summaryrefslogtreecommitdiff
path: root/arch/powerpc/lib
diff options
context:
space:
mode:
Diffstat (limited to 'arch/powerpc/lib')
-rw-r--r--arch/powerpc/lib/Makefile28
-rw-r--r--arch/powerpc/lib/alloc.c6
-rw-r--r--arch/powerpc/lib/copy_32.S127
-rw-r--r--arch/powerpc/lib/copypage_power7.S32
-rw-r--r--arch/powerpc/lib/copyuser_64.S3
-rw-r--r--arch/powerpc/lib/copyuser_power7.S228
-rw-r--r--arch/powerpc/lib/crtsavres.S96
-rw-r--r--arch/powerpc/lib/devres.c43
-rw-r--r--arch/powerpc/lib/feature-fixups.c2
-rw-r--r--arch/powerpc/lib/ldstfp.S32
-rw-r--r--arch/powerpc/lib/locks.c5
-rw-r--r--arch/powerpc/lib/memcmp_64.S233
-rw-r--r--arch/powerpc/lib/memcpy_power7.S228
-rw-r--r--arch/powerpc/lib/ppc_ksyms.c35
-rw-r--r--arch/powerpc/lib/rheap.c2
-rw-r--r--arch/powerpc/lib/sstep.c998
-rw-r--r--arch/powerpc/lib/string.S2
17 files changed, 1238 insertions, 862 deletions
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index 59fa2de9546d..7902802a19a5 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -9,34 +9,30 @@ ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC)
CFLAGS_REMOVE_code-patching.o = -pg
CFLAGS_REMOVE_feature-fixups.o = -pg
-obj-y := string.o alloc.o \
- crtsavres.o
+obj-y += string.o alloc.o crtsavres.o ppc_ksyms.o code-patching.o \
+ feature-fixups.o
+
obj-$(CONFIG_PPC32) += div64.o copy_32.o
-obj-$(CONFIG_HAS_IOMEM) += devres.o
-obj-$(CONFIG_PPC64) += copypage_64.o copyuser_64.o \
- usercopy_64.o mem_64.o string.o \
- hweight_64.o \
- copyuser_power7.o string_64.o copypage_power7.o
+obj64-y += copypage_64.o copyuser_64.o usercopy_64.o mem_64.o hweight_64.o \
+ copyuser_power7.o string_64.o copypage_power7.o memcpy_power7.o \
+ memcpy_64.o memcmp_64.o
+
+obj64-$(CONFIG_SMP) += locks.o
+obj64-$(CONFIG_ALTIVEC) += vmx-helper.o
+
ifeq ($(CONFIG_GENERIC_CSUM),)
obj-y += checksum_$(CONFIG_WORD_SIZE).o
obj-$(CONFIG_PPC64) += checksum_wrappers_64.o
endif
-obj-$(CONFIG_PPC64) += memcpy_power7.o memcpy_64.o
-
obj-$(CONFIG_PPC_EMULATE_SSTEP) += sstep.o ldstfp.o
-ifeq ($(CONFIG_PPC64),y)
-obj-$(CONFIG_SMP) += locks.o
-obj-$(CONFIG_ALTIVEC) += vmx-helper.o
-endif
-
obj-$(CONFIG_PPC_LIB_RHEAP) += rheap.o
-obj-y += code-patching.o
-obj-y += feature-fixups.o
obj-$(CONFIG_FTR_FIXUP_SELFTEST) += feature-fixups-test.o
obj-$(CONFIG_ALTIVEC) += xor_vmx.o
CFLAGS_xor_vmx.o += -maltivec -mabi=altivec
+
+obj-$(CONFIG_PPC64) += $(obj64-y)
diff --git a/arch/powerpc/lib/alloc.c b/arch/powerpc/lib/alloc.c
index da22c84a8fed..60b0b3fc8fc1 100644
--- a/arch/powerpc/lib/alloc.c
+++ b/arch/powerpc/lib/alloc.c
@@ -10,12 +10,10 @@ void * __init_refok zalloc_maybe_bootmem(size_t size, gfp_t mask)
{
void *p;
- if (mem_init_done)
+ if (slab_is_available())
p = kzalloc(size, mask);
else {
- p = alloc_bootmem(size);
- if (p)
- memset(p, 0, size);
+ p = memblock_virt_alloc(size, 0);
}
return p;
}
diff --git a/arch/powerpc/lib/copy_32.S b/arch/powerpc/lib/copy_32.S
index 55f19f9fd708..6813f80d1eec 100644
--- a/arch/powerpc/lib/copy_32.S
+++ b/arch/powerpc/lib/copy_32.S
@@ -69,54 +69,6 @@ CACHELINE_BYTES = L1_CACHE_BYTES
LG_CACHELINE_BYTES = L1_CACHE_SHIFT
CACHELINE_MASK = (L1_CACHE_BYTES-1)
-/*
- * Use dcbz on the complete cache lines in the destination
- * to set them to zero. This requires that the destination
- * area is cacheable. -- paulus
- */
-_GLOBAL(cacheable_memzero)
- mr r5,r4
- li r4,0
- addi r6,r3,-4
- cmplwi 0,r5,4
- blt 7f
- stwu r4,4(r6)
- beqlr
- andi. r0,r6,3
- add r5,r0,r5
- subf r6,r0,r6
- clrlwi r7,r6,32-LG_CACHELINE_BYTES
- add r8,r7,r5
- srwi r9,r8,LG_CACHELINE_BYTES
- addic. r9,r9,-1 /* total number of complete cachelines */
- ble 2f
- xori r0,r7,CACHELINE_MASK & ~3
- srwi. r0,r0,2
- beq 3f
- mtctr r0
-4: stwu r4,4(r6)
- bdnz 4b
-3: mtctr r9
- li r7,4
-10: dcbz r7,r6
- addi r6,r6,CACHELINE_BYTES
- bdnz 10b
- clrlwi r5,r8,32-LG_CACHELINE_BYTES
- addi r5,r5,4
-2: srwi r0,r5,2
- mtctr r0
- bdz 6f
-1: stwu r4,4(r6)
- bdnz 1b
-6: andi. r5,r5,3
-7: cmpwi 0,r5,0
- beqlr
- mtctr r5
- addi r6,r6,3
-8: stbu r4,1(r6)
- bdnz 8b
- blr
-
_GLOBAL(memset)
rlwimi r4,r4,8,16,23
rlwimi r4,r4,16,0,15
@@ -142,85 +94,6 @@ _GLOBAL(memset)
bdnz 8b
blr
-/*
- * This version uses dcbz on the complete cache lines in the
- * destination area to reduce memory traffic. This requires that
- * the destination area is cacheable.
- * We only use this version if the source and dest don't overlap.
- * -- paulus.
- */
-_GLOBAL(cacheable_memcpy)
- add r7,r3,r5 /* test if the src & dst overlap */
- add r8,r4,r5
- cmplw 0,r4,r7
- cmplw 1,r3,r8
- crand 0,0,4 /* cr0.lt &= cr1.lt */
- blt memcpy /* if regions overlap */
-
- addi r4,r4,-4
- addi r6,r3,-4
- neg r0,r3
- andi. r0,r0,CACHELINE_MASK /* # bytes to start of cache line */
- beq 58f
-
- cmplw 0,r5,r0 /* is this more than total to do? */
- blt 63f /* if not much to do */
- andi. r8,r0,3 /* get it word-aligned first */
- subf r5,r0,r5
- mtctr r8
- beq+ 61f
-70: lbz r9,4(r4) /* do some bytes */
- stb r9,4(r6)
- addi r4,r4,1
- addi r6,r6,1
- bdnz 70b
-61: srwi. r0,r0,2
- mtctr r0
- beq 58f
-72: lwzu r9,4(r4) /* do some words */
- stwu r9,4(r6)
- bdnz 72b
-
-58: srwi. r0,r5,LG_CACHELINE_BYTES /* # complete cachelines */
- clrlwi r5,r5,32-LG_CACHELINE_BYTES
- li r11,4
- mtctr r0
- beq 63f
-53:
- dcbz r11,r6
- COPY_16_BYTES
-#if L1_CACHE_BYTES >= 32
- COPY_16_BYTES
-#if L1_CACHE_BYTES >= 64
- COPY_16_BYTES
- COPY_16_BYTES
-#if L1_CACHE_BYTES >= 128
- COPY_16_BYTES
- COPY_16_BYTES
- COPY_16_BYTES
- COPY_16_BYTES
-#endif
-#endif
-#endif
- bdnz 53b
-
-63: srwi. r0,r5,2
- mtctr r0
- beq 64f
-30: lwzu r0,4(r4)
- stwu r0,4(r6)
- bdnz 30b
-
-64: andi. r0,r5,3
- mtctr r0
- beq+ 65f
-40: lbz r0,4(r4)
- stb r0,4(r6)
- addi r4,r4,1
- addi r6,r6,1
- bdnz 40b
-65: blr
-
_GLOBAL(memmove)
cmplw 0,r3,r4
bgt backwards_memcpy
diff --git a/arch/powerpc/lib/copypage_power7.S b/arch/powerpc/lib/copypage_power7.S
index d7dafb3777ac..a84d333ecb09 100644
--- a/arch/powerpc/lib/copypage_power7.S
+++ b/arch/powerpc/lib/copypage_power7.S
@@ -83,23 +83,23 @@ _GLOBAL(copypage_power7)
li r12,112
.align 5
-1: lvx vr7,r0,r4
- lvx vr6,r4,r6
- lvx vr5,r4,r7
- lvx vr4,r4,r8
- lvx vr3,r4,r9
- lvx vr2,r4,r10
- lvx vr1,r4,r11
- lvx vr0,r4,r12
+1: lvx v7,r0,r4
+ lvx v6,r4,r6
+ lvx v5,r4,r7
+ lvx v4,r4,r8
+ lvx v3,r4,r9
+ lvx v2,r4,r10
+ lvx v1,r4,r11
+ lvx v0,r4,r12
addi r4,r4,128
- stvx vr7,r0,r3
- stvx vr6,r3,r6
- stvx vr5,r3,r7
- stvx vr4,r3,r8
- stvx vr3,r3,r9
- stvx vr2,r3,r10
- stvx vr1,r3,r11
- stvx vr0,r3,r12
+ stvx v7,r0,r3
+ stvx v6,r3,r6
+ stvx v5,r3,r7
+ stvx v4,r3,r8
+ stvx v3,r3,r9
+ stvx v2,r3,r10
+ stvx v1,r3,r11
+ stvx v0,r3,r12
addi r3,r3,128
bdnz 1b
diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S
index 0860ee46013c..f09899e35991 100644
--- a/arch/powerpc/lib/copyuser_64.S
+++ b/arch/powerpc/lib/copyuser_64.S
@@ -461,8 +461,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_UNALIGNED_LD_STD)
/*
* Routine to copy a whole page of data, optimized for POWER4.
