[PATCH v3 0/4] arm64: accelerate crc32_be

[PATCH v3 0/4] arm64: accelerate crc32_be

[Kevin Bracey]

Originally sent only to the arm-linux list - now including linux-crypto.
Ard suggested that Herbert take the series.

This series completes the arm64 crc32 helper acceleration by adding crc32_be.

There are plenty of users, for example OF.

To compensate for the extra supporting cruft in lib/crc32.c, a couple of minor
tidies.

changes since v2:
- no code change, but sent to Herbert+crypto with Catalin's ack for arm64

changes since v1:
- assembler style fixes from Ard's review

Kevin Bracey (4):
  lib/crc32.c: remove unneeded casts
  lib/crc32.c: Make crc32_be weak for arch override
  lib/crc32test.c: correct printed bytes count
  arm64: accelerate crc32_be

 arch/arm64/lib/crc32.S | 87 +++++++++++++++++++++++++++++++++++-------
 lib/crc32.c            | 14 +++----
 lib/crc32test.c        |  2 +-
 3 files changed, 80 insertions(+), 23 deletions(-)

-- 
2.25.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH v3 0/4] arm64: accelerate crc32_be

[Kevin Bracey]

Originally sent only to the arm-linux list - now including linux-crypto.
Ard suggested that Herbert take the series.

This series completes the arm64 crc32 helper acceleration by adding crc32_be.

There are plenty of users, for example OF.

To compensate for the extra supporting cruft in lib/crc32.c, a couple of minor
tidies.

changes since v2:
- no code change, but sent to Herbert+crypto with Catalin's ack for arm64

changes since v1:
- assembler style fixes from Ard's review

Kevin Bracey (4):
  lib/crc32.c: remove unneeded casts
  lib/crc32.c: Make crc32_be weak for arch override
  lib/crc32test.c: correct printed bytes count
  arm64: accelerate crc32_be

 arch/arm64/lib/crc32.S | 87 +++++++++++++++++++++++++++++++++++-------
 lib/crc32.c            | 14 +++----
 lib/crc32test.c        |  2 +-
 3 files changed, 80 insertions(+), 23 deletions(-)

-- 
2.25.1

[PATCH v3 1/4] lib/crc32.c: remove unneeded casts

[Kevin Bracey]

Casts were added in commit 8f243af42ade ("sections: fix const sections
for crc32 table") to cope with the tables not being const. They are no
longer required since commit f5e38b9284e1 ("lib: crc32: constify crc32
lookup table").

Signed-off-by: Kevin Bracey <kevin@bracey.fi>
---
 lib/crc32.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/lib/crc32.c b/lib/crc32.c
index 2a68dfd3b96c..7f062a2639df 100644
--- a/lib/crc32.c
+++ b/lib/crc32.c
@@ -194,13 +194,11 @@ u32 __pure __weak __crc32c_le(u32 crc, unsigned char const *p, size_t len)
 #else
 u32 __pure __weak crc32_le(u32 crc, unsigned char const *p, size_t len)
 {
-	return crc32_le_generic(crc, p, len,
-			(const u32 (*)[256])crc32table_le, CRC32_POLY_LE);
+	return crc32_le_generic(crc, p, len, crc32table_le, CRC32_POLY_LE);
 }
 u32 __pure __weak __crc32c_le(u32 crc, unsigned char const *p, size_t len)
 {
-	return crc32_le_generic(crc, p, len,
-			(const u32 (*)[256])crc32ctable_le, CRC32C_POLY_LE);
+	return crc32_le_generic(crc, p, len, crc32ctable_le, CRC32C_POLY_LE);
 }
 #endif
 EXPORT_SYMBOL(crc32_le);
@@ -339,8 +337,7 @@ u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
 #else
 u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
 {
-	return crc32_be_generic(crc, p, len,
-			(const u32 (*)[256])crc32table_be, CRC32_POLY_BE);
+	return crc32_be_generic(crc, p, len, crc32table_be, CRC32_POLY_BE);
 }
 #endif
 EXPORT_SYMBOL(crc32_be);
-- 
2.25.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH v3 1/4] lib/crc32.c: remove unneeded casts

[Kevin Bracey]

Casts were added in commit 8f243af42ade ("sections: fix const sections
for crc32 table") to cope with the tables not being const. They are no
longer required since commit f5e38b9284e1 ("lib: crc32: constify crc32
lookup table").

