:
-	_ASM_EXTABLE(30b, \L)
-	.endm
-
-
 SYM_FUNC_START(csum_partial_copy_generic)
-	cmpl	$3*64, %edx
-	jle	.Lignore
-
-.Lignore:
-	subq  $7*8, %rsp
-	movq  %rbx, 2*8(%rsp)
-	movq  %r12, 3*8(%rsp)
-	movq  %r14, 4*8(%rsp)
-	movq  %r13, 5*8(%rsp)
-	movq  %r15, 6*8(%rsp)
+	subq  $5*8, %rsp
+	movq  %rbx, 0*8(%rsp)
+	movq  %r12, 1*8(%rsp)
+	movq  %r14, 2*8(%rsp)
+	movq  %r13, 3*8(%rsp)
+	movq  %r15, 4*8(%rsp)
 
-	movq  %r8, (%rsp)
-	movq  %r9, 1*8(%rsp)
-
-	movl  %ecx, %eax
+	movl  $-1, %eax
+	xorl  %r9d, %r9d
 	movl  %edx, %ecx
+	cmpl  $8, %ecx
+	jb    .Lshort
 
-	xorl  %r9d, %r9d
-	movq  %rcx, %r12
+	testb  $7, %sil
+	jne   .Lunaligned
+.Laligned:
+	movl  %ecx, %r12d
 
 	shrq  $6, %r12
 	jz	.Lhandle_tail       /* < 64 */
@@ -99,7 +84,12 @@ SYM_FUNC_START(csum_partial_copy_generic)
 	source
 	movq  56(%rdi), %r13
 
-	ignore 2f
+30:
+	/*
+	 * No _ASM_EXTABLE_UA; this is used for intentional prefetch on a
+	 * potentially unmapped kernel address.
+	 */
+	_ASM_EXTABLE(30b, 2f)
 	prefetcht0 5*64(%rdi)
 2:
 	adcq  %rbx, %rax
@@ -131,8 +121,6 @@ SYM_FUNC_START(csum_partial_copy_generic)
 	dest
 	movq %r13, 56(%rsi)
 
-3:
-
 	leaq 64(%rdi), %rdi
 	leaq 64(%rsi), %rsi
 
@@ -142,8 +130,8 @@ SYM_FUNC_START(csum_partial_copy_generic)
 
 	/* do last up to 56 bytes */
 .Lhandle_tail:
-	/* ecx:	count */
-	movl %ecx, %r10d
+	/* ecx:	count, rcx.63: the end result needs to be rol8 */
+	movq %rcx, %r10
 	andl $63, %ecx
 	shrl $3, %ecx
 	jz	.Lfold
@@ -172,6 +160,7 @@ SYM_FUNC_START(csum_partial_copy_generic)
 .Lhandle_7:
 	movl %r10d, %ecx
 	andl $7, %ecx
+.L1:				/* .Lshort rejoins the common path here */
 	shrl $1, %ecx
 	jz   .Lhandle_1
 	movl $2, %edx
@@ -203,26 +192,65 @@ SYM_FUNC_START(csum_partial_copy_generic)
 	adcl %r9d, %eax		/* carry */
 
 .Lende:
-	movq 2*8(%rsp), %rbx
-	movq 3*8(%rsp), %r12
-	movq 4*8(%rsp), %r14
-	movq 5*8(%rsp), %r13
-	movq 6*8(%rsp), %r15
-	addq $7*8, %rsp
+	testq %r10, %r10
+	js  .Lwas_odd
+.Lout:
+	movq 0*8(%rsp), %rbx
+	movq 1*8(%rsp), %r12
+	movq 2*8(%rsp), %r14
+	movq 3*8(%rsp), %r13
+	movq 4*8(%rsp), %r15
+	addq $5*8, %rsp
 	ret
+.Lshort:
+	movl %ecx, %r10d
+	jmp  .L1
+.Lunaligned:
+	xorl %ebx, %ebx
+	testb $1, %sil
+	jne  .Lodd
+1:	testb $2, %sil
+	je   2f
+	source
+	movw (%rdi), %bx
+	dest
+	movw %bx, (%rsi)
+	leaq 2(%rdi), %rdi
+	subq $2, %rcx
+	leaq 2(%rsi), %rsi
+	addq %rbx, %rax
+2:	testb $4, %sil
+	je .Laligned
+	source
+	movl (%rdi), %ebx
+	dest
+	movl %ebx, (%rsi)
+	leaq 4(%rdi), %rdi
+	subq $4, %rcx
+	leaq 4(%rsi), %rsi
+	addq %rbx, %rax
+	jmp .Laligned
+
+.Lodd:
+	source
+	movb (%rdi), %bl
+	dest
+	movb %bl, (%rsi)
+	leaq 1(%rdi), %rdi
+	leaq 1(%rsi), %rsi
+	/* decrement, set MSB */
+	leaq -1(%rcx, %rcx), %rcx
+	rorq $1, %rcx
+	shll $8, %ebx
+	addq %rbx, %rax
+	jmp 1b
+
+.Lwas_odd:
+	roll $8, %eax
+	jmp .Lout
 