* On POWER4 it is more than 50% faster than the simple loop
- * above (following the .Ldst_aligned label) but it runs slightly
- * slower on POWER3.
+ * above (following the .Ldst_aligned label).
*/
.Lcopy_page_4K:
std r31,-32(1)
diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S
index c46c876ac96a..da0c568d18c4 100644
--- a/arch/powerpc/lib/copyuser_power7.S
+++ b/arch/powerpc/lib/copyuser_power7.S
@@ -388,29 +388,29 @@ err3; std r0,0(r3)
li r11,48
bf cr7*4+3,5f
-err3; lvx vr1,r0,r4
+err3; lvx v1,r0,r4
addi r4,r4,16
-err3; stvx vr1,r0,r3
+err3; stvx v1,r0,r3
addi r3,r3,16
5: bf cr7*4+2,6f
-err3; lvx vr1,r0,r4
-err3; lvx vr0,r4,r9
+err3; lvx v1,r0,r4
+err3; lvx v0,r4,r9
addi r4,r4,32
-err3; stvx vr1,r0,r3
-err3; stvx vr0,r3,r9
+err3; stvx v1,r0,r3
+err3; stvx v0,r3,r9
addi r3,r3,32
6: bf cr7*4+1,7f
-err3; lvx vr3,r0,r4
-err3; lvx vr2,r4,r9
-err3; lvx vr1,r4,r10
-err3; lvx vr0,r4,r11
+err3; lvx v3,r0,r4
+err3; lvx v2,r4,r9
+err3; lvx v1,r4,r10
+err3; lvx v0,r4,r11
addi r4,r4,64
-err3; stvx vr3,r0,r3
-err3; stvx vr2,r3,r9
-err3; stvx vr1,r3,r10
-err3; stvx vr0,r3,r11
+err3; stvx v3,r0,r3
+err3; stvx v2,r3,r9
+err3; stvx v1,r3,r10
+err3; stvx v0,r3,r11
addi r3,r3,64
7: sub r5,r5,r6
@@ -433,23 +433,23 @@ err3; stvx vr0,r3,r11
*/
.align 5
8:
-err4; lvx vr7,r0,r4
-err4; lvx vr6,r4,r9
-err4; lvx vr5,r4,r10
-err4; lvx vr4,r4,r11
-err4; lvx vr3,r4,r12
-err4; lvx vr2,r4,r14
-err4; lvx vr1,r4,r15
-err4; lvx vr0,r4,r16
+err4; lvx v7,r0,r4
+err4; lvx v6,r4,r9
+err4; lvx v5,r4,r10
+err4; lvx v4,r4,r11
+err4; lvx v3,r4,r12
+err4; lvx v2,r4,r14
+err4; lvx v1,r4,r15
+err4; lvx v0,r4,r16
addi r4,r4,128
-err4; stvx vr7,r0,r3
-err4; stvx vr6,r3,r9
-err4; stvx vr5,r3,r10
-err4; stvx vr4,r3,r11
-err4; stvx vr3,r3,r12
-err4; stvx vr2,r3,r14
-err4; stvx vr1,r3,r15
-err4; stvx vr0,r3,r16
+err4; stvx v7,r0,r3
+err4; stvx v6,r3,r9
+err4; stvx v5,r3,r10
+err4; stvx v4,r3,r11
+err4; stvx v3,r3,r12
+err4; stvx v2,r3,r14
+err4; stvx v1,r3,r15
+err4; stvx v0,r3,r16
addi r3,r3,128
bdnz 8b
@@ -463,29 +463,29 @@ err4; stvx vr0,r3,r16
mtocrf 0x01,r6
bf cr7*4+1,9f
-err3; lvx vr3,r0,r4
-err3; lvx vr2,r4,r9
-err3; lvx vr1,r4,r10
-err3; lvx vr0,r4,r11
+err3; lvx v3,r0,r4
+err3; lvx v2,r4,r9
+err3; lvx v1,r4,r10
+err3; lvx v0,r4,r11
addi r4,r4,64
-err3; stvx vr3,r0,r3
-err3; stvx vr2,r3,r9
-err3; stvx vr1,r3,r10
-err3; stvx vr0,r3,r11
+err3; stvx v3,r0,r3
+err3; stvx v2,r3,r9
+err3; stvx v1,r3,r10
+err3; stvx v0,r3,r11
addi r3,r3,64
9: bf cr7*4+2,10f
-err3; lvx vr1,r0,r4
-err3; lvx vr0,r4,r9
+err3; lvx v1,r0,r4
+err3; lvx v0,r4,r9
addi r4,r4,32
-err3; stvx vr1,r0,r3
-err3; stvx vr0,r3,r9
+err3; stvx v1,r0,r3
+err3; stvx v0,r3,r9
addi r3,r3,32
10: bf cr7*4+3,11f
-err3; lvx vr1,r0,r4
+err3; lvx v1,r0,r4
addi r4,r4,16
-err3; stvx vr1,r0,r3
+err3; stvx v1,r0,r3
addi r3,r3,16
/* Up to 15B to go */
@@ -560,42 +560,42 @@ err3; stw r7,4(r3)
li r10,32
li r11,48
- LVS(vr16,0,r4) /* Setup permute control vector */
-err3; lvx vr0,0,r4
+ LVS(v16,0,r4) /* Setup permute control vector */
+err3; lvx v0,0,r4
addi r4,r4,16
bf cr7*4+3,5f
-err3; lvx vr1,r0,r4
- VPERM(vr8,vr0,vr1,vr16)
+err3; lvx v1,r0,r4
+ VPERM(v8,v0,v1,v16)
addi r4,r4,16
-err3; stvx vr8,r0,r3
+err3; stvx v8,r0,r3
addi r3,r3,16
- vor vr0,vr1,vr1
+ vor v0,v1,v1
5: bf cr7*4+2,6f
-err3; lvx vr1,r0,r4
- VPERM(vr8,vr0,vr1,vr16)
-err3; lvx vr0,r4,r9
- VPERM(vr9,vr1,vr0,vr16)
+err3; lvx v1,r0,r4
+ VPERM(v8,v0,v1,v16)
+err3; lvx v0,r4,r9
+ VPERM(v9,v1,v0,v16)
addi r4,r4,32
-err3; stvx vr8,r0,r3
-err3; stvx vr9,r3,r9
+err3; stvx v8,r0,r3
+err3; stvx v9,r3,r9
addi r3,r3,32
6: bf cr7*4+1,7f
-err3; lvx vr3,r0,r4
- VPERM(vr8,vr0,vr3,vr16)
-err3; lvx vr2,r4,r9
- VPERM(vr9,vr3,vr2,vr16)
-err3; lvx vr1,r4,r10
- VPERM(vr10,vr2,vr1,vr16)
-err3; lvx vr0,r4,r11
- VPERM(vr11,vr1,vr0,vr16)
+err3; lvx v3,r0,r4
+ VPERM(v8,v0,v3,v16)
+err3; lvx v2,r4,r9
+ VPERM(v9,v3,v2,v16)
+err3; lvx v1,r4,r10
+ VPERM(v10,v2,v1,v16)
+err3; lvx v0,r4,r11
+ VPERM(v11,v1,v0,v16)
addi r4,r4,64
-err3; stvx vr8,r0,r3
-err3; stvx vr9,r3,r9
-err3; stvx vr10,r3,r10
-err3; stvx vr11,r3,r11
+err3; stvx v8,r0,r3
+err3; stvx v9,r3,r9
+err3; stvx v10,r3,r10
+err3; stvx v11,r3,r11
addi r3,r3,64
7: sub r5,r5,r6
@@ -618,31 +618,31 @@ err3; stvx vr11,r3,r11
*/
.align 5
8:
-err4; lvx vr7,r0,r4
- VPERM(vr8,vr0,vr7,vr16)
-err4; lvx vr6,r4,r9
- VPERM(vr9,vr7,vr6,vr16)
-err4; lvx vr5,r4,r10
- VPERM(vr10,vr6,vr5,vr16)
-err4; lvx vr4,r4,r11
- VPERM(vr11,vr5,vr4,vr16)
-err4; lvx vr3,r4,r12
- VPERM(vr12,vr4,vr3,vr16)
-err4; lvx vr2,r4,r14
- VPERM(vr13,vr3,vr2,vr16)
-err4; lvx vr1,r4,r15
- VPERM(vr14,vr2,vr1,vr16)
-err4; lvx vr0,r4,r16
- VPERM(vr15,vr1,vr0,vr16)
+err4; lvx v7,r0,r4
+ VPERM(v8,v0,v7,v16)
+err4; lvx v6,r4,r9
+ VPERM(v9,v7,v6,v16)
+err4; lvx v5,r4,r10
+ VPERM(v10,v6,v5,v16)
+err4; lvx v4,r4,r11
+ VPERM(v11,v5,v4,v16)
+err4; lvx v3,r4,r12
+ VPERM(v12,v4,v3,v16)
+err4; lvx v2,r4,r14
+ VPERM(v13,v3,v2,v16)
+err4; lvx v1,r4,r15
+ VPERM(v14,v2,v1,v16)
+err4; lvx v0,r4,r16
+ VPERM(v15,v1,v0,v16)
addi r4,r4,128
-err4; stvx vr8,r0,r3
-err4; stvx vr9,r3,r9
-err4; stvx vr10,r3,r10
-err4; stvx vr11,r3,r11
-err4; stvx vr12,r3,r12
-err4; stvx vr13,r3,r14
-err4; stvx vr14,r3,r15
-err4; stvx vr15,r3,r16
+err4; stvx v8,r0,r3
+err4; stvx v9,r3,r9
+err4; stvx v10,r3,r10
+err4; stvx v11,r3,r11
+err4; stvx v12,r3,r12
+err4; stvx v13,r3,r14
+err4; stvx v14,r3,r15
+err4; stvx v15,r3,r16
addi r3,r3,128
bdnz 8b
@@ -656,36 +656,36 @@ err4; stvx vr15,r3,r16
mtocrf 0x01,r6
bf cr7*4+1,9f
-err3; lvx vr3,r0,r4
- VPERM(vr8,vr0,vr3,vr16)
-err3; lvx vr2,r4,r9
- VPERM(vr9,vr3,vr2,vr16)
-err3; lvx vr1,r4,r10
- VPERM(vr10,vr2,vr1,vr16)
-err3; lvx vr0,r4,r11
- VPERM(vr11,vr1,vr0,vr16)