Signed-off-by: Kevin Bracey <kevin@bracey.fi>
---
 lib/crc32.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/lib/crc32.c b/lib/crc32.c
index 2a68dfd3b96c..7f062a2639df 100644
--- a/lib/crc32.c
+++ b/lib/crc32.c
@@ -194,13 +194,11 @@ u32 __pure __weak __crc32c_le(u32 crc, unsigned char const *p, size_t len)
 #else
 u32 __pure __weak crc32_le(u32 crc, unsigned char const *p, size_t len)
 {
-	return crc32_le_generic(crc, p, len,
-			(const u32 (*)[256])crc32table_le, CRC32_POLY_LE);
+	return crc32_le_generic(crc, p, len, crc32table_le, CRC32_POLY_LE);
 }
 u32 __pure __weak __crc32c_le(u32 crc, unsigned char const *p, size_t len)
 {
-	return crc32_le_generic(crc, p, len,
-			(const u32 (*)[256])crc32ctable_le, CRC32C_POLY_LE);
+	return crc32_le_generic(crc, p, len, crc32ctable_le, CRC32C_POLY_LE);
 }
 #endif
 EXPORT_SYMBOL(crc32_le);
@@ -339,8 +337,7 @@ u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
 #else
 u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
 {
-	return crc32_be_generic(crc, p, len,
-			(const u32 (*)[256])crc32table_be, CRC32_POLY_BE);
+	return crc32_be_generic(crc, p, len, crc32table_be, CRC32_POLY_BE);
 }
 #endif
 EXPORT_SYMBOL(crc32_be);
-- 
2.25.1

[PATCH v3 2/4] lib/crc32.c: Make crc32_be weak for arch override

[Kevin Bracey]

crc32_le and __crc32c_le can be overridden - extend this to crc32_be.

Signed-off-by: Kevin Bracey <kevin@bracey.fi>
---
 lib/crc32.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/lib/crc32.c b/lib/crc32.c
index 7f062a2639df..5649847d0a8d 100644
--- a/lib/crc32.c
+++ b/lib/crc32.c
@@ -206,6 +206,7 @@ EXPORT_SYMBOL(__crc32c_le);
 
 u32 __pure crc32_le_base(u32, unsigned char const *, size_t) __alias(crc32_le);
 u32 __pure __crc32c_le_base(u32, unsigned char const *, size_t) __alias(__crc32c_le);
+u32 __pure crc32_be_base(u32, unsigned char const *, size_t) __alias(crc32_be);
 
 /*
  * This multiplies the polynomials x and y modulo the given modulus.
@@ -330,12 +331,12 @@ static inline u32 __pure crc32_be_generic(u32 crc, unsigned char const *p,
 }
 
 #if CRC_BE_BITS == 1
-u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
+u32 __pure __weak crc32_be(u32 crc, unsigned char const *p, size_t len)
 {
 	return crc32_be_generic(crc, p, len, NULL, CRC32_POLY_BE);
 }
 #else
-u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
+u32 __pure __weak crc32_be(u32 crc, unsigned char const *p, size_t len)
 {
 	return crc32_be_generic(crc, p, len, crc32table_be, CRC32_POLY_BE);
 }
-- 
2.25.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH v3 2/4] lib/crc32.c: Make crc32_be weak for arch override

[Kevin Bracey]

crc32_le and __crc32c_le can be overridden - extend this to crc32_be.

Signed-off-by: Kevin Bracey <kevin@bracey.fi>
---
 lib/crc32.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/lib/crc32.c b/lib/crc32.c
index 7f062a2639df..5649847d0a8d 100644
--- a/lib/crc32.c
+++ b/lib/crc32.c
@@ -206,6 +206,7 @@ EXPORT_SYMBOL(__crc32c_le);
 
 u32 __pure crc32_le_base(u32, unsigned char const *, size_t) __alias(crc32_le);
 u32 __pure __crc32c_le_base(u32, unsigned char const *, size_t) __alias(__crc32c_le);
+u32 __pure crc32_be_base(u32, unsigned char const *, size_t) __alias(crc32_be);
 
