forked from Minki/linux
f718d426d7
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>
21 lines
717 B
C
21 lines
717 B
C
/*
|
|
* Simple interface to link xor_vmx.c and xor_vmx_glue.c
|
|
*
|
|
* Separating these file ensures that no altivec instructions are run
|
|
* outside of the enable/disable altivec block.
|
|
*/
|
|
|
|
void __xor_altivec_2(unsigned long bytes, unsigned long *v1_in,
|
|
unsigned long *v2_in);
|
|
|
|
void __xor_altivec_3(unsigned long bytes, unsigned long *v1_in,
|
|
unsigned long *v2_in, unsigned long *v3_in);
|
|
|
|
void __xor_altivec_4(unsigned long bytes, unsigned long *v1_in,
|
|
unsigned long *v2_in, unsigned long *v3_in,
|
|
unsigned long *v4_in);
|
|
|
|
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);
|