+err3; lvx v3,r0,r4
+ VPERM(v8,v0,v3,v16)
+err3; lvx v2,r4,r9
+ VPERM(v9,v3,v2,v16)
+err3; lvx v1,r4,r10
+ VPERM(v10,v2,v1,v16)
+err3; lvx v0,r4,r11
+ VPERM(v11,v1,v0,v16)
addi r4,r4,64
-err3; stvx vr8,r0,r3
-err3; stvx vr9,r3,r9
-err3; stvx vr10,r3,r10
-err3; stvx vr11,r3,r11
+err3; stvx v8,r0,r3
+err3; stvx v9,r3,r9
+err3; stvx v10,r3,r10
+err3; stvx v11,r3,r11
addi r3,r3,64
9: bf cr7*4+2,10f
-err3; lvx vr1,r0,r4
- VPERM(vr8,vr0,vr1,vr16)
-err3; lvx vr0,r4,r9
- VPERM(vr9,vr1,vr0,vr16)
+err3; lvx v1,r0,r4
+ VPERM(v8,v0,v1,v16)
+err3; lvx v0,r4,r9
+ VPERM(v9,v1,v0,v16)
addi r4,r4,32
-err3; stvx vr8,r0,r3
-err3; stvx vr9,r3,r9
+err3; stvx v8,r0,r3
+err3; stvx v9,r3,r9
addi r3,r3,32
10: bf cr7*4+3,11f
-err3; lvx vr1,r0,r4
- VPERM(vr8,vr0,vr1,vr16)
+err3; lvx v1,r0,r4
+ VPERM(v8,v0,v1,v16)
addi r4,r4,16
-err3; stvx vr8,r0,r3
+err3; stvx v8,r0,r3
addi r3,r3,16
/* Up to 15B to go */
@@ -718,4 +718,4 @@ err3; stb r0,0(r3)
15: addi r1,r1,STACKFRAMESIZE
b exit_vmx_usercopy /* tail call optimise */
-#endif /* CONFiG_ALTIVEC */
+#endif /* CONFIG_ALTIVEC */
diff --git a/arch/powerpc/lib/crtsavres.S b/arch/powerpc/lib/crtsavres.S
index a5b30c71a8d3..18af0b3d3eb2 100644
--- a/arch/powerpc/lib/crtsavres.S
+++ b/arch/powerpc/lib/crtsavres.S
@@ -236,78 +236,78 @@ _GLOBAL(_rest32gpr_31_x)
_GLOBAL(_savevr_20)
li r11,-192
- stvx vr20,r11,r0
+ stvx v20,r11,r0
_GLOBAL(_savevr_21)
li r11,-176
- stvx vr21,r11,r0
+ stvx v21,r11,r0
_GLOBAL(_savevr_22)
li r11,-160
- stvx vr22,r11,r0
+ stvx v22,r11,r0
_GLOBAL(_savevr_23)
li r11,-144
- stvx vr23,r11,r0
+ stvx v23,r11,r0
_GLOBAL(_savevr_24)
li r11,-128
- stvx vr24,r11,r0
+ stvx v24,r11,r0
_GLOBAL(_savevr_25)
li r11,-112
- stvx vr25,r11,r0
+ stvx v25,r11,r0
_GLOBAL(_savevr_26)
li r11,-96
- stvx vr26,r11,r0
+ stvx v26,r11,r0
_GLOBAL(_savevr_27)
li r11,-80
- stvx vr27,r11,r0
+ stvx v27,r11,r0
_GLOBAL(_savevr_28)
li r11,-64
- stvx vr28,r11,r0
+ stvx v28,r11,r0
_GLOBAL(_savevr_29)
li r11,-48
- stvx vr29,r11,r0
+ stvx v29,r11,r0
_GLOBAL(_savevr_30)
li r11,-32
- stvx vr30,r11,r0
+ stvx v30,r11,r0
_GLOBAL(_savevr_31)
li r11,-16
- stvx vr31,r11,r0
+ stvx v31,r11,r0
blr
_GLOBAL(_restvr_20)
li r11,-192
- lvx vr20,r11,r0
+ lvx v20,r11,r0
_GLOBAL(_restvr_21)
li r11,-176
- lvx vr21,r11,r0
+ lvx v21,r11,r0
_GLOBAL(_restvr_22)
li r11,-160
- lvx vr22,r11,r0
+ lvx v22,r11,r0
_GLOBAL(_restvr_23)
li r11,-144
- lvx vr23,r11,r0
+ lvx v23,r11,r0
_GLOBAL(_restvr_24)
li r11,-128
- lvx vr24,r11,r0
+ lvx v24,r11,r0
_GLOBAL(_restvr_25)
li r11,-112
- lvx vr25,r11,r0
+ lvx v25,r11,r0
_GLOBAL(_restvr_26)
li r11,-96
- lvx vr26,r11,r0
+ lvx v26,r11,r0
_GLOBAL(_restvr_27)
li r11,-80
- lvx vr27,r11,r0
+ lvx v27,r11,r0
_GLOBAL(_restvr_28)
li r11,-64
- lvx vr28,r11,r0
+ lvx v28,r11,r0
_GLOBAL(_restvr_29)
li r11,-48
- lvx vr29,r11,r0
+ lvx v29,r11,r0
_GLOBAL(_restvr_30)
li r11,-32
- lvx vr30,r11,r0
+ lvx v30,r11,r0
_GLOBAL(_restvr_31)
li r11,-16
- lvx vr31,r11,r0
+ lvx v31,r11,r0
blr
#endif /* CONFIG_ALTIVEC */
@@ -443,101 +443,101 @@ _restgpr0_31:
.globl _savevr_20
_savevr_20:
li r12,-192
- stvx vr20,r12,r0
+ stvx v20,r12,r0
.globl _savevr_21
_savevr_21:
li r12,-176
- stvx vr21,r12,r0
+ stvx v21,r12,r0
.globl _savevr_22
_savevr_22:
li r12,-160
- stvx vr22,r12,r0
+ stvx v22,r12,r0
.globl _savevr_23
_savevr_23:
li r12,-144
- stvx vr23,r12,r0
+ stvx v23,r12,r0
.globl _savevr_24
_savevr_24:
li r12,-128
- stvx vr24,r12,r0
+ stvx v24,r12,r0
.globl _savevr_25
_savevr_25:
li r12,-112
- stvx vr25,r12,r0
+ stvx v25,r12,r0
.globl _savevr_26
_savevr_26:
li r12,-96
- stvx vr26,r12,r0
+ stvx v26,r12,r0
.globl _savevr_27
_savevr_27:
li r12,-80
- stvx vr27,r12,r0
+ stvx v27,r12,r0
.globl _savevr_28
_savevr_28:
li r12,-64
- stvx vr28,r12,r0
+ stvx v28,r12,r0
.globl _savevr_29
_savevr_29:
li r12,-48
- stvx vr29,r12,r0
+ stvx v29,r12,r0
.globl _savevr_30
_savevr_30:
li r12,-32
- stvx vr30,r12,r0
+ stvx v30,r12,r0
.globl _savevr_31
_savevr_31:
li r12,-16
- stvx vr31,r12,r0
+ stvx v31,r12,r0
blr
.globl _restvr_20
_restvr_20:
li r12,-192
- lvx vr20,r12,r0
+ lvx v20,r12,r0
.globl _restvr_21
_restvr_21:
li r12,-176
- lvx vr21,r12,r0
+ lvx v21,r12,r0
.globl _restvr_22
_restvr_22:
li r12,-160
- lvx vr22,r12,r0
+ lvx v22,r12,r0
.globl _restvr_23
_restvr_23:
li r12,-144
- lvx vr23,r12,r0
+ lvx v23,r12,r0
.globl _restvr_24
_restvr_24:
li r12,-128
- lvx vr24,r12,r0
+ lvx v24,r12,r0
.globl _restvr_25
_restvr_25:
li r12,-112
- lvx vr25,r12,r0
+ lvx v25,r12,r0
.globl _restvr_26
_restvr_26:
li r12,-96
- lvx vr26,r12,r0
+ lvx v26,r12,r0
.globl _restvr_27
_restvr_27:
li r12,-80
- lvx vr27,r12,r0
+ lvx v27,r12,r0
.globl _restvr_28
_restvr_28:
li r12,-64
- lvx vr28,r12,r0
+ lvx v28,r12,r0
.globl _restvr_29
_restvr_29:
li r12,-48
- lvx vr29,r12,r0
+ lvx v29,r12,r0
.globl _restvr_30
_restvr_30:
li r12,-32
- lvx vr30,r12,r0
+ lvx v30,r12,r0
.globl _restvr_31
_restvr_31:
li r12,-16
- lvx vr31,r12,r0
+ lvx v31,r12,r0
blr
#endif /* CONFIG_ALTIVEC */
diff --git a/arch/powerpc/lib/devres.c b/arch/powerpc/lib/devres.c
deleted file mode 100644
index 8df55fc3aad6..000000000000
--- a/arch/powerpc/lib/devres.c
+++ /dev/null
@@ -1,43 +0,0 @@
-/*
- * Copyright (C) 2008 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <linux/device.h> /* devres_*(), devm_ioremap_release() */
-#include <linux/gfp.h>
-#include <linux/io.h> /* ioremap_prot() */
-#include <linux/export.h> /* EXPORT_SYMBOL() */
-
-/**
- * devm_ioremap_prot - Managed ioremap_prot()
- * @dev: Generic device to remap IO address for
- * @offset: BUS offset to map
- * @size: Size of map
- * @flags: Page flags
- *
- * Managed ioremap_prot(). Map is automatically unmapped on driver
- * detach.
