s390/crc32-vx: use vector instructions to optimize CRC-32 computation
Use vector instructions to optimize the computation of CRC-32 checksums. An optimized version is provided for CRC-32 (IEEE 802.3 Ethernet) in normal and bitreflected domain, as well as, for bitreflected CRC-32C (Castagnoli). Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com> Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
This commit is contained in:
Hendrik Brueckner
Martin Schwidefsky
parent
0486480802
commit
19c93787f5
|
|
@ -0,0 +1,207 @@
|
|||
/*
|
||||
* Hardware-accelerated CRC-32 variants for Linux on z Systems
|
||||
*
|
||||
* Use the z/Architecture Vector Extension Facility to accelerate the
|
||||
* computing of CRC-32 checksums.
|
||||
*
|
||||
* This CRC-32 implementation algorithm processes the most-significant
|
||||
* bit first (BE).
|
||||
*
|
||||
* Copyright IBM Corp. 2015
|
||||
* Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
|
||||
*/
|
||||
|
||||
#include <linux/linkage.h>
|
||||
#include <asm/vx-insn.h>
|
||||
|
||||
/* Vector register range containing CRC-32 constants */
|
||||
#define CONST_R1R2 %v9
|
||||
#define CONST_R3R4 %v10
|
||||
#define CONST_R5 %v11
|
||||
#define CONST_R6 %v12
|
||||
#define CONST_RU_POLY %v13
|
||||
#define CONST_CRC_POLY %v14
|
||||
|
||||
.data
|
||||
.align 8
|
||||
|
||||
/*
|
||||
* The CRC-32 constant block contains reduction constants to fold and
|
||||
* process particular chunks of the input data stream in parallel.
|
||||
*
|
||||
* For the CRC-32 variants, the constants are precomputed according to
|
||||
* these defintions:
|
||||
*
|
||||
* R1 = x4*128+64 mod P(x)
|
||||
* R2 = x4*128 mod P(x)
|
||||
* R3 = x128+64 mod P(x)
|
||||
* R4 = x128 mod P(x)
|
||||
* R5 = x96 mod P(x)
|
||||
* R6 = x64 mod P(x)
|
||||
*
|
||||
* Barret reduction constant, u, is defined as floor(x**64 / P(x)).
|
||||
*
|
||||
* where P(x) is the polynomial in the normal domain and the P'(x) is the
|
||||
* polynomial in the reversed (bitreflected) domain.
|
||||
*
|
||||
* Note that the constant definitions below are extended in order to compute
|
||||
* intermediate results with a single VECTOR GALOIS FIELD MULTIPLY instruction.
|
||||
* The righmost doubleword can be 0 to prevent contribution to the result or
|
||||
* can be multiplied by 1 to perform an XOR without the need for a separate
|
||||
* VECTOR EXCLUSIVE OR instruction.
|
||||
*
|
||||
* CRC-32 (IEEE 802.3 Ethernet, ...) polynomials:
|
||||
*
|
||||
* P(x) = 0x04C11DB7
|
||||
* P'(x) = 0xEDB88320
|
||||
*/
|
||||
|
||||
.Lconstants_CRC_32_BE:
|
||||
.quad 0x08833794c, 0x0e6228b11 # R1, R2
|
||||
.quad 0x0c5b9cd4c, 0x0e8a45605 # R3, R4
|
||||
.quad 0x0f200aa66, 1 << 32 # R5, x32
|
||||
.quad 0x0490d678d, 1 # R6, 1
|
||||
.quad 0x104d101df, 0 # u
|
||||
.quad 0x104C11DB7, 0 # P(x)
|
||||
|
||||
.previous
|
||||
|
||||
.text
|
||||
/*
|
||||
* The CRC-32 function(s) use these calling conventions:
|
||||
*
|
||||
* Parameters:
|
||||
*
|
||||
* %r2: Initial CRC value, typically ~0; and final CRC (return) value.
|
||||
* %r3: Input buffer pointer, performance might be improved if the
|
||||
* buffer is on a doubleword boundary.