 /*
  * This multiplies the polynomials x and y modulo the given modulus.
@@ -330,12 +331,12 @@ static inline u32 __pure crc32_be_generic(u32 crc, unsigned char const *p,
 }
 
 #if CRC_BE_BITS == 1
-u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
+u32 __pure __weak crc32_be(u32 crc, unsigned char const *p, size_t len)
 {
 	return crc32_be_generic(crc, p, len, NULL, CRC32_POLY_BE);
 }
 #else
-u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
+u32 __pure __weak crc32_be(u32 crc, unsigned char const *p, size_t len)
 {
 	return crc32_be_generic(crc, p, len, crc32table_be, CRC32_POLY_BE);
 }
-- 
2.25.1

[PATCH v3 3/4] lib/crc32test.c: correct printed bytes count

[Kevin Bracey]

crc32c_le self test had a stray multiply by two inherited from
the crc32_le+crc32_be test loop.

Signed-off-by: Kevin Bracey <kevin@bracey.fi>
---
 lib/crc32test.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/crc32test.c b/lib/crc32test.c
index 61ddce2cff77..9b4af79412c4 100644
--- a/lib/crc32test.c
+++ b/lib/crc32test.c
@@ -675,7 +675,7 @@ static int __init crc32c_test(void)
 
 	/* pre-warm the cache */
 	for (i = 0; i < 100; i++) {
-		bytes += 2*test[i].length;
+		bytes += test[i].length;
 
 		crc ^= __crc32c_le(test[i].crc, test_buf +
 		    test[i].start, test[i].length);
-- 
2.25.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH v3 3/4] lib/crc32test.c: correct printed bytes count

[Kevin Bracey]

crc32c_le self test had a stray multiply by two inherited from
the crc32_le+crc32_be test loop.

Signed-off-by: Kevin Bracey <kevin@bracey.fi>
---
 lib/crc32test.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/crc32test.c b/lib/crc32test.c
index 61ddce2cff77..9b4af79412c4 100644
--- a/lib/crc32test.c
+++ b/lib/crc32test.c
@@ -675,7 +675,7 @@ static int __init crc32c_test(void)
 
 	/* pre-warm the cache */
 	for (i = 0; i < 100; i++) {
-		bytes += 2*test[i].length;
+		bytes += test[i].length;
 
 		crc ^= __crc32c_le(test[i].crc, test_buf +
 		    test[i].start, test[i].length);
-- 
2.25.1

[PATCH v3 4/4] arm64: accelerate crc32_be

[Kevin Bracey]

It makes no sense to leave crc32_be using the generic code while we
only accelerate the little-endian ops.

Even though the big-endian form doesn't fit as smoothly into the arm64,
we can speed it up and avoid hitting the D cache.

Tested on Cortex-A53. Without acceleration:

    crc32: CRC_LE_BITS = 64, CRC_BE BITS = 64
    crc32: self tests passed, processed 225944 bytes in 192240 nsec
    crc32c: CRC_LE_BITS = 64
    crc32c: self tests passed, processed 112972 bytes in 21360 nsec

With acceleration:

    crc32: CRC_LE_BITS = 64, CRC_BE BITS = 64
    crc32: self tests passed, processed 225944 bytes in 53480 nsec
    crc32c: CRC_LE_BITS = 64
    crc32c: self tests passed, processed 112972 bytes in 21480 nsec

Signed-off-by: Kevin Bracey <kevin@bracey.fi>
Tested-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/lib/crc32.S | 87 +++++++++++++++++++++++++++++++++++-------
 1 file changed, 73 insertions(+), 14 deletions(-)

diff --git a/arch/arm64/lib/crc32.S b/arch/arm64/lib/crc32.S
index 0f9e10ecda23..8340dccff46f 100644
--- a/arch/arm64/lib/crc32.S
+++ b/arch/arm64/lib/crc32.S
@@ -11,7 +11,44 @@
 