- */
-void __iomem *devm_ioremap_prot(struct device *dev, resource_size_t offset,
- size_t size, unsigned long flags)
-{
- void __iomem **ptr, *addr;
-
- ptr = devres_alloc(devm_ioremap_release, sizeof(*ptr), GFP_KERNEL);
- if (!ptr)
- return NULL;
-
- addr = ioremap_prot(offset, size, flags);
- if (addr) {
- *ptr = addr;
- devres_add(dev, ptr);
- } else
- devres_free(ptr);
-
- return addr;
-}
-EXPORT_SYMBOL(devm_ioremap_prot);
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index 7a8a7487cee8..7ce3870d7ddd 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -164,7 +164,7 @@ static long calc_offset(struct fixup_entry *entry, unsigned int *p)
return (unsigned long)p - (unsigned long)entry;
}
-void test_basic_patching(void)
+static void test_basic_patching(void)
{
extern unsigned int ftr_fixup_test1;
extern unsigned int end_ftr_fixup_test1;
diff --git a/arch/powerpc/lib/ldstfp.S b/arch/powerpc/lib/ldstfp.S
index 85aec08ab234..5d0cdbfbe3f2 100644
--- a/arch/powerpc/lib/ldstfp.S
+++ b/arch/powerpc/lib/ldstfp.S
@@ -184,16 +184,16 @@ _GLOBAL(do_stfd)
extab 2b,3b
#ifdef CONFIG_ALTIVEC
-/* Get the contents of vrN into vr0; N is in r3. */
+/* Get the contents of vrN into v0; N is in r3. */
_GLOBAL(get_vr)
mflr r0
rlwinm r3,r3,3,0xf8
bcl 20,31,1f
- blr /* vr0 is already in vr0 */
+ blr /* v0 is already in v0 */
nop
reg = 1
.rept 31
- vor vr0,reg,reg /* assembler doesn't know vmr? */
+ vor v0,reg,reg /* assembler doesn't know vmr? */
blr
reg = reg + 1
.endr
@@ -203,16 +203,16 @@ reg = reg + 1
mtlr r0
bctr
-/* Put the contents of vr0 into vrN; N is in r3. */
+/* Put the contents of v0 into vrN; N is in r3. */
_GLOBAL(put_vr)
mflr r0
rlwinm r3,r3,3,0xf8
bcl 20,31,1f
- blr /* vr0 is already in vr0 */
+ blr /* v0 is already in v0 */
nop
reg = 1
.rept 31
- vor reg,vr0,vr0
+ vor reg,v0,v0
blr
reg = reg + 1
.endr
@@ -234,13 +234,13 @@ _GLOBAL(do_lvx)
MTMSRD(r7)
isync
beq cr7,1f
- stvx vr0,r1,r8
+ stvx v0,r1,r8
1: li r9,-EFAULT
-2: lvx vr0,0,r4
+2: lvx v0,0,r4
li r9,0
3: beq cr7,4f
bl put_vr
- lvx vr0,r1,r8
+ lvx v0,r1,r8
4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1)
mtlr r0
MTMSRD(r6)
@@ -262,13 +262,13 @@ _GLOBAL(do_stvx)
MTMSRD(r7)
isync
beq cr7,1f
- stvx vr0,r1,r8
+ stvx v0,r1,r8
bl get_vr
1: li r9,-EFAULT
-2: stvx vr0,0,r4
+2: stvx v0,0,r4
li r9,0
3: beq cr7,4f
- lvx vr0,r1,r8
+ lvx v0,r1,r8
4: PPC_LL r0,STKFRM+PPC_LR_STKOFF(r1)
mtlr r0
MTMSRD(r6)
@@ -280,12 +280,12 @@ _GLOBAL(do_stvx)
#endif /* CONFIG_ALTIVEC */
#ifdef CONFIG_VSX
-/* Get the contents of vsrN into vsr0; N is in r3. */
+/* Get the contents of vsN into vs0; N is in r3. */
_GLOBAL(get_vsr)
mflr r0
rlwinm r3,r3,3,0x1f8
bcl 20,31,1f
- blr /* vsr0 is already in vsr0 */
+ blr /* vs0 is already in vs0 */
nop
reg = 1
.rept 63
@@ -299,12 +299,12 @@ reg = reg + 1
mtlr r0
bctr
-/* Put the contents of vsr0 into vsrN; N is in r3. */
+/* Put the contents of vs0 into vsN; N is in r3. */
_GLOBAL(put_vsr)
mflr r0
rlwinm r3,r3,3,0x1f8
bcl 20,31,1f
- blr /* vr0 is already in vr0 */
+ blr /* v0 is already in v0 */
nop
reg = 1
.rept 63
diff --git a/arch/powerpc/lib/locks.c b/arch/powerpc/lib/locks.c
index 0c9c8d7d0734..f7deebdf3365 100644
--- a/arch/powerpc/lib/locks.c
+++ b/arch/powerpc/lib/locks.c
@@ -41,6 +41,7 @@ void __spin_yield(arch_spinlock_t *lock)
plpar_hcall_norets(H_CONFER,
get_hard_smp_processor_id(holder_cpu), yield_count);
}
+EXPORT_SYMBOL_GPL(__spin_yield);
/*
* Waiting for a read lock or a write lock on a rwlock...
@@ -70,12 +71,16 @@ void __rw_yield(arch_rwlock_t *rw)
void arch_spin_unlock_wait(arch_spinlock_t *lock)
{
+ smp_mb();
+
while (lock->slock) {
HMT_low();
if (SHARED_PROCESSOR)
__spin_yield(lock);
}
HMT_medium();
+
+ smp_mb();
}
EXPORT_SYMBOL(arch_spin_unlock_wait);
diff --git a/arch/powerpc/lib/memcmp_64.S b/arch/powerpc/lib/memcmp_64.S
new file mode 100644
index 000000000000..8953d2382a65
--- /dev/null
+++ b/arch/powerpc/lib/memcmp_64.S
@@ -0,0 +1,233 @@
+/*
+ * Author: Anton Blanchard <anton@au.ibm.com>
+ * Copyright 2015 IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <asm/ppc_asm.h>
+
+#define off8 r6
+#define off16 r7
+#define off24 r8
+
+#define rA r9
+#define rB r10
+#define rC r11
+#define rD r27
+#define rE r28
+#define rF r29
+#define rG r30
+#define rH r31
+
+#ifdef __LITTLE_ENDIAN__
+#define LD ldbrx
+#else
+#define LD ldx
+#endif
+
+_GLOBAL(memcmp)
+ cmpdi cr1,r5,0
+
+ /* Use the short loop if both strings are not 8B aligned */
+ or r6,r3,r4
+ andi. r6,r6,7
+
+ /* Use the short loop if length is less than 32B */
+ cmpdi cr6,r5,31
+
+ beq cr1,.Lzero
+ bne .Lshort
+ bgt cr6,.Llong
+
+.Lshort:
+ mtctr r5
+
+1: lbz rA,0(r3)
+ lbz rB,0(r4)
+ subf. rC,rB,rA
+ bne .Lnon_zero
+ bdz .Lzero
+
+ lbz rA,1(r3)
+ lbz rB,1(r4)
+ subf. rC,rB,rA
+ bne .Lnon_zero
+ bdz .Lzero
+
+ lbz rA,2(r3)
+ lbz rB,2(r4)
+ subf. rC,rB,rA
+ bne .Lnon_zero
+ bdz .Lzero
+
+ lbz rA,3(r3)
+ lbz rB,3(r4)
+ subf. rC,rB,rA
+ bne .Lnon_zero
+
+ addi r3,r3,4
+ addi r4,r4,4
+
+ bdnz 1b
+
+.Lzero:
+ li r3,0
+ blr
+
+.Lnon_zero:
+ mr r3,rC
+ blr
+
+.Llong:
+ li off8,8
+ li off16,16
+ li off24,24
+
+ std r31,-8(r1)
+ std r30,-16(r1)
+ std r29,-24(r1)
+ std r28,-32(r1)
+ std r27,-40(r1)
+
+ srdi r0,r5,5
+ mtctr r0
+ andi. r5,r5,31
+
+ LD rA,0,r3
+ LD rB,0,r4
+
+ LD rC,off8,r3
+ LD rD,off8,r4
+
+ LD rE,off16,r3
+ LD rF,off16,r4
+
+ LD rG,off24,r3
+ LD rH,off24,r4
+ cmpld cr0,rA,rB
+
+ addi r3,r3,32
+ addi r4,r4,32
+
+ bdz .Lfirst32
+
+ LD rA,0,r3
+ LD rB,0,r4
+ cmpld cr1,rC,rD
+
+ LD rC,off8,r3
+ LD rD,off8,r4
+ cmpld cr6,rE,rF
+
+ LD rE,off16,r3
+ LD rF,off16,r4
+ cmpld cr7,rG,rH
+ bne cr0,.LcmpAB
+
+ LD rG,off24,r3
+ LD rH,off24,r4
+ cmpld cr0,rA,rB
+ bne cr1,.LcmpCD
+
+ addi r3,r3,32
+ addi r4,r4,32
+
+ bdz .Lsecond32
+
+ .balign 16
+
+1: LD rA,0,r3
+ LD rB,0,r4
+ cmpld cr1,rC,rD
+ bne cr6,.LcmpEF
+
+ LD rC,off8,r3
+ LD rD,off8,r4
+ cmpld cr6,rE,rF
+ bne cr7,.LcmpGH
+
+ LD rE,off16,r3
+ LD rF,off16,r4
+ cmpld cr7,rG,rH
+ bne cr0,.LcmpAB
+
+ LD rG,off24,r3
+ LD rH,off24,r4
+ cmpld cr0,rA,rB
+ bne cr1,.LcmpCD
+
+ addi r3,r3,32
+ addi r4,r4,32
+
+ bdnz 1b
+
+.Lsecond32:
+ cmpld cr1,rC,rD
+ bne cr6,.LcmpEF
+
+ cmpld cr6,rE,rF
+ bne cr7,.LcmpGH
+
+ cmpld cr7,rG,rH
+ bne cr0,.LcmpAB
+
+ bne cr1,.LcmpCD
+ bne cr6,.LcmpEF
+ bne cr7,.LcmpGH
+
+.Ltail:
+ ld r31,-8(r1)
+ ld r30,-16(r1)
+ ld r29,-24(r1)
+ ld r28,-32(r1)
+ ld r27,-40(r1)
+
+ cmpdi r5,0
+ beq .Lzero
+ b .Lshort
+
+.Lfirst32:
+ cmpld cr1,rC,rD
+ cmpld cr6,rE,rF
+ cmpld cr7,rG,rH
+
+ bne cr0,.LcmpAB
+ bne cr1,.LcmpCD
+ bne cr6,.LcmpEF
+ bne cr7,.LcmpGH
+
+ b .Ltail
+
+.LcmpAB:
+ li r3,1
+ bgt cr0,.Lout
+ li r3,-1
+ b .Lout
+
+.LcmpCD:
+ li r3,1
+ bgt cr1,.Lout
+ li r3,-1
+ b .Lout
+
+.LcmpEF:
+ li r3,1
+ bgt cr6,.Lout
+ li r3,-1
+ b .Lout
+
+.LcmpGH:
+ li r3,1
+ bgt cr7,.Lout
+ li r3,-1
+
+.Lout:
+ ld r31,-8(r1)
+ ld r30,-16(r1)
+ ld r29,-24(r1)
+ ld r28,-32(r1)
+ ld r27,-40(r1)
+ blr
diff --git a/arch/powerpc/lib/memcpy_power7.S b/arch/powerpc/lib/memcpy_power7.S
index 2ff5c142f87b..786234fd4e91 100644
--- a/arch/powerpc/lib/memcpy_power7.S
+++ b/arch/powerpc/lib/memcpy_power7.S
@@ -321,29 +321,29 @@ _GLOBAL(memcpy_power7)
li r11,48
bf cr7*4+3,5f
- lvx vr1,r0,r4
+ lvx v1,r0,r4
addi r4,r4,16
- stvx vr1,r0,r3
+ stvx v1,r0,r3
addi r3,r3,16
5: bf cr7*4+2,6f
- lvx vr1,r0,r4
- lvx vr0,r4,r9
+ lvx v1,r0,r4
+ lvx v0,r4,r9
addi r4,r4,32
- stvx vr1,r0,r3
- stvx vr0,r3,r9
+ stvx v1,r0,r3
+ stvx v0,r3,r9
addi r3,r3,32
6: bf cr7*4+1,7f
- lvx vr3,r0,r4
- lvx vr2,r4,r9
- lvx vr1,r4,r10
- lvx vr0,r4,r11
+ lvx v3,r0,r4
+ lvx v2,r4,r9
+ lvx v1,r4,r10
+ lvx v0,r4,r11
addi r4,r4,64
- stvx vr3,r0,r3
- stvx vr2,r3,r9
- stvx vr1,r3,r10
- stvx vr0,r3,r11
+ stvx v3,r0,r3
+ stvx v2,r3,r9
+ stvx v1,r3,r10
+ stvx v0,r3,r11
addi r3,r3,64
7: sub r5,r5,r6
@@ -366,23 +366,23 @@ _GLOBAL(memcpy_power7)
*/
.align 5
8:
- lvx vr7,r0,r4
- lvx vr6,r4,r9
- lvx vr5,r4,r10
- lvx vr4,r4,r11
- lvx vr3,r4,r12
- lvx vr2,r4,r14
- lvx vr1,r4,r15
- lvx vr0,r4,r16
+ lvx v7,r0,r4
+ lvx v6,r4,r9
+ lvx v5,r4,r10
+ lvx v4,r4,r11
+ lvx v3,r4,r12
+ lvx v2,r4,r14
+ lvx v1,r4,r15
+ lvx v0,r4,r16
addi r4,r4,128
- stvx vr7,r0,r3
- stvx vr6,r3,r9
- stvx vr5,r3,r10
- stvx vr4,r3,r11
- stvx vr3,r3,r12
- stvx vr2,r3,r14
- stvx vr1,r3,r15
- stvx vr0,r3,r16
+ stvx v7,r0,r3
+ stvx v6,r3,r9
+ stvx v5,r3,r10
+ stvx v4,r3,r11
+ stvx v3,r3,r12
+ stvx v2,r3,r14
+ stvx v1,r3,r15
+ stvx v0,r3,r16
addi r3,r3,128
bdnz 8b
@@ -396,29 +396,29 @@ _GLOBAL(memcpy_power7)
mtocrf 0x01,r6
bf cr7*4+1,9f
- lvx vr3,r0,r4
- lvx vr2,r4,r9
- lvx vr1,r4,r10
- lvx vr0,r4,r11
+ lvx v3,r0,r4
+ lvx v2,r4,r9
+ lvx v1,r4,r10
+ lvx v0,r4,r11
addi r4,r4,64
- stvx vr3,r0,r3
- stvx vr2,r3,r9
- stvx vr1,r3,r10
- stvx vr0,r3,r11
+ stvx v3,r0,r3
+ stvx v2,r3,r9
+ stvx v1,r3,r10
+ stvx v0,r3,r11
addi r3,r3,64
9: bf cr7*4+2,10f
- lvx vr1,r0,r4
- lvx vr0,r4,r9
+ lvx v1,r0,r4
+ lvx v0,r4,r9
addi r4,r4,32
- stvx vr1,r0,r3
- stvx vr0,r3,r9
+ stvx v1,r0,r3
+ stvx v0,r3,r9
addi r3,r3,32
10: bf cr7*4+3,11f
- lvx vr1,r0,r4
+ lvx v1,r0,r4
addi r4,r4,16
- stvx vr1,r0,r3
+ stvx v1,r0,r3
addi r3,r3,16
/* Up to 15B to go */
@@ -494,42 +494,42 @@ _GLOBAL(memcpy_power7)
li r10,32
li r11,48
- LVS(vr16,0,r4) /* Setup permute control vector */
- lvx vr0,0,r4
+ LVS(v16,0,r4) /* Setup permute control vector */
+ lvx v0,0,r4
addi r4,r4,16
bf cr7*4+3,5f
- lvx vr1,r0,r4
- VPERM(vr8,vr0,vr1,vr16)
+ lvx v1,r0,r4
+ VPERM(v8,v0,v1,v16)
addi r4,r4,16
- stvx vr8,r0,r3
+ stvx v8,r0,r3
addi r3,r3,16
- vor vr0,vr1,vr1
+ vor v0,v1,v1
5: bf cr7*4+2,6f
- lvx vr1,r0,r4
- VPERM(vr8,vr0,vr1,vr16)
- lvx vr0,r4,r9
- VPERM(vr9,vr1,vr0,vr16)
+ lvx v1,r0,r4
+ VPERM(v8,v0,v1,v16)
+ lvx v0,r4,r9
+ VPERM(v9,v1,v0,v16)
addi r4,r4,32
- stvx vr8,r0,r3
- stvx vr9,r3,r9
+ stvx v8,r0,r3
+ stvx v9,r3,r9
addi r3,r3,32
6: bf cr7*4+1,7f
- lvx vr3,r0,r4
- VPERM(vr8,vr0,vr3,vr16)
- lvx vr2,r4,r9
- VPERM(vr9,vr3,vr2,vr16)
- lvx vr1,r4,r10
- VPERM(vr10,vr2,vr1,vr16)
- lvx vr0,r4,r11
- VPERM(vr11,vr1,vr0,vr16)
+ lvx v3,r0,r4
+ VPERM(v8,v0,v3,v16)
+ lvx v2,r4,r9
+ VPERM(v9,v3,v2,v16)
+ lvx v1,r4,r10
+ VPERM(v10,v2,v1,v16)
+ lvx v0,r4,r11
+ VPERM(v11,v1,v0,v16)
addi r4,r4,64
- stvx vr8,r0,r3
- stvx vr9,r3,r9
- stvx vr10,r3,r10
- stvx vr11,r3,r11
+ stvx v8,r0,r3
+ stvx v9,r3,r9
+ stvx v10,r3,r10
+ stvx v11,r3,r11
addi r3,r3,64
7: sub r5,r5,r6
@@ -552,31 +552,31 @@ _GLOBAL(memcpy_power7)
*/
.align 5
8:
- lvx vr7,r0,r4
- VPERM(vr8,vr0,vr7,vr16)
- lvx vr6,r4,r9
- VPERM(vr9,vr7,vr6,vr16)
- lvx vr5,r4,r10
- VPERM(vr10,vr6,vr5,vr16)
- lvx vr4,r4,r11
- VPERM(vr11,vr5,vr4,vr16)
- lvx vr3,r4,r12
- VPERM(vr12,vr4,vr3,vr16)
- lvx vr2,r4,r14
- VPERM(vr13,vr3,vr2,vr16)
- lvx vr1,r4,r15
- VPERM(vr14,vr2,vr1,vr16)
- lvx vr0,r4,r16
- VPERM(vr15,vr1,vr0,vr16)
+ lvx v7,r0,r4
+ VPERM(v8,v0,v7,v16)
+ lvx v6,r4,r9
+ VPERM(v9,v7,v6,v16)
+ lvx v5,r4,r10
+ VPERM(v10,v6,v5,v16)
+ lvx v4,r4,r11
+ VPERM(v11,v5,v4,v16)
+ lvx v3,r4,r12
+ VPERM(v12,v4,v3,v16)
+ lvx v2,r4,r14
+ VPERM(v13,v3,v2,v16)
+ lvx v1,r4,r15
+ VPERM(v14,v2,v1,v16)
+ lvx v0,r4,r16
+ VPERM(v15,v1,v0,v16)
addi r4,r4,128
- stvx vr8,r0,r3
- stvx vr9,r3,r9
- stvx vr10,r3,r10
- stvx vr11,r3,r11
- stvx vr12,r3,r12
- stvx vr13,r3,r14
- stvx vr14,r3,r15
- stvx vr15,r3,r16
+ stvx v8,r0,r3
+ stvx v9,r3,r9
+ stvx v10,r3,r10
+ stvx v11,r3,r11
+ stvx v12,r3,r12
+ stvx v13,r3,r14
+ stvx v14,r3,r15
+ stvx v15,r3,r16
addi r3,r3,128
bdnz 8b
@@ -590,36 +590,36 @@ _GLOBAL(memcpy_power7)
mtocrf 0x01,r6
bf cr7*4+1,9f
- lvx vr3,r0,r4
- VPERM(vr8,vr0,vr3,vr16)
- lvx vr2,r4,r9
- VPERM(vr9,vr3,vr2,vr16)
- lvx vr1,r4,r10
- VPERM(vr10,vr2,vr1,vr16)
- lvx vr0,r4,r11
- VPERM(vr11,vr1,vr0,vr16)
+ lvx v3,r0,r4
+ VPERM(v8,v0,v3,v16)
+ lvx v2,r4,r9
+ VPERM(v9,v3,v2,v16)
+ lvx v1,r4,r10
+ VPERM(v10,v2,v1,v16)
+ lvx v0,r4,r11
+ VPERM(v11,v1,v0,v16)
addi r4,r4,64
- stvx vr8,r0,r3
- stvx vr9,r3,r9
- stvx vr10,r3,r10
- stvx vr11,r3,r11
+ stvx v8,r0,r3
+ stvx v9,r3,r9
+ stvx v10,r3,r10
+ stvx v11,r3,r11
addi r3,r3,64
9: bf cr7*4+2,10f
- lvx vr1,r0,r4
- VPERM(vr8,vr0,vr1,vr16)
- lvx vr0,r4,r9
- VPERM(vr9,vr1,vr0,vr16)
+ lvx v1,r0,r4
+ VPERM(v8,v0,v1,v16)
+ lvx v0,r4,r9
+ VPERM(v9,v1,v0,v16)
addi r4,r4,32
- stvx vr8,r0,r3
- stvx vr9,r3,r9
+ stvx v8,r0,r3
+ stvx v9,r3,r9
addi r3,r3,32
10: bf cr7*4+3,11f
- lvx vr1,r0,r4
- VPERM(vr8,vr0,vr1,vr16)
+ lvx v1,r0,r4
+ VPERM(v8,v0,v1,v16)
addi r4,r4,16
- stvx vr8,r0,r3
+ stvx v8,r0,r3
addi r3,r3,16
/* Up to 15B to go */
@@ -653,4 +653,4 @@ _GLOBAL(memcpy_power7)
15: addi r1,r1,STACKFRAMESIZE
ld r3,-STACKFRAMESIZE+STK_REG(R31)(r1)
b exit_vmx_copy /* tail call optimise */
-#endif /* CONFiG_ALTIVEC */
+#endif /* CONFIG_ALTIVEC */
diff --git a/arch/powerpc/lib/ppc_ksyms.c b/arch/powerpc/lib/ppc_ksyms.c
new file mode 100644
index 000000000000..c7f8e9586316
--- /dev/null
+++ b/arch/powerpc/lib/ppc_ksyms.c
@@ -0,0 +1,35 @@
+#include <linux/string.h>
+#include <linux/uaccess.h>
+#include <linux/bitops.h>
+#include <net/checksum.h>
+
+EXPORT_SYMBOL(memcpy);
+EXPORT_SYMBOL(memset);
+EXPORT_SYMBOL(memmove);
+EXPORT_SYMBOL(memcmp);
+EXPORT_SYMBOL(memchr);
+
+EXPORT_SYMBOL(strcpy);
+EXPORT_SYMBOL(strncpy);
+EXPORT_SYMBOL(strcat);
+EXPORT_SYMBOL(strlen);
+EXPORT_SYMBOL(strcmp);
+EXPORT_SYMBOL(strncmp);
+
+#ifndef CONFIG_GENERIC_CSUM
+EXPORT_SYMBOL(csum_partial);
+EXPORT_SYMBOL(csum_partial_copy_generic);
+EXPORT_SYMBOL(ip_fast_csum);
+EXPORT_SYMBOL(csum_tcpudp_magic);
+#endif
+
+EXPORT_SYMBOL(__copy_tofrom_user);
+EXPORT_SYMBOL(__clear_user);
+EXPORT_SYMBOL(copy_page);
+
+#ifdef CONFIG_PPC64
+EXPORT_SYMBOL(__arch_hweight8);
+EXPORT_SYMBOL(__arch_hweight16);
+EXPORT_SYMBOL(__arch_hweight32);
+EXPORT_SYMBOL(__arch_hweight64);
+#endif
diff --git a/arch/powerpc/lib/rheap.c b/arch/powerpc/lib/rheap.c
index a1060a868e69..69abf844c2c3 100644
--- a/arch/powerpc/lib/rheap.c
+++ b/arch/powerpc/lib/rheap.c
@@ -284,7 +284,7 @@ EXPORT_SYMBOL_GPL(rh_create);
*/
void rh_destroy(rh_info_t * info)
{
- if ((info->flags & RHIF_STATIC_BLOCK) == 0 && info->block != NULL)
+ if ((info->flags & RHIF_STATIC_BLOCK) == 0)
kfree(info->block);
if ((info->flags & RHIF_STATIC_INFO) == 0)
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index 5c09f365c842..dc885b30f7a6 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -98,13 +98,8 @@ static unsigned long __kprobes dform_ea(unsigned int instr, struct pt_regs *regs
ra = (instr >> 16) & 0x1f;
ea = (signed short) instr; /* sign-extend */
- if (ra) {
+ if (ra)
ea += regs->gpr[ra];
- if (instr & 0x04000000) { /* update forms */
- if ((instr>>26) != 47) /* stmw is not an update form */
- regs->gpr[ra] = ea;
- }
- }
return truncate_if_32bit(regs->msr, ea);
}
@@ -120,11 +115,8 @@ static unsigned long __kprobes dsform_ea(unsigned int instr, struct pt_regs *reg
ra = (instr >> 16) & 0x1f;
ea = (signed short) (instr & ~3); /* sign-extend */
- if (ra) {
+ if (ra)
ea += regs->gpr[ra];
- if ((instr & 3) == 1) /* update forms */
- regs->gpr[ra] = ea;
- }
return truncate_if_32bit(regs->msr, ea);
}
@@ -133,8 +125,8 @@ static unsigned long __kprobes dsform_ea(unsigned int instr, struct pt_regs *reg
/*
* Calculate effective address for an X-form instruction
*/
-static unsigned long __kprobes xform_ea(unsigned int instr, struct pt_regs *regs,
- int do_update)
+static unsigned long __kprobes xform_ea(unsigned int instr,
+ struct pt_regs *regs)
{
int ra, rb;
unsigned long ea;
@@ -142,11 +134,8 @@ static unsigned long __kprobes xform_ea(unsigned int instr, struct pt_regs *regs
ra = (instr >> 16) & 0x1f;
rb = (instr >> 11) & 0x1f;
ea = regs->gpr[rb];
- if (ra) {
+ if (ra)
ea += regs->gpr[ra];
- if (do_update) /* update forms */
- regs->gpr[ra] = ea;
- }
return truncate_if_32bit(regs->msr, ea);
}
@@ -611,6 +600,23 @@ static void __kprobes do_cmp_unsigned(struct pt_regs *regs, unsigned long v1,
regs->ccr = (regs->ccr & ~(0xf << shift)) | (crval << shift);
}
+static int __kprobes trap_compare(long v1, long v2)
+{
+ int ret = 0;
+
+ if (v1 < v2)
+ ret |= 0x10;
+ else if (v1 > v2)
+ ret |= 0x08;
+ else
+ ret |= 0x04;
+ if ((unsigned long)v1 < (unsigned long)v2)
+ ret |= 0x02;
+ else if ((unsigned long)v1 > (unsigned long)v2)
+ ret |= 0x01;
+ return ret;
+}
+
/*
* Elements of 32-bit rotate and mask instructions.
*/
@@ -627,26 +633,27 @@ static void __kprobes do_cmp_unsigned(struct pt_regs *regs, unsigned long v1,
#define ROTATE(x, n) ((n) ? (((x) << (n)) | ((x) >> (8 * sizeof(long) - (n)))) : (x))
/*
- * Emulate instructions that cause a transfer of control,
- * loads and stores, and a few other instructions.
- * Returns 1 if the step was emulated, 0 if not,
- * or -1 if the instruction is one that should not be stepped,
- * such as an rfid, or a mtmsrd that would clear MSR_RI.
+ * Decode an instruction, and execute it if that can be done just by
+ * modifying *regs (i.e. integer arithmetic and logical instructions,
+ * branches, and barrier instructions).
+ * Returns 1 if the instruction has been executed, or 0 if not.
+ * Sets *op to indicate what the instruction does.
*/
-int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
+int __kprobes analyse_instr(struct instruction_op *op, struct pt_regs *regs,
+ unsigned int instr)
{
unsigned int opcode, ra, rb, rd, spr, u;
unsigned long int imm;
unsigned long int val, val2;
- unsigned long int ea;
- unsigned int cr, mb, me, sh;
- int err;
- unsigned long old_ra, val3;
+ unsigned int mb, me, sh;
long ival;
+ op->type = COMPUTE;
+
opcode = instr >> 26;
switch (opcode) {
case 16: /* bc */
+ op->type = BRANCH;
imm = (signed short)(instr & 0xfffc);
if ((instr & 2) == 0)
imm += regs->nip;
@@ -659,26 +666,14 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
return 1;
#ifdef CONFIG_PPC64
case 17: /* sc */
- /*
- * N.B. this uses knowledge about how the syscall
- * entry code works. If that is changed, this will
- * need to be changed also.
- */
- if (regs->gpr[0] == 0x1ebe &&
- cpu_has_feature(CPU_FTR_REAL_LE)) {
- regs->msr ^= MSR_LE;
- goto instr_done;
- }
- regs->gpr[9] = regs->gpr[13];
- regs->gpr[10] = MSR_KERNEL;
- regs->gpr[11] = regs->nip + 4;
- regs->gpr[12] = regs->msr & MSR_MASK;
- regs->gpr[13] = (unsigned long) get_paca();
- regs->nip = (unsigned long) &system_call_common;
- regs->msr = MSR_KERNEL;
- return 1;
+ if ((instr & 0xfe2) == 2)
+ op->type = SYSCALL;
+ else
+ op->type = UNKNOWN;
+ return 0;
#endif
case 18: /* b */
+ op->type = BRANCH;
imm = instr & 0x03fffffc;
if (imm & 0x02000000)
imm -= 0x04000000;
@@ -691,8 +686,16 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
return 1;
case 19:
switch ((instr >> 1) & 0x3ff) {
+ case 0: /* mcrf */
+ rd = (instr >> 21) & 0x1c;
+ ra = (instr >> 16) & 0x1c;
+ val = (regs->ccr >> ra) & 0xf;
+ regs->ccr = (regs->ccr & ~(0xfUL << rd)) | (val << rd);
+ goto instr_done;
+
case 16: /* bclr */
case 528: /* bcctr */
+ op->type = BRANCH;
imm = (instr & 0x400)? regs->ctr: regs->link;
regs->nip = truncate_if_32bit(regs->msr, regs->nip + 4);
imm = truncate_if_32bit(regs->msr, imm);
@@ -703,9 +706,13 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
return 1;
case 18: /* rfid, scary */
- return -1;
+ if (regs->msr & MSR_PR)
+ goto priv;
+ op->type = RFI;
+ return 0;
case 150: /* isync */
+ op->type = BARRIER;
isync();
goto instr_done;
@@ -731,6 +738,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
case 31:
switch ((instr >> 1) & 0x3ff) {
case 598: /* sync */
+ op->type = BARRIER;
#ifdef __powerpc64__
switch ((instr >> 21) & 3) {
case 1: /* lwsync */
@@ -745,6 +753,7 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
goto instr_done;
case 854: /* eieio */
+ op->type = BARRIER;
eieio();
goto instr_done;
}
@@ -760,6 +769,17 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
rb = (instr >> 11) & 0x1f;
switch (opcode) {
+#ifdef __powerpc64__
+ case 2: /* tdi */
+ if (rd & trap_compare(regs->gpr[ra], (short) instr))
+ goto trap;
+ goto instr_done;
+#endif
+ case 3: /* twi */
+ if (rd & trap_compare((int)regs->gpr[ra], (short) instr))
+ goto trap;
+ goto instr_done;
+
case 7: /* mulli */
regs->gpr[rd] = regs->gpr[ra] * (short) instr;
goto instr_done;
@@ -908,35 +928,44 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
case 31:
switch ((instr >> 1) & 0x3ff) {
+ case 4: /* tw */
+ if (rd == 0x1f ||
+ (rd & trap_compare((int)regs->gpr[ra],
+ (int)regs->gpr[rb])))
+ goto trap;
+ goto instr_done;
+#ifdef __powerpc64__
+ case 68: /* td */
+ if (rd & trap_compare(regs->gpr[ra], regs->gpr[rb]))
+ goto trap;
+ goto instr_done;
+#endif
case 83: /* mfmsr */
if (regs->msr & MSR_PR)
- break;
- regs->gpr[rd] = regs->msr & MSR_MASK;
- goto instr_done;
+ goto priv;
+ op->type = MFMSR;
+ op->reg = rd;
+ return 0;
case 146: /* mtmsr */
if (regs->msr & MSR_PR)
- break;
- imm = regs->gpr[rd];
- if ((imm & MSR_RI) == 0)
- /* can't step mtmsr that would clear MSR_RI */
- return -1;
- regs->msr = imm;
- goto instr_done;
+ goto priv;
+ op->type = MTMSR;
+ op->reg = rd;
+ op->val = 0xffffffff & ~(MSR_ME | MSR_LE);
+ return 0;
#ifdef CONFIG_PPC64
case 178: /* mtmsrd */
- /* only MSR_EE and MSR_RI get changed if bit 15 set */
- /* mtmsrd doesn't change MSR_HV and MSR_ME */
if (regs->msr & MSR_PR)
- break;
- imm = (instr & 0x10000)? 0x8002: 0xefffffffffffefffUL;
- imm = (regs->msr & MSR_MASK & ~imm)
- | (regs->gpr[rd] & imm);
- if ((imm & MSR_RI) == 0)
- /* can't step mtmsrd that would clear MSR_RI */
- return -1;
- regs->msr = imm;
- goto instr_done;
+ goto priv;
+ op->type = MTMSR;
+ op->reg = rd;
+ /* only MSR_EE and MSR_RI get changed if bit 15 set */
+ /* mtmsrd doesn't change MSR_HV, MSR_ME or MSR_LE */
+ imm = (instr & 0x10000)? 0x8002: 0xefffffffffffeffeUL;
+ op->val = imm;
+ return 0;
#endif
+
case 19: /* mfcr */
regs->gpr[rd] = regs->ccr;
regs->gpr[rd] &= 0xffffffffUL;
@@ -954,33 +983,43 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
goto instr_done;
case 339: /* mfspr */
- spr = (instr >> 11) & 0x3ff;
+ spr = ((instr >> 16) & 0x1f) | ((instr >> 6) & 0x3e0);
switch (spr) {
- case 0x20: /* mfxer */
+ case SPRN_XER: /* mfxer */
regs->gpr[rd] = regs->xer;
regs->gpr[rd] &= 0xffffffffUL;
goto instr_done;
- case 0x100: /* mflr */
+ case SPRN_LR: /* mflr */
regs->gpr[rd] = regs->link;
goto instr_done;
- case 0x120: /* mfctr */
+ case SPRN_CTR: /* mfctr */
regs->gpr[rd] = regs->ctr;
goto instr_done;
+ default:
+ op->type = MFSPR;
+ op->reg = rd;
+ op->spr = spr;
+ return 0;
}
break;
case 467: /* mtspr */
- spr = (instr >> 11) & 0x3ff;
+ spr = ((instr >> 16) & 0x1f) | ((instr >> 6) & 0x3e0);
switch (spr) {
- case 0x20: /* mtxer */
+ case SPRN_XER: /* mtxer */
regs->xer = (regs->gpr[rd] & 0xffffffffUL);
goto instr_done;
- case 0x100: /* mtlr */
+ case SPRN_LR: /* mtlr */
regs->link = regs->gpr[rd];
goto instr_done;
- case 0x120: /* mtctr */
+ case SPRN_CTR: /* mtctr */
regs->ctr = regs->gpr[rd];
goto instr_done;
+ default:
+ op->type = MTSPR;
+ op->val = regs->gpr[rd];
+ op->spr = spr;
+ return 0;
}
break;
@@ -1257,294 +1296,242 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
* Cache instructions
*/
case 54: /* dcbst */
- ea = xform_ea(instr, regs, 0);
- if (!address_ok(regs, ea, 8))
- return 0;
- err = 0;
- __cacheop_user_asmx(ea, err, "dcbst");
- if (err)
- return 0;
- goto instr_done;
+ op->type = MKOP(CACHEOP, DCBST, 0);
+ op->ea = xform_ea(instr, regs);
+ return 0;
case 86: /* dcbf */
- ea = xform_ea(instr, regs, 0);
- if (!address_ok(regs, ea, 8))
- return 0;
- err = 0;
- __cacheop_user_asmx(ea, err, "dcbf");
- if (err)
- return 0;
- goto instr_done;
+ op->type = MKOP(CACHEOP, DCBF, 0);
+ op->ea = xform_ea(instr, regs);
+ return 0;
case 246: /* dcbtst */
- if (rd == 0) {
- ea = xform_ea(instr, regs, 0);
- prefetchw((void *) ea);
- }
- goto instr_done;
+ op->type = MKOP(CACHEOP, DCBTST, 0);
+ op->ea = xform_ea(instr, regs);
+ op->reg = rd;
+ return 0;
case 278: /* dcbt */
- if (rd == 0) {
- ea = xform_ea(instr, regs, 0);
- prefetch((void *) ea);
- }
- goto instr_done;
+ op->type = MKOP(CACHEOP, DCBTST, 0);
+ op->ea = xform_ea(instr, regs);
+ op->reg = rd;
+ return 0;
+ case 982: /* icbi */
+ op->type = MKOP(CACHEOP, ICBI, 0);
+ op->ea = xform_ea(instr, regs);
+ return 0;
}
break;
}
/*
- * Following cases are for loads and stores, so bail out
- * if we're in little-endian mode.
+ * Loads and stores.
*/
- if (regs->msr & MSR_LE)
- return 0;
-
- /*
- * Save register RA in case it's an update form load or store
- * and the access faults.
- */
- old_ra = regs->gpr[ra];
+ op->type = UNKNOWN;
+ op->update_reg = ra;
+ op->reg = rd;
+ op->val = regs->gpr[rd];
+ u = (instr >> 20) & UPDATE;
switch (opcode) {
case 31:
- u = instr & 0x40;
+ u = instr & UPDATE;
+ op->ea = xform_ea(instr, regs);
switch ((instr >> 1) & 0x3ff) {
case 20: /* lwarx */
- ea = xform_ea(instr, regs, 0);
- if (ea & 3)
- break; /* can't handle misaligned */
- err = -EFAULT;
- if (!address_ok(regs, ea, 4))
- goto ldst_done;
- err = 0;
- __get_user_asmx(val, ea, err, "lwarx");
- if (!err)
- regs->gpr[rd] = val;
- goto ldst_done;
+ op->type = MKOP(LARX, 0, 4);
+ break;
case 150: /* stwcx. */
- ea = xform_ea(instr, regs, 0);
- if (ea & 3)
- break; /* can't handle misaligned */
- err = -EFAULT;
- if (!address_ok(regs, ea, 4))
- goto ldst_done;
- err = 0;
- __put_user_asmx(regs->gpr[rd], ea, err, "stwcx.", cr);
- if (!err)
- regs->ccr = (regs->ccr & 0x0fffffff) |
- (cr & 0xe0000000) |
- ((regs->xer >> 3) & 0x10000000);
- goto ldst_done;
+ op->type = MKOP(STCX, 0, 4);
+ break;
#ifdef __powerpc64__
case 84: /* ldarx */
- ea = xform_ea(instr, regs, 0);
- if (ea & 7)
- break; /* can't handle misaligned */
- err = -EFAULT;
- if (!address_ok(regs, ea, 8))
- goto ldst_done;
- err = 0;
- __get_user_asmx(val, ea, err, "ldarx");
- if (!err)
- regs->gpr[rd] = val;
- goto ldst_done;
+ op->type = MKOP(LARX, 0, 8);
+ break;
case 214: /* stdcx. */
- ea = xform_ea(instr, regs, 0);
- if (ea & 7)
- break; /* can't handle misaligned */
- err = -EFAULT;
- if (!address_ok(regs, ea, 8))
- goto ldst_done;
- err = 0;
- __put_user_asmx(regs->gpr[rd], ea, err, "stdcx.", cr);
- if (!err)
- regs->ccr = (regs->ccr & 0x0fffffff) |
- (cr & 0xe0000000) |
- ((regs->xer >> 3) & 0x10000000);
- goto ldst_done;
+ op->type = MKOP(STCX, 0, 8);
+ break;
case 21: /* ldx */
case 53: /* ldux */
- err = read_mem(&regs->gpr[rd], xform_ea(instr, regs, u),
- 8, regs);
- goto ldst_done;
+ op->type = MKOP(LOAD, u, 8);
+ break;
#endif
case 23: /* lwzx */
case 55: /* lwzux */
- err = read_mem(&regs->gpr[rd], xform_ea(instr, regs, u),
- 4, regs);
- goto ldst_done;
+ op->type = MKOP(LOAD, u, 4);
+ break;
case 87: /* lbzx */
case 119: /* lbzux */
- err = read_mem(&regs->gpr[rd], xform_ea(instr, regs, u),
- 1, regs);
- goto ldst_done;
+ op->type = MKOP(LOAD, u, 1);
+ break;
#ifdef CONFIG_ALTIVEC
case 103: /* lvx */
case 359: /* lvxl */
if (!(regs->msr & MSR_VEC))
- break;
- ea = xform_ea(instr, regs, 0);
- err = do_vec_load(rd, do_lvx, ea, regs);
- goto ldst_done;
+ goto vecunavail;
+ op->type = MKOP(LOAD_VMX, 0, 16);
+ break;
case 231: /* stvx */
case 487: /* stvxl */
if (!(regs->msr & MSR_VEC))
- break;
- ea = xform_ea(instr, regs, 0);
- err = do_vec_store(rd, do_stvx, ea, regs);
- goto ldst_done;
+ goto vecunavail;
+ op->type = MKOP(STORE_VMX, 0, 16);
+ break;
#endif /* CONFIG_ALTIVEC */
#ifdef __powerpc64__
case 149: /* stdx */
case 181: /* stdux */
- val = regs->gpr[rd];
- err = write_mem(val, xform_ea(instr, regs, u), 8, regs);
- goto ldst_done;
+ op->type = MKOP(STORE, u, 8);
+ break;
#endif
case 151: /* stwx */
case 183: /* stwux */
- val = regs->gpr[rd];
- err = write_mem(val, xform_ea(instr, regs, u), 4, regs);
- goto ldst_done;
+ op->type = MKOP(STORE, u, 4);
+ break;
case 215: /* stbx */
case 247: /* stbux */
- val = regs->gpr[rd];
- err = write_mem(val, xform_ea(instr, regs, u), 1, regs);
- goto ldst_done;
+ op->type = MKOP(STORE, u, 1);
+ break;
case 279: /* lhzx */
case 311: /* lhzux */
- err = read_mem(&regs->gpr[rd], xform_ea(instr, regs, u),
- 2, regs);
- goto ldst_done;
+ op->type = MKOP(LOAD, u, 2);
+ break;
#ifdef __powerpc64__
case 341: /* lwax */
case 373: /* lwaux */
- err = read_mem(&regs->gpr[rd], xform_ea(instr, regs, u),
- 4, regs);
- if (!err)
- regs->gpr[rd] = (signed int) regs->gpr[rd];
- goto ldst_done;
+ op->type = MKOP(LOAD, SIGNEXT | u, 4);
+ break;
#endif
case 343: /* lhax */
case 375: /* lhaux */
- err = read_mem(&regs->gpr[rd], xform_ea(instr, regs, u),
- 2, regs);
- if (!err)
- regs->gpr[rd] = (signed short) regs->gpr[rd];
- goto ldst_done;
+ op->type = MKOP(LOAD, SIGNEXT | u, 2);
+ break;
case 407: /* sthx */
case 439: /* sthux */
- val = regs->gpr[rd];
- err = write_mem(val, xform_ea(instr, regs, u), 2, regs);
- goto ldst_done;
+ op->type = MKOP(STORE, u, 2);
+ break;
#ifdef __powerpc64__
case 532: /* ldbrx */
- err = read_mem(&val, xform_ea(instr, regs, 0), 8, regs);
- if (!err)
- regs->gpr[rd] = byterev_8(val);
- goto ldst_done;
+ op->type = MKOP(LOAD, BYTEREV, 8);
+ break;
#endif
+ case 533: /* lswx */
+ op->type = MKOP(LOAD_MULTI, 0, regs->xer & 0x7f);
+ break;
case 534: /* lwbrx */
- err = read_mem(&val, xform_ea(instr, regs, 0), 4, regs);
- if (!err)
- regs->gpr[rd] = byterev_4(val);
- goto ldst_done;
+ op->type = MKOP(LOAD, BYTEREV, 4);
+ break;
+
+ case 597: /* lswi */
+ if (rb == 0)
+ rb = 32; /* # bytes to load */