|
||||
* %r4: Length of the buffer, must be 64 bytes or greater.
|
||||
*
|
||||
* Register usage:
|
||||
*
|
||||
* %r5: CRC-32 constant pool base pointer.
|
||||
* V0: Initial CRC value and intermediate constants and results.
|
||||
* V1..V4: Data for CRC computation.
|
||||
* V5..V8: Next data chunks that are fetched from the input buffer.
|
||||
*
|
||||
* V9..V14: CRC-32 constants.
|
||||
*/
|
||||
ENTRY(crc32_be_vgfm_16)
|
||||
/* Load CRC-32 constants */
|
||||
larl %r5,.Lconstants_CRC_32_BE
|
||||
VLM CONST_R1R2,CONST_CRC_POLY,0,%r5
|
||||
|
||||
/* Load the initial CRC value into the leftmost word of V0. */
|
||||
VZERO %v0
|
||||
VLVGF %v0,%r2,0
|
||||
|
||||
/* Load a 64-byte data chunk and XOR with CRC */
|
||||
VLM %v1,%v4,0,%r3 /* 64-bytes into V1..V4 */
|
||||
VX %v1,%v0,%v1 /* V1 ^= CRC */
|
||||
aghi %r3,64 /* BUF = BUF + 64 */
|
||||
aghi %r4,-64 /* LEN = LEN - 64 */
|
||||
|
||||
/* Check remaining buffer size and jump to proper folding method */
|
||||
cghi %r4,64
|
||||
jl .Lless_than_64bytes
|
||||
|
||||
.Lfold_64bytes_loop:
|
||||
/* Load the next 64-byte data chunk into V5 to V8 */
|
||||
VLM %v5,%v8,0,%r3
|
||||
|
||||
/*
|
||||
* Perform a GF(2) multiplication of the doublewords in V1 with
|
||||
* the reduction constants in V0. The intermediate result is
|
||||
* then folded (accumulated) with the next data chunk in V5 and
|
||||
* stored in V1. Repeat this step for the register contents
|
||||
* in V2, V3, and V4 respectively.
|
||||
*/
|
||||
VGFMAG %v1,CONST_R1R2,%v1,%v5
|
||||
VGFMAG %v2,CONST_R1R2,%v2,%v6
|
||||
VGFMAG %v3,CONST_R1R2,%v3,%v7
|
||||
VGFMAG %v4,CONST_R1R2,%v4,%v8
|
||||
|
||||
/* Adjust buffer pointer and length for next loop */
|
||||
aghi %r3,64 /* BUF = BUF + 64 */
|
||||
aghi %r4,-64 /* LEN = LEN - 64 */
|
||||
|
||||
cghi %r4,64
|
||||
jnl .Lfold_64bytes_loop
|
||||
|
||||
.Lless_than_64bytes:
|
||||
/* Fold V1 to V4 into a single 128-bit value in V1 */
|
||||
VGFMAG %v1,CONST_R3R4,%v1,%v2
|
||||
VGFMAG %v1,CONST_R3R4,%v1,%v3
|
||||
VGFMAG %v1,CONST_R3R4,%v1,%v4
|
||||
|
||||
/* Check whether to continue with 64-bit folding */
|
||||
cghi %r4,16
|
||||
jl .Lfinal_fold
|
||||
|
||||
.Lfold_16bytes_loop:
|
||||
|
||||
VL %v2,0,,%r3 /* Load next data chunk */
|
||||
VGFMAG %v1,CONST_R3R4,%v1,%v2 /* Fold next data chunk */
|
||||
|
||||
/* Adjust buffer pointer and size for folding next data chunk */
|
||||
aghi %r3,16
|
||||
aghi %r4,-16
|
||||
|
||||
/* Process remaining data chunks */
|
||||
cghi %r4,16
|
||||
jnl .Lfold_16bytes_loop
|
||||
|
||||
.Lfinal_fold:
|
||||
/*
|
||||
* The R5 constant is used to fold a 128-bit value into an 96-bit value
|
||||
* that is XORed with the next 96-bit input data chunk. To use a single
|
||||
* VGFMG instruction, multiply the rightmost 64-bit with x^32 (1<<32) to
|
||||
* form an intermediate 96-bit value (with appended zeros) which is then
|
||||
* XORed with the intermediate reduction result.
|
||||
*/
|
||||
VGFMG %v1,CONST_R5,%v1
|
||||
|
||||
/*
|
||||
* Further reduce the remaining 96-bit value to a 64-bit value using a
|
||||
* single VGFMG, the rightmost doubleword is multiplied with 0x1. The
|
||||
* intermediate result is then XORed with the product of the leftmost
|
||||
* doubleword with R6. The result is a 64-bit value and is subject to
|
||||
* the Barret reduction.
|
||||
*/
|
||||
VGFMG %v1,CONST_R6,%v1
|
||||
|
||||
/*
|
||||
* The input values to the Barret reduction are the degree-63 polynomial
|
||||
* in V1 (R(x)), degree-32 generator polynomial, and the reduction
|
||||
* constant u. The Barret reduction result is the CRC value of R(x) mod
|
||||
* P(x).
|
||||
*
|
||||
* The Barret reduction algorithm is defined as:
|
||||
*
|
||||
* 1. T1(x) = floor( R(x) / x^32 ) GF2MUL u
|
||||
* 2. T2(x) = floor( T1(x) / x^32 ) GF2MUL P(x)
|
||||
* 3. C(x) = R(x) XOR T2(x) mod x^32
|
||||
*
|
||||
* Note: To compensate the division by x^32, use the vector unpack
|
||||
* instruction to move the leftmost word into the leftmost doubleword
|
||||
* of the vector register. The rightmost doubleword is multiplied
|
||||
* with zero to not contribute to the intermedate results.
|
||||
*/
|
||||
|
||||
/* T1(x) = floor( R(x) / x^32 ) GF2MUL u */
|
||||
VUPLLF %v2,%v1
|
||||
VGFMG %v2,CONST_RU_POLY,%v2
|
||||
|
||||
/*
|
||||
* Compute the GF(2) product of the CRC polynomial in VO with T1(x) in
|
||||
* V2 and XOR the intermediate result, T2(x), with the value in V1.
|
||||
* The final result is in the rightmost word of V2.
|
||||
*/
|
||||
VUPLLF %v2,%v2
|
||||
VGFMAG %v2,CONST_CRC_POLY,%v2,%v1
|
||||
|
||||
.Ldone:
|
||||
VLGVF %r2,%v2,3
|
||||
br %r14
|
||||
|
||||
.previous
|
||||
|
|
@ -0,0 +1,268 @@
|
|||
/*
|
||||
* Hardware-accelerated CRC-32 variants for Linux on z Systems
|
||||
*
|
||||
* Use the z/Architecture Vector Extension Facility to accelerate the
|
||||
* computing of bitreflected CRC-32 checksums for IEEE 802.3 Ethernet
|
||||
* and Castagnoli.
|
||||
*
|
||||
* This CRC-32 implementation algorithm is bitreflected and processes
|
||||
* the least-significant bit first (Little-Endian).
|
||||
*
|
||||
* Copyright IBM Corp. 2015
|
||||
* Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
|
||||
*/
|
||||
|
||||
#include <linux/linkage.h>
|
||||
#include <asm/vx-insn.h>
|
||||
|
||||
/* Vector register range containing CRC-32 constants */
|
||||
#define CONST_PERM_LE2BE %v9
|
||||
#define CONST_R2R1 %v10
|
||||
#define CONST_R4R3 %v11
|
||||
#define CONST_R5 %v12
|
||||
#define CONST_RU_POLY %v13
|
||||
#define CONST_CRC_POLY %v14
|
||||
|
||||
.data
|
||||
.align 8
|
||||
|
||||
/*
|
||||
* The CRC-32 constant block contains reduction constants to fold and
|
||||
* process particular chunks of the input data stream in parallel.
|
||||
*
|
||||
* For the CRC-32 variants, the constants are precomputed according to
|
||||
* these definitions:
|
||||
*
|
||||
* R1 = [(x4*128+32 mod P'(x) << 32)]' << 1
|
||||
* R2 = [(x4*128-32 mod P'(x) << 32)]' << 1
|
||||
* R3 = [(x128+32 mod P'(x) << 32)]' << 1
|
||||
* R4 = [(x128-32 mod P'(x) << 32)]' << 1
|
||||
* R5 = [(x64 mod P'(x) << 32)]' << 1
|
||||
* R6 = [(x32 mod P'(x) << 32)]' << 1
|
||||
*
|
||||
* The bitreflected Barret reduction constant, u', is defined as
|
||||
* the bit reversal of floor(x**64 / P(x)).
|
||||
*
|
||||
* where P(x) is the polynomial in the normal domain and the P'(x) is the
|
||||
* polynomial in the reversed (bitreflected) domain.
|
||||
*
|
||||
* CRC-32 (IEEE 802.3 Ethernet, ...) polynomials:
|
||||
*
|
||||
* P(x) = 0x04C11DB7
|
||||
* P'(x) = 0xEDB88320
|
||||
*
|
||||
* CRC-32C (Castagnoli) polynomials:
|
||||
*
|
||||
* P(x) = 0x1EDC6F41
|
||||
* P'(x) = 0x82F63B78
|
||||
*/
|
||||
|
||||
.Lconstants_CRC_32_LE:
|
||||
.octa 0x0F0E0D0C0B0A09080706050403020100 # BE->LE mask
|
||||
.quad 0x1c6e41596, 0x154442bd4 # R2, R1
|
||||
.quad 0x0ccaa009e, 0x1751997d0 # R4, R3
|
||||
.octa 0x163cd6124 # R5
|
||||
.octa 0x1F7011641 # u'
|
||||
.octa 0x1DB710641 # P'(x) << 1
|
||||
|
||||
.Lconstants_CRC_32C_LE:
|
||||
.octa 0x0F0E0D0C0B0A09080706050403020100 # BE->LE mask
|
||||
.quad 0x09e4addf8, 0x740eef02 # R2, R1
|
||||
.quad 0x14cd00bd6, 0xf20c0dfe # R4, R3
|
||||
.octa 0x0dd45aab8 # R5
|
||||
.octa 0x0dea713f1 # u'
|
||||
.octa 0x105ec76f0 # P'(x) << 1
|
||||
|
||||
.previous
|
||||
|
||||
|
||||
.text
|
||||
|
||||
/*
|
||||
* The CRC-32 functions use these calling conventions:
|
||||
*
|
||||
* Parameters:
|
||||
*
|
||||
* %r2: Initial CRC value, typically ~0; and final CRC (return) value.
|
||||
* %r3: Input buffer pointer, performance might be improved if the
|
||||
* buffer is on a doubleword boundary.
|
||||
* %r4: Length of the buffer, must be 64 bytes or greater.
|
||||
*
|
||||
* Register usage:
|
||||
*
|
||||
* %r5: CRC-32 constant pool base pointer.
|
||||
* V0: Initial CRC value and intermediate constants and results.
|
||||
* V1..V4: Data for CRC computation.
|
||||
* V5..V8: Next data chunks that are fetched from the input buffer.
|
||||
* V9: Constant for BE->LE conversion and shift operations
|
||||
*
|
||||
* V10..V14: CRC-32 constants.
|
||||
*/
|
||||
|
||||
ENTRY(crc32_le_vgfm_16)
|
||||
larl %r5,.Lconstants_CRC_32_LE
|
||||
j crc32_le_vgfm_generic
|
||||
|
||||
ENTRY(crc32c_le_vgfm_16)
|
||||
larl %r5,.Lconstants_CRC_32C_LE
|
||||
j crc32_le_vgfm_generic
|
||||
|
||||
|
||||
crc32_le_vgfm_generic:
|
||||
/* Load CRC-32 constants */
|
||||
VLM CONST_PERM_LE2BE,CONST_CRC_POLY,0,%r5
|
||||
|
||||
/*
|
||||
* Load the initial CRC value.