 	.arch		armv8-a+crc
 
-	.macro		__crc32, c
+	.macro		byteorder, reg, be
+	.if		\be
+CPU_LE( rev		\reg, \reg	)
+	.else
+CPU_BE( rev		\reg, \reg	)
+	.endif
+	.endm
+
+	.macro		byteorder16, reg, be
+	.if		\be
+CPU_LE( rev16		\reg, \reg	)
+	.else
+CPU_BE( rev16		\reg, \reg	)
+	.endif
+	.endm
+
+	.macro		bitorder, reg, be
+	.if		\be
+	rbit		\reg, \reg
+	.endif
+	.endm
+
+	.macro		bitorder16, reg, be
+	.if		\be
+	rbit		\reg, \reg
+	lsr		\reg, \reg, #16
+	.endif
+	.endm
+
+	.macro		bitorder8, reg, be
+	.if		\be
+	rbit		\reg, \reg
+	lsr		\reg, \reg, #24
+	.endif
+	.endm
+
+	.macro		__crc32, c, be=0
+	bitorder	w0, \be
 	cmp		x2, #16
 	b.lt		8f			// less than 16 bytes
 
@@ -24,10 +61,14 @@
 	add		x8, x8, x1
 	add		x1, x1, x7
 	ldp		x5, x6, [x8]
-CPU_BE(	rev		x3, x3		)
-CPU_BE(	rev		x4, x4		)
-CPU_BE(	rev		x5, x5		)
-CPU_BE(	rev		x6, x6		)
+	byteorder	x3, \be
+	byteorder	x4, \be
+	byteorder	x5, \be
+	byteorder	x6, \be
+	bitorder	x3, \be
+	bitorder	x4, \be
+	bitorder	x5, \be
+	bitorder	x6, \be
 
 	tst		x7, #8
 	crc32\c\()x	w8, w0, x3
@@ -55,33 +96,43 @@ CPU_BE(	rev		x6, x6		)
 32:	ldp		x3, x4, [x1], #32
 	sub		x2, x2, #32
 	ldp		x5, x6, [x1, #-16]
-CPU_BE(	rev		x3, x3		)
-CPU_BE(	rev		x4, x4		)
-CPU_BE(	rev		x5, x5		)
-CPU_BE(	rev		x6, x6		)
+	byteorder	x3, \be
+	byteorder	x4, \be
+	byteorder	x5, \be
+	byteorder	x6, \be
+	bitorder	x3, \be
+	bitorder	x4, \be
+	bitorder	x5, \be
+	bitorder	x6, \be
 	crc32\c\()x	w0, w0, x3
 	crc32\c\()x	w0, w0, x4
 	crc32\c\()x	w0, w0, x5
 	crc32\c\()x	w0, w0, x6
 	cbnz		x2, 32b
-0:	ret
+0:	bitorder	w0, \be
+	ret
 
 8:	tbz		x2, #3, 4f
 	ldr		x3, [x1], #8
-CPU_BE(	rev		x3, x3		)
+	byteorder	x3, \be
+	bitorder	x3, \be
 	crc32\c\()x	w0, w0, x3
 4:	tbz		x2, #2, 2f
 	ldr		w3, [x1], #4
-CPU_BE(	rev		w3, w3		)
+	byteorder	w3, \be
+	bitorder	w3, \be
 	crc32\c\()w	w0, w0, w3
 2:	tbz		x2, #1, 1f
 	ldrh		w3, [x1], #2
-CPU_BE(	rev16		w3, w3		)
+	byteorder16	w3, \be
+	bitorder16	w3, \be
 	crc32\c\()h	w0, w0, w3
 1:	tbz		x2, #0, 0f
 	ldrb		w3, [x1]
+	bitorder8	w3, \be
 	crc32\c\()b	w0, w0, w3
-0:	ret
+0:	bitorder	w0, \be
+	ret
 	.endm
 
 	.align		5
@@ -99,3 +150,11 @@ alternative_if_not ARM64_HAS_CRC32
 alternative_else_nop_endif
 	__crc32		c
 SYM_FUNC_END(__crc32c_le)
+
+	.align		5
+SYM_FUNC_START(crc32_be)
+alternative_if_not ARM64_HAS_CRC32
+	b		crc32_be_base
+alternative_else_nop_endif
+	__crc32		be=1
+SYM_FUNC_END(crc32_be)
-- 
2.25.1


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH v3 4/4] arm64: accelerate crc32_be

[Kevin Bracey]

It makes no sense to leave crc32_be using the generic code while we
only accelerate the little-endian ops.