-	/* Exception handlers. Very simple, zeroing is done in the wrappers */
-.Lbad_source:
-	movq (%rsp), %rax
-	testq %rax, %rax
-	jz   .Lende
-	movl $-EFAULT, (%rax)
-	jmp  .Lende
-
-.Lbad_dest:
-	movq 8(%rsp), %rax
-	testq %rax, %rax
-	jz   .Lende
-	movl $-EFAULT, (%rax)
-	jmp .Lende
+	/* Exception: just return 0 */
+.Lfault:
+	xorl %eax, %eax
+	jmp  .Lout
 SYM_FUNC_END(csum_partial_copy_generic)
diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c
index ee63d7576fd2..189344924a2b 100644
--- a/arch/x86/lib/csum-wrappers_64.c
+++ b/arch/x86/lib/csum-wrappers_64.c
@@ -21,52 +21,16 @@
  * src and dst are best aligned to 64bits.
  */
 __wsum
-csum_and_copy_from_user(const void __user *src, void *dst,
-			    int len, __wsum isum, int *errp)
+csum_and_copy_from_user(const void __user *src, void *dst, int len)
 {
-	might_sleep();
-	*errp = 0;
+	__wsum sum;
 
+	might_sleep();
 	if (!user_access_begin(src, len))
-		goto out_err;
-
-	/*
-	 * Why 6, not 7? To handle odd addresses aligned we
-	 * would need to do considerable complications to fix the
-	 * checksum which is defined as an 16bit accumulator. The
-	 * fix alignment code is primarily for performance
-	 * compatibility with 32bit and that will handle odd
-	 * addresses slowly too.
-	 */
-	if (unlikely((unsigned long)src & 6)) {
-		while (((unsigned long)src & 6) && len >= 2) {
-			__u16 val16;
-
-			unsafe_get_user(val16, (const __u16 __user *)src, out);
-
-			*(__u16 *)dst = val16;
-			isum = (__force __wsum)add32_with_carry(
-					(__force unsigned)isum, val16);
-			src += 2;
-			dst += 2;
-			len -= 2;
-		}
-	}
-	isum = csum_partial_copy_generic((__force const void *)src,
-				dst, len, isum, errp, NULL);
-	user_access_end();
-	if (unlikely(*errp))
-		goto out_err;
-
-	return isum;
-
-out:
+		return 0;
+	sum = csum_partial_copy_generic((__force const void *)src, dst, len);
 	user_access_end();
-out_err:
-	*errp = -EFAULT;
-	memset(dst, 0, len);
-
-	return isum;
+	return sum;
 }
 EXPORT_SYMBOL(csum_and_copy_from_user);
 
@@ -82,40 +46,16 @@ EXPORT_SYMBOL(csum_and_copy_from_user);
  * src and dst are best aligned to 64bits.
  */
 __wsum
-csum_and_copy_to_user(const void *src, void __user *dst,
-			  int len, __wsum isum, int *errp)
+csum_and_copy_to_user(const void *src, void __user *dst, int len)
 {
-	__wsum ret;
+	__wsum sum;
 
 	might_sleep();
-
-	if (!user_access_begin(dst, len)) {
-		*errp = -EFAULT;
+	if (!user_access_begin(dst, len))
 		return 0;
-	}
-
-	if (unlikely((unsigned long)dst & 6)) {
-		while (((unsigned long)dst & 6) && len >= 2) {
-			__u16 val16 = *(__u16 *)src;
-
-			isum = (__force __wsum)add32_with_carry(
-					(__force unsigned)isum, val16);
-			unsafe_put_user(val16, (__u16 __user *)dst, out);
-			src += 2;
-			dst += 2;
-			len -= 2;
-		}
-	}
-
-	*errp = 0;
-	ret = csum_partial_copy_generic(src, (void __force *)dst,
-					len, isum, NULL, errp);
-	user_access_end();
-	return ret;
-out:
+	sum = csum_partial_copy_generic(src, (void __force *)dst, len);
 	user_access_end();
-	*errp = -EFAULT;
-	return isum;
+	return sum;
 }
 EXPORT_SYMBOL(csum_and_copy_to_user);
 
@@ -129,9 +69,9 @@ EXPORT_SYMBOL(csum_and_copy_to_user);
  * Returns an 32bit unfolded checksum of the buffer.
  */
 __wsum
-csum_partial_copy_nocheck(const void *src, void *dst, int len, __wsum sum)
+csum_partial_copy_nocheck(const void *src, void *dst, int len)
 {
-	return csum_partial_copy_generic(src, dst, len, sum, NULL, NULL);
+	return csum_partial_copy_generic(src, dst, len);
 }
 EXPORT_SYMBOL(csum_partial_copy_nocheck);
 
diff --git a/arch/x86/um/asm/checksum.h b/arch/x86/um/asm/checksum.h
index ff6bba2c8ab6..b07824500363 100644
--- a/arch/x86/um/asm/checksum.h
+++ b/arch/x86/um/asm/checksum.h
@@ -20,22 +20,6 @@
  */
 extern __wsum csum_partial(const void *buff, int len, __wsum sum);
 
-/*
- *	Note: when you get a NULL pointer exception here this means someone
- *	passed in an incorrect kernel address to one of these functions.
- *
- *	If you use these functions directly please don't forget the
- *	access_ok().
- */
-
-static __inline__
-__wsum csum_partial_copy_nocheck(const void *src, void *dst,
-				       int len, __wsum sum)
-{
-	memcpy(dst, src, len);
-	return csum_partial(dst, len, sum);
-}
-
 /**
  * csum_fold - Fold and invert a 32bit checksum.
  * sum: 32bit unfolded sum
diff --git a/arch/x86/um/asm/checksum_32.h b/arch/x86/um/asm/checksum_32.h
index b9ac7c9eb72c..0b13c2947ad1 100644
--- a/arch/x86/um/asm/checksum_32.h
+++ b/arch/x86/um/asm/checksum_32.h
@@ -35,27 +35,4 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
 	return csum_fold(sum);
 }
 
-/*
- *	Copy and checksum to user
- */
-#define HAVE_CSUM_COPY_USER
-static __inline__ __wsum csum_and_copy_to_user(const void *src,
-						     void __user *dst,
-						     int len, __wsum sum, int *err_ptr)
-{
-	if (access_ok(dst, len)) {
-		if (copy_to_user(dst, src, len)) {
-			*err_ptr = -EFAULT;
-			return (__force __wsum)-1;
-		}
-
-		return csum_partial(src, len, sum);
-	}
-
-	if (len)
-		*err_ptr = -EFAULT;
-
-	return (__force __wsum)-1; /* invalid checksum */
-}
-
 #endif
diff --git a/arch/xtensa/include/asm/checksum.h b/arch/xtensa/include/asm/checksum.h
index 243a5fe79d3c..44ec1d0b2a35 100644
--- a/arch/xtensa/include/asm/checksum.h
+++ b/arch/xtensa/include/asm/checksum.h
@@ -37,32 +37,27 @@ asmlinkage __wsum csum_partial(const void *buff, int len, __wsum sum);
  * better 64-bit) boundary
  */
 
-asmlinkage __wsum csum_partial_copy_generic(const void *src, void *dst,
-					    int len, __wsum sum,
-					    int *src_err_ptr, int *dst_err_ptr);
+asmlinkage __wsum csum_partial_copy_generic(const void *src, void *dst, int len);
 
+#define _HAVE_ARCH_CSUM_AND_COPY
 /*
  *	Note: when you get a NULL pointer exception here this means someone
  *	passed in an incorrect kernel address to one of these functions.
  */
 static inline
-__wsum csum_partial_copy_nocheck(const void *src, void *dst,
-					int len, __wsum sum)
+__wsum csum_partial_copy_nocheck(const void *src, void *dst, int len)
 {
-	return csum_partial_copy_generic(src, dst, len, sum, NULL, NULL);
+	return csum_partial_copy_generic(src, dst, len);
 }
 
 #define _HAVE_ARCH_COPY_AND_CSUM_FROM_USER
 static inline
 __wsum csum_and_copy_from_user(const void __user *src, void *dst,
-				   int len, __wsum sum, int *err_ptr)
+				   int len)
 {
-	if (access_ok(src, len))
-		return csum_partial_copy_generic((__force const void *)src, dst,
-					len, sum, err_ptr, NULL);
-	if (len)
-		*err_ptr = -EFAULT;
-	return sum;
+	if (!access_ok(src, len))
+		return 0;
+	return csum_partial_copy_generic((__force const void *)src, dst, len);
 }
 
 /*
@@ -243,15 +238,10 @@ static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
  */
 #define HAVE_CSUM_COPY_USER
 static __inline__ __wsum csum_and_copy_to_user(const void *src,
-					       void __user *dst, int len,
-					       __wsum sum, int *err_ptr)
+					       void __user *dst, int len)
 {
-	if (access_ok(dst, len))
-		return csum_partial_copy_generic(src,dst,len,sum,NULL,err_ptr);
-
-	if (len)
-		*err_ptr = -EFAULT;
-
-	return (__force __wsum)-1; /* invalid checksum */
+	if (!access_ok(dst, len))
+		return 0;
+	return csum_partial_copy_generic(src, (__force void *)dst, len);
 }
 #endif
diff --git a/arch/xtensa/lib/checksum.S b/arch/xtensa/lib/checksum.S
index 4cb9ca58d9ad..cf1bed1a5bd6 100644
--- a/arch/xtensa/lib/checksum.S
+++ b/arch/xtensa/lib/checksum.S
@@ -175,19 +175,14 @@ ENDPROC(csum_partial)
  */
 
 /*
-unsigned int csum_partial_copy_generic (const char *src, char *dst, int len,
-					int sum, int *src_err_ptr, int *dst_err_ptr)
+unsigned int csum_partial_copy_generic (const char *src, char *dst, int len)
 	a2  = src
 	a3  = dst
 	a4  = len
 	a5  = sum
-	a6  = src_err_ptr
-	a7  = dst_err_ptr
 	a8  = temp
 	a9  = temp
 	a10 = temp
-	a11 = original len for exception handling
-	a12 = original dst for exception handling
 
     This function is optimized for 4-byte aligned addresses.  Other
     alignments work, but not nearly as efficiently.
@@ -196,8 +191,7 @@ unsigned int csum_partial_copy_generic (const char *src, char *dst, int len,
 ENTRY(csum_partial_copy_generic)
 
 	abi_entry_default
-	mov	a12, a3
-	mov	a11, a4
+	movi	a5, -1
 	or	a10, a2, a3
 
 	/* We optimize the following alignment tests for the 4-byte
@@ -228,26 +222,26 @@ ENTRY(csum_partial_copy_generic)
 #endif
 EX(10f)	l32i	a9, a2, 0
 EX(10f)	l32i	a8, a2, 4
-EX(11f)	s32i	a9, a3, 0
-EX(11f)	s32i	a8, a3, 4
+EX(10f)	s32i	a9, a3, 0
+EX(10f)	s32i	a8, a3, 4
 	ONES_ADD(a5, a9)
 	ONES_ADD(a5, a8)
 EX(10f)	l32i	a9, a2, 8
 EX(10f)	l32i	a8, a2, 12
-EX(11f)	s32i	a9, a3, 8
-EX(11f)	s32i	a8, a3, 12
+EX(10f)	s32i	a9, a3, 8
+EX(10f)	s32i	a8, a3, 12
 	ONES_ADD(a5, a9)
 	ONES_ADD(a5, a8)
 EX(10f)	l32i	a9, a2, 16
 EX(10f)	l32i	a8, a2, 20
-EX(11f)	s32i	a9, a3, 16
-EX(11f)	s32i	a8, a3, 20
+EX(10f)	s32i	a9, a3, 16
+EX(10f)	s32i	a8, a3, 20
 	ONES_ADD(a5, a9)
 	ONES_ADD(a5, a8)
 EX(10f)	l32i	a9, a2, 24
 EX(10f)	l32i	a8, a2, 28
-EX(11f)	s32i	a9, a3, 24
-EX(11f)	s32i	a8, a3, 28
+EX(10f)	s32i	a9, a3, 24
+EX(10f)	s32i	a8, a3, 28
 	ONES_ADD(a5, a9)
 	ONES_ADD(a5, a8)
 	addi	a2, a2, 32
@@ -267,7 +261,7 @@ EX(11f)	s32i	a8, a3, 28
 .Loop6:
 #endif
 EX(10f)	l32i	a9, a2, 0
-EX(11f)	s32i	a9, a3, 0
+EX(10f)	s32i	a9, a3, 0
 	ONES_ADD(a5, a9)
 	addi	a2, a2, 4
 	addi	a3, a3, 4
@@ -298,7 +292,7 @@ EX(11f)	s32i	a9, a3, 0
 .Loop7:
 #endif
 EX(10f)	l16ui	a9, a2, 0
-EX(11f)	s16i	a9, a3, 0
+EX(10f)	s16i	a9, a3, 0
 	ONES_ADD(a5, a9)
 	addi	a2, a2, 2
 	addi	a3, a3, 2
@@ -309,7 +303,7 @@ EX(11f)	s16i	a9, a3, 0
 	/* This section processes a possible trailing odd byte. */
 	_bbci.l	a4, 0, 8f	/* 1-byte chunk */
 EX(10f)	l8ui	a9, a2, 0
-EX(11f)	s8i	a9, a3, 0
+EX(10f)	s8i	a9, a3, 0
 #ifdef __XTENSA_EB__
 	slli	a9, a9, 8	/* shift byte to bits 8..15 */
 #endif
@@ -334,8 +328,8 @@ EX(11f)	s8i	a9, a3, 0
 #endif
 EX(10f)	l8ui	a9, a2, 0
 EX(10f)	l8ui	a8, a2, 1
-EX(11f)	s8i	a9, a3, 0
-EX(11f)	s8i	a8, a3, 1
+EX(10f)	s8i	a9, a3, 0
+EX(10f)	s8i	a8, a3, 1
 #ifdef __XTENSA_EB__
 	slli	a9, a9, 8	/* combine into a single 16-bit value */
 #else				/* for checksum computation */
@@ -356,38 +350,7 @@ ENDPROC(csum_partial_copy_generic)
 
 # Exception handler:
 .section .fixup, "ax"
-/*
-	a6  = src_err_ptr
-	a7  = dst_err_ptr
-	a11 = original len for exception handling
-	a12 = original dst for exception handling
-*/
-
 10:
-	_movi	a2, -EFAULT
-	s32i	a2, a6, 0	/* src_err_ptr */
-
-	# clear the complete destination - computing the rest
-	# is too much work
-	movi	a2, 0
-#if XCHAL_HAVE_LOOPS
-	loopgtz	a11, 2f
-#else
-	beqz	a11, 2f
-	add	a11, a11, a12	/* a11 = ending address */
-.Leloop:
-#endif
-	s8i	a2, a12, 0
-	addi	a12, a12, 1
-#if !XCHAL_HAVE_LOOPS
-	blt	a12, a11, .Leloop
-#endif
-2:
-	abi_ret_default
-
-11:
-	movi	a2, -EFAULT
-	s32i	a2, a7, 0	/* dst_err_ptr */
 	movi	a2, 0
 	abi_ret_default