|
||||
*
|
||||
* The CRC value is loaded into the rightmost word of the
|
||||
* vector register and is later XORed with the LSB portion
|
||||
* of the loaded input data.
|
||||
*/
|
||||
VZERO %v0 /* Clear V0 */
|
||||
VLVGF %v0,%r2,3 /* Load CRC into rightmost word */
|
||||
|
||||
/* Load a 64-byte data chunk and XOR with CRC */
|
||||
VLM %v1,%v4,0,%r3 /* 64-bytes into V1..V4 */
|
||||
VPERM %v1,%v1,%v1,CONST_PERM_LE2BE
|
||||
VPERM %v2,%v2,%v2,CONST_PERM_LE2BE
|
||||
VPERM %v3,%v3,%v3,CONST_PERM_LE2BE
|
||||
VPERM %v4,%v4,%v4,CONST_PERM_LE2BE
|
||||
|
||||
VX %v1,%v0,%v1 /* V1 ^= CRC */
|
||||
aghi %r3,64 /* BUF = BUF + 64 */
|
||||
aghi %r4,-64 /* LEN = LEN - 64 */
|
||||
|
||||
cghi %r4,64
|
||||
jl .Lless_than_64bytes
|
||||
|
||||
.Lfold_64bytes_loop:
|
||||
/* Load the next 64-byte data chunk into V5 to V8 */
|
||||
VLM %v5,%v8,0,%r3
|
||||
VPERM %v5,%v5,%v5,CONST_PERM_LE2BE
|
||||
VPERM %v6,%v6,%v6,CONST_PERM_LE2BE
|
||||
VPERM %v7,%v7,%v7,CONST_PERM_LE2BE
|
||||
VPERM %v8,%v8,%v8,CONST_PERM_LE2BE
|
||||
|
||||
/*
|
||||
* Perform a GF(2) multiplication of the doublewords in V1 with
|
||||
* the R1 and R2 reduction constants in V0. The intermediate result
|
||||
* is then folded (accumulated) with the next data chunk in V5 and
|
||||
* stored in V1. Repeat this step for the register contents
|
||||
* in V2, V3, and V4 respectively.
|
||||
*/
|
||||
VGFMAG %v1,CONST_R2R1,%v1,%v5
|
||||
VGFMAG %v2,CONST_R2R1,%v2,%v6
|
||||
VGFMAG %v3,CONST_R2R1,%v3,%v7
|
||||
VGFMAG %v4,CONST_R2R1,%v4,%v8
|
||||
|
||||
aghi %r3,64 /* BUF = BUF + 64 */
|
||||
aghi %r4,-64 /* LEN = LEN - 64 */
|
||||
|
||||
cghi %r4,64
|
||||
jnl .Lfold_64bytes_loop
|
||||
|
||||
.Lless_than_64bytes:
|
||||
/*
|
||||
* Fold V1 to V4 into a single 128-bit value in V1. Multiply V1 with R3
|
||||
* and R4 and accumulating the next 128-bit chunk until a single 128-bit
|
||||
* value remains.
|
||||
*/
|
||||
VGFMAG %v1,CONST_R4R3,%v1,%v2
|
||||
VGFMAG %v1,CONST_R4R3,%v1,%v3
|
||||
VGFMAG %v1,CONST_R4R3,%v1,%v4
|
||||
|
||||
cghi %r4,16
|
||||
jl .Lfinal_fold
|
||||
|
||||
.Lfold_16bytes_loop:
|
||||
|
||||
VL %v2,0,,%r3 /* Load next data chunk */
|
||||
VPERM %v2,%v2,%v2,CONST_PERM_LE2BE
|
||||
VGFMAG %v1,CONST_R4R3,%v1,%v2 /* Fold next data chunk */
|
||||
|
||||
aghi %r3,16
|
||||
aghi %r4,-16
|
||||
|
||||
cghi %r4,16
|
||||
jnl .Lfold_16bytes_loop
|
||||
|
||||
.Lfinal_fold:
|
||||
/*
|
||||
* Set up a vector register for byte shifts. The shift value must
|
||||
* be loaded in bits 1-4 in byte element 7 of a vector register.