Even though the big-endian form doesn't fit as smoothly into the arm64,
we can speed it up and avoid hitting the D cache.

Tested on Cortex-A53. Without acceleration:

    crc32: CRC_LE_BITS = 64, CRC_BE BITS = 64
    crc32: self tests passed, processed 225944 bytes in 192240 nsec
    crc32c: CRC_LE_BITS = 64
    crc32c: self tests passed, processed 112972 bytes in 21360 nsec

With acceleration:

    crc32: CRC_LE_BITS = 64, CRC_BE BITS = 64
    crc32: self tests passed, processed 225944 bytes in 53480 nsec
    crc32c: CRC_LE_BITS = 64
    crc32c: self tests passed, processed 112972 bytes in 21480 nsec

Signed-off-by: Kevin Bracey <kevin@bracey.fi>
Tested-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Ard Biesheuvel <ardb@kernel.org>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm64/lib/crc32.S | 87 +++++++++++++++++++++++++++++++++++-------
 1 file changed, 73 insertions(+), 14 deletions(-)

diff --git a/arch/arm64/lib/crc32.S b/arch/arm64/lib/crc32.S
index 0f9e10ecda23..8340dccff46f 100644
--- a/arch/arm64/lib/crc32.S
+++ b/arch/arm64/lib/crc32.S
@@ -11,7 +11,44 @@
 
 	.arch		armv8-a+crc
 
-	.macro		__crc32, c
+	.macro		byteorder, reg, be
+	.if		\be
+CPU_LE( rev		\reg, \reg	)
+	.else
+CPU_BE( rev		\reg, \reg	)
+	.endif
+	.endm
+
+	.macro		byteorder16, reg, be
+	.if		\be
+CPU_LE( rev16		\reg, \reg	)
+	.else
+CPU_BE( rev16		\reg, \reg	)
+	.endif
+	.endm
+
+	.macro		bitorder, reg, be
+	.if		\be
+	rbit		\reg, \reg
+	.endif
+	.endm
+
+	.macro		bitorder16, reg, be
+	.if		\be
+	rbit		\reg, \reg
+	lsr		\reg, \reg, #16
+	.endif
+	.endm
+
+	.macro		bitorder8, reg, be
+	.if		\be
+	rbit		\reg, \reg
+	lsr		\reg, \reg, #24
+	.endif
+	.endm
+
+	.macro		__crc32, c, be=0
+	bitorder	w0, \be
 	cmp		x2, #16
 	b.lt		8f			// less than 16 bytes
 
@@ -24,10 +61,14 @@
 	add		x8, x8, x1
 	add		x1, x1, x7
 	ldp		x5, x6, [x8]
-CPU_BE(	rev		x3, x3		)
-CPU_BE(	rev		x4, x4		)
-CPU_BE(	rev		x5, x5		)
-CPU_BE(	rev		x6, x6		)
+	byteorder	x3, \be
+	byteorder	x4, \be
+	byteorder	x5, \be
+	byteorder	x6, \be
+	bitorder	x3, \be
+	bitorder	x4, \be
+	bitorder	x5, \be
+	bitorder	x6, \be
 
 	tst		x7, #8
 	crc32\c\()x	w8, w0, x3
@@ -55,33 +96,43 @@ CPU_BE(	rev		x6, x6		)
 32:	ldp		x3, x4, [x1], #32
 	sub		x2, x2, #32
 	ldp		x5, x6, [x1, #-16]
-CPU_BE(	rev		x3, x3		)
-CPU_BE(	rev		x4, x4		)
-CPU_BE(	rev		x5, x5		)
-CPU_BE(	rev		x6, x6		)
+	byteorder	x3, \be
+	byteorder	x4, \be
+	byteorder	x5, \be
+	byteorder	x6, \be
+	bitorder	x3, \be
+	bitorder	x4, \be
+	bitorder	x5, \be
+	bitorder	x6, \be
 	crc32\c\()x	w0, w0, x3
 	crc32\c\()x	w0, w0, x4
 	crc32\c\()x	w0, w0, x5
 	crc32\c\()x	w0, w0, x6
 	cbnz		x2, 32b
-0:	ret
+0:	bitorder	w0, \be
+	ret
 
