2019-05-27 13:55:05 +07:00
|
|
|
// SPDX-License-Identifier: GPL-2.0-or-later
|
2013-10-14 17:03:58 +07:00
|
|
|
/*
|
|
|
|
*
|
|
|
|
* Copyright (C) IBM Corporation, 2012
|
|
|
|
*
|
|
|
|
* Author: Anton Blanchard <anton@au.ibm.com>
|
|
|
|
*/
|
2016-04-26 20:49:09 +07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Sparse (as at v0.5.0) gets very, very confused by this file.
|
|
|
|
* Make it a bit simpler for it.
|
|
|
|
*/
|
|
|
|
#if !defined(__CHECKER__)
|
2013-10-14 17:03:58 +07:00
|
|
|
#include <altivec.h>
|
2016-04-26 20:49:09 +07:00
|
|
|
#else
|
|
|
|
#define vec_xor(a, b) a ^ b
|
|
|
|
#define vector __attribute__((vector_size(16)))
|
|
|
|
#endif
|
2013-10-14 17:03:58 +07:00
|
|
|
|
powerpc/lib/xor_vmx: Ensure no altivec code executes before enable_kernel_altivec()
The xor_vmx.c file is used for the RAID5 xor operations. In these functions
altivec is enabled to run the operation and then disabled.
The code uses enable_kernel_altivec() around the core of the algorithm, however
the whole file is built with -maltivec, so the compiler is within its rights to
generate altivec code anywhere. This has been seen at least once in the wild:
0:mon> di $xor_altivec_2
c0000000000b97d0 3c4c01d9 addis r2,r12,473
c0000000000b97d4 3842db30 addi r2,r2,-9424
c0000000000b97d8 7c0802a6 mflr r0
c0000000000b97dc f8010010 std r0,16(r1)
c0000000000b97e0 60000000 nop
c0000000000b97e4 7c0802a6 mflr r0
c0000000000b97e8 faa1ffa8 std r21,-88(r1)
...
c0000000000b981c f821ff41 stdu r1,-192(r1)
c0000000000b9820 7f8101ce stvx v28,r1,r0 <-- POP
c0000000000b9824 38000030 li r0,48
c0000000000b9828 7fa101ce stvx v29,r1,r0
...
c0000000000b984c 4bf6a06d bl c0000000000238b8 # enable_kernel_altivec
This patch splits the non-altivec code into xor_vmx_glue.c which calls the
altivec functions in xor_vmx.c. By compiling xor_vmx_glue.c without
-maltivec we can guarantee that altivec instruction will not be executed
outside of the enable/disable block.
Signed-off-by: Matt Brown <matthew.brown.dev@gmail.com>
[mpe: Rework change log and include disassembly]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-05-24 06:45:59 +07:00
|
|
|
#include "xor_vmx.h"
|
2013-10-14 17:03:58 +07:00
|
|
|
|
|
|
|
typedef vector signed char unative_t;
|
|
|
|
|
|
|
|
#define DEFINE(V) \
|
|
|
|
unative_t *V = (unative_t *)V##_in; \
|
|
|
|
unative_t V##_0, V##_1, V##_2, V##_3
|
|
|
|
|
|
|
|
#define LOAD(V) \
|
|
|
|
do { \
|
|
|
|
V##_0 = V[0]; \
|
|
|
|
V##_1 = V[1]; \
|
|
|
|
V##_2 = V[2]; \
|
|
|
|
V##_3 = V[3]; \
|
|
|
|
} while (0)
|
|
|
|
|
|
|
|
#define STORE(V) \
|
|
|
|
do { \
|
|
|
|
V[0] = V##_0; \
|
|
|
|
V[1] = V##_1; \
|
|
|
|
V[2] = V##_2; \
|
|
|
|
V[3] = V##_3; \
|
|
|
|
} while (0)
|
|
|
|
|
|
|
|
#define XOR(V1, V2) \
|
|
|
|
do { \
|
|
|
|
V1##_0 = vec_xor(V1##_0, V2##_0); \
|
|
|
|
V1##_1 = vec_xor(V1##_1, V2##_1); \
|
|
|
|
V1##_2 = vec_xor(V1##_2, V2##_2); \
|
|
|
|
V1##_3 = vec_xor(V1##_3, V2##_3); \
|
|
|
|
} while (0)
|
|
|
|
|
powerpc/lib/xor_vmx: Ensure no altivec code executes before enable_kernel_altivec()
The xor_vmx.c file is used for the RAID5 xor operations. In these functions
altivec is enabled to run the operation and then disabled.
The code uses enable_kernel_altivec() around the core of the algorithm, however
the whole file is built with -maltivec, so the compiler is within its rights to
generate altivec code anywhere. This has been seen at least once in the wild:
0:mon> di $xor_altivec_2
c0000000000b97d0 3c4c01d9 addis r2,r12,473
c0000000000b97d4 3842db30 addi r2,r2,-9424
c0000000000b97d8 7c0802a6 mflr r0
c0000000000b97dc f8010010 std r0,16(r1)
c0000000000b97e0 60000000 nop
c0000000000b97e4 7c0802a6 mflr r0
c0000000000b97e8 faa1ffa8 std r21,-88(r1)
...
c0000000000b981c f821ff41 stdu r1,-192(r1)
c0000000000b9820 7f8101ce stvx v28,r1,r0 <-- POP
c0000000000b9824 38000030 li r0,48
c0000000000b9828 7fa101ce stvx v29,r1,r0
...
c0000000000b984c 4bf6a06d bl c0000000000238b8 # enable_kernel_altivec
This patch splits the non-altivec code into xor_vmx_glue.c which calls the
altivec functions in xor_vmx.c. By compiling xor_vmx_glue.c without
-maltivec we can guarantee that altivec instruction will not be executed
outside of the enable/disable block.
Signed-off-by: Matt Brown <matthew.brown.dev@gmail.com>
[mpe: Rework change log and include disassembly]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-05-24 06:45:59 +07:00
|
|
|
void __xor_altivec_2(unsigned long bytes, unsigned long *v1_in,
|
|
|
|
unsigned long *v2_in)
|
2013-10-14 17:03:58 +07:00
|
|
|
{
|
|
|
|
DEFINE(v1);
|
|
|
|
DEFINE(v2);
|
|
|
|
unsigned long lines = bytes / (sizeof(unative_t)) / 4;
|
|
|
|
|
|
|
|
do {
|
|
|
|
LOAD(v1);
|
|
|
|
LOAD(v2);
|
|
|
|
XOR(v1, v2);
|
|
|
|
STORE(v1);
|
|
|
|
|
|
|
|
v1 += 4;
|
|
|
|
v2 += 4;
|
|
|
|
} while (--lines > 0);
|
|
|
|
}
|
|
|
|
|
powerpc/lib/xor_vmx: Ensure no altivec code executes before enable_kernel_altivec()
The xor_vmx.c file is used for the RAID5 xor operations. In these functions
altivec is enabled to run the operation and then disabled.
The code uses enable_kernel_altivec() around the core of the algorithm, however
the whole file is built with -maltivec, so the compiler is within its rights to
generate altivec code anywhere. This has been seen at least once in the wild:
0:mon> di $xor_altivec_2
c0000000000b97d0 3c4c01d9 addis r2,r12,473
c0000000000b97d4 3842db30 addi r2,r2,-9424
c0000000000b97d8 7c0802a6 mflr r0
c0000000000b97dc f8010010 std r0,16(r1)
c0000000000b97e0 60000000 nop
c0000000000b97e4 7c0802a6 mflr r0
c0000000000b97e8 faa1ffa8 std r21,-88(r1)
...
c0000000000b981c f821ff41 stdu r1,-192(r1)
c0000000000b9820 7f8101ce stvx v28,r1,r0 <-- POP
c0000000000b9824 38000030 li r0,48
c0000000000b9828 7fa101ce stvx v29,r1,r0
...
c0000000000b984c 4bf6a06d bl c0000000000238b8 # enable_kernel_altivec
This patch splits the non-altivec code into xor_vmx_glue.c which calls the
altivec functions in xor_vmx.c. By compiling xor_vmx_glue.c without
-maltivec we can guarantee that altivec instruction will not be executed
outside of the enable/disable block.
Signed-off-by: Matt Brown <matthew.brown.dev@gmail.com>
[mpe: Rework change log and include disassembly]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-05-24 06:45:59 +07:00
|
|
|
void __xor_altivec_3(unsigned long bytes, unsigned long *v1_in,
|
|
|
|
unsigned long *v2_in, unsigned long *v3_in)
|
2013-10-14 17:03:58 +07:00
|
|
|
{
|
|
|
|
DEFINE(v1);
|
|
|
|
DEFINE(v2);
|
|
|
|
DEFINE(v3);
|
|
|
|
unsigned long lines = bytes / (sizeof(unative_t)) / 4;
|
|
|
|
|
|
|
|
do {
|
|
|
|
LOAD(v1);
|
|
|
|
LOAD(v2);
|
|
|
|
LOAD(v3);
|
|
|
|
XOR(v1, v2);
|
|
|
|
XOR(v1, v3);
|
|
|
|
STORE(v1);
|
|
|
|
|
|
|
|
v1 += 4;
|
|
|
|
v2 += 4;
|
|
|
|
v3 += 4;
|
|
|
|
} while (--lines > 0);
|
|
|
|
}
|
|
|
|
|
powerpc/lib/xor_vmx: Ensure no altivec code executes before enable_kernel_altivec()
The xor_vmx.c file is used for the RAID5 xor operations. In these functions
altivec is enabled to run the operation and then disabled.
The code uses enable_kernel_altivec() around the core of the algorithm, however
the whole file is built with -maltivec, so the compiler is within its rights to
generate altivec code anywhere. This has been seen at least once in the wild:
0:mon> di $xor_altivec_2
c0000000000b97d0 3c4c01d9 addis r2,r12,473
c0000000000b97d4 3842db30 addi r2,r2,-9424
c0000000000b97d8 7c0802a6 mflr r0
c0000000000b97dc f8010010 std r0,16(r1)
c0000000000b97e0 60000000 nop
c0000000000b97e4 7c0802a6 mflr r0
c0000000000b97e8 faa1ffa8 std r21,-88(r1)
...
c0000000000b981c f821ff41 stdu r1,-192(r1)
c0000000000b9820 7f8101ce stvx v28,r1,r0 <-- POP
c0000000000b9824 38000030 li r0,48
c0000000000b9828 7fa101ce stvx v29,r1,r0
...
c0000000000b984c 4bf6a06d bl c0000000000238b8 # enable_kernel_altivec
This patch splits the non-altivec code into xor_vmx_glue.c which calls the
altivec functions in xor_vmx.c. By compiling xor_vmx_glue.c without
-maltivec we can guarantee that altivec instruction will not be executed
outside of the enable/disable block.
Signed-off-by: Matt Brown <matthew.brown.dev@gmail.com>
[mpe: Rework change log and include disassembly]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-05-24 06:45:59 +07:00
|
|
|
void __xor_altivec_4(unsigned long bytes, unsigned long *v1_in,
|
|
|
|
unsigned long *v2_in, unsigned long *v3_in,
|
|
|
|
unsigned long *v4_in)
|
2013-10-14 17:03:58 +07:00
|
|
|
{
|
|
|
|
DEFINE(v1);
|
|
|
|
DEFINE(v2);
|
|
|
|
DEFINE(v3);
|
|
|
|
DEFINE(v4);
|
|
|
|
unsigned long lines = bytes / (sizeof(unative_t)) / 4;
|
|
|
|
|
|
|
|
do {
|
|
|
|
LOAD(v1);
|
|
|
|
LOAD(v2);
|
|
|
|
LOAD(v3);
|
|
|
|
LOAD(v4);
|
|
|
|
XOR(v1, v2);
|
|
|
|
XOR(v3, v4);
|
|
|
|
XOR(v1, v3);
|
|
|
|
STORE(v1);
|
|
|
|
|
|
|
|
v1 += 4;
|
|
|
|
v2 += 4;
|
|
|
|
v3 += 4;
|
|
|
|
v4 += 4;
|
|
|
|
} while (--lines > 0);
|
|
|
|
}
|
|
|
|
|
powerpc/lib/xor_vmx: Ensure no altivec code executes before enable_kernel_altivec()
The xor_vmx.c file is used for the RAID5 xor operations. In these functions
altivec is enabled to run the operation and then disabled.
The code uses enable_kernel_altivec() around the core of the algorithm, however
the whole file is built with -maltivec, so the compiler is within its rights to
generate altivec code anywhere. This has been seen at least once in the wild:
0:mon> di $xor_altivec_2
c0000000000b97d0 3c4c01d9 addis r2,r12,473
c0000000000b97d4 3842db30 addi r2,r2,-9424
c0000000000b97d8 7c0802a6 mflr r0
c0000000000b97dc f8010010 std r0,16(r1)
c0000000000b97e0 60000000 nop
c0000000000b97e4 7c0802a6 mflr r0
c0000000000b97e8 faa1ffa8 std r21,-88(r1)
...
c0000000000b981c f821ff41 stdu r1,-192(r1)
c0000000000b9820 7f8101ce stvx v28,r1,r0 <-- POP
c0000000000b9824 38000030 li r0,48
c0000000000b9828 7fa101ce stvx v29,r1,r0
...
c0000000000b984c 4bf6a06d bl c0000000000238b8 # enable_kernel_altivec
This patch splits the non-altivec code into xor_vmx_glue.c which calls the
altivec functions in xor_vmx.c. By compiling xor_vmx_glue.c without
-maltivec we can guarantee that altivec instruction will not be executed
outside of the enable/disable block.
Signed-off-by: Matt Brown <matthew.brown.dev@gmail.com>
[mpe: Rework change log and include disassembly]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-05-24 06:45:59 +07:00
|
|
|
void __xor_altivec_5(unsigned long bytes, unsigned long *v1_in,
|
|
|
|
unsigned long *v2_in, unsigned long *v3_in,
|
|
|
|
unsigned long *v4_in, unsigned long *v5_in)
|
2013-10-14 17:03:58 +07:00
|
|
|
{
|
|
|
|
DEFINE(v1);
|
|
|
|
DEFINE(v2);
|
|
|
|
DEFINE(v3);
|
|
|
|
DEFINE(v4);
|
|
|
|
DEFINE(v5);
|
|
|
|
unsigned long lines = bytes / (sizeof(unative_t)) / 4;
|
|
|
|
|
|
|
|
do {
|
|
|
|
LOAD(v1);
|
|
|
|
LOAD(v2);
|
|
|
|
LOAD(v3);
|
|
|
|
LOAD(v4);
|
|
|
|
LOAD(v5);
|
|
|
|
XOR(v1, v2);
|
|
|
|
XOR(v3, v4);
|
|
|
|
XOR(v1, v5);
|
|
|
|
XOR(v1, v3);
|
|
|
|
STORE(v1);
|
|
|
|
|
|
|
|
v1 += 4;
|
|
|
|
v2 += 4;
|
|
|
|
v3 += 4;
|
|
|
|
v4 += 4;
|
|
|
|
v5 += 4;
|
|
|
|
} while (--lines > 0);
|
|
|
|
}
|