|
||||
* Shift by 8 bytes: 0x40
|
||||
* Shift by 4 bytes: 0x20
|
||||
*/
|
||||
VLEIB %v9,0x40,7
|
||||
|
||||
/*
|
||||
* Prepare V0 for the next GF(2) multiplication: shift V0 by 8 bytes
|
||||
* to move R4 into the rightmost doubleword and set the leftmost
|
||||
* doubleword to 0x1.
|
||||
*/
|
||||
VSRLB %v0,CONST_R4R3,%v9
|
||||
VLEIG %v0,1,0
|
||||
|
||||
/*
|
||||
* Compute GF(2) product of V1 and V0. The rightmost doubleword
|
||||
* of V1 is multiplied with R4. The leftmost doubleword of V1 is
|
||||
* multiplied by 0x1 and is then XORed with rightmost product.
|
||||
* Implicitly, the intermediate leftmost product becomes padded
|
||||
*/
|
||||
VGFMG %v1,%v0,%v1
|
||||
|
||||
/*
|
||||
* Now do the final 32-bit fold by multiplying the rightmost word
|
||||
* in V1 with R5 and XOR the result with the remaining bits in V1.
|
||||
*
|
||||
* To achieve this by a single VGFMAG, right shift V1 by a word
|
||||
* and store the result in V2 which is then accumulated. Use the
|
||||
* vector unpack instruction to load the rightmost half of the
|
||||
* doubleword into the rightmost doubleword element of V1; the other
|
||||
* half is loaded in the leftmost doubleword.
|
||||
* The vector register with CONST_R5 contains the R5 constant in the
|
||||
* rightmost doubleword and the leftmost doubleword is zero to ignore
|
||||
* the leftmost product of V1.
|
||||
*/
|
||||
VLEIB %v9,0x20,7 /* Shift by words */
|
||||
VSRLB %v2,%v1,%v9 /* Store remaining bits in V2 */
|
||||
VUPLLF %v1,%v1 /* Split rightmost doubleword */
|
||||
VGFMAG %v1,CONST_R5,%v1,%v2 /* V1 = (V1 * R5) XOR V2 */
|
||||
|
||||
/*
|
||||
* Apply a Barret reduction to compute the final 32-bit CRC value.
|
||||
*
|
||||
* The input values to the Barret reduction are the degree-63 polynomial
|
||||
* in V1 (R(x)), degree-32 generator polynomial, and the reduction
|
||||
* constant u. The Barret reduction result is the CRC value of R(x) mod
|
||||
* P(x).
|
||||
*
|
||||
* The Barret reduction algorithm is defined as:
|
||||
*
|
||||
* 1. T1(x) = floor( R(x) / x^32 ) GF2MUL u
|
||||
* 2. T2(x) = floor( T1(x) / x^32 ) GF2MUL P(x)
|
||||
* 3. C(x) = R(x) XOR T2(x) mod x^32
|
||||
*
|
||||
* Note: The leftmost doubleword of vector register containing
|
||||
* CONST_RU_POLY is zero and, thus, the intermediate GF(2) product
|
||||
* is zero and does not contribute to the final result.
|
||||
*/
|
||||
|
||||
/* T1(x) = floor( R(x) / x^32 ) GF2MUL u */
|
||||
VUPLLF %v2,%v1
|
||||
VGFMG %v2,CONST_RU_POLY,%v2
|
||||
|
||||
/*
|
||||
* Compute the GF(2) product of the CRC polynomial with T1(x) in
|
||||
* V2 and XOR the intermediate result, T2(x), with the value in V1.
|
||||
* The final result is stored in word element 2 of V2.
|
||||
*/
|
||||
VUPLLF %v2,%v2
|
||||
VGFMAG %v2,CONST_CRC_POLY,%v2,%v1
|
||||
|
||||
.Ldone:
|
||||
VLGVF %r2,%v2,2
|
||||
br %r14
|
||||
|
||||
.previous
|
||||
Loading…
Reference in New Issue