 8:	tbz		x2, #3, 4f
 	ldr		x3, [x1], #8
-CPU_BE(	rev		x3, x3		)
+	byteorder	x3, \be
+	bitorder	x3, \be
 	crc32\c\()x	w0, w0, x3
 4:	tbz		x2, #2, 2f
 	ldr		w3, [x1], #4
-CPU_BE(	rev		w3, w3		)
+	byteorder	w3, \be
+	bitorder	w3, \be
 	crc32\c\()w	w0, w0, w3
 2:	tbz		x2, #1, 1f
 	ldrh		w3, [x1], #2
-CPU_BE(	rev16		w3, w3		)
+	byteorder16	w3, \be
+	bitorder16	w3, \be
 	crc32\c\()h	w0, w0, w3
 1:	tbz		x2, #0, 0f
 	ldrb		w3, [x1]
+	bitorder8	w3, \be
 	crc32\c\()b	w0, w0, w3
-0:	ret
+0:	bitorder	w0, \be
+	ret
 	.endm
 
 	.align		5
@@ -99,3 +150,11 @@ alternative_if_not ARM64_HAS_CRC32
 alternative_else_nop_endif
 	__crc32		c
 SYM_FUNC_END(__crc32c_le)
+
+	.align		5
+SYM_FUNC_START(crc32_be)
+alternative_if_not ARM64_HAS_CRC32
+	b		crc32_be_base
+alternative_else_nop_endif
+	__crc32		be=1
+SYM_FUNC_END(crc32_be)
-- 
2.25.1

Re: [PATCH v3 0/4] arm64: accelerate crc32_be

[Herbert Xu]

On Tue, Jan 18, 2022 at 12:23:47PM +0200, Kevin Bracey wrote:
> Originally sent only to the arm-linux list - now including linux-crypto.
> Ard suggested that Herbert take the series.
> 
> This series completes the arm64 crc32 helper acceleration by adding crc32_be.
> 
> There are plenty of users, for example OF.
> 
> To compensate for the extra supporting cruft in lib/crc32.c, a couple of minor
> tidies.
> 
> changes since v2:
> - no code change, but sent to Herbert+crypto with Catalin's ack for arm64
> 
> changes since v1:
> - assembler style fixes from Ard's review
> 
> Kevin Bracey (4):
>   lib/crc32.c: remove unneeded casts
>   lib/crc32.c: Make crc32_be weak for arch override
>   lib/crc32test.c: correct printed bytes count
>   arm64: accelerate crc32_be
> 
>  arch/arm64/lib/crc32.S | 87 +++++++++++++++++++++++++++++++++++-------
>  lib/crc32.c            | 14 +++----
>  lib/crc32test.c        |  2 +-
>  3 files changed, 80 insertions(+), 23 deletions(-)

All applied.  Thanks.
-- 
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt

Re: [PATCH v3 0/4] arm64: accelerate crc32_be

[Herbert Xu]

On Tue, Jan 18, 2022 at 12:23:47PM +0200, Kevin Bracey wrote:
> Originally sent only to the arm-linux list - now including linux-crypto.
> Ard suggested that Herbert take the series.
> 
> This series completes the arm64 crc32 helper acceleration by adding crc32_be.
> 
> There are plenty of users, for example OF.
> 
> To compensate for the extra supporting cruft in lib/crc32.c, a couple of minor
> tidies.
> 
> changes since v2:
> - no code change, but sent to Herbert+crypto with Catalin's ack for arm64
> 
> changes since v1:
> - assembler style fixes from Ard's review
> 
> Kevin Bracey (4):
>   lib/crc32.c: remove unneeded casts
>   lib/crc32.c: Make crc32_be weak for arch override
>   lib/crc32test.c: correct printed bytes count
>   arm64: accelerate crc32_be
> 
>  arch/arm64/lib/crc32.S | 87 +++++++++++++++++++++++++++++++++++-------
>  lib/crc32.c            | 14 +++----
>  lib/crc32test.c        |  2 +-
>  3 files changed, 80 insertions(+), 23 deletions(-)

All applied.  Thanks.
-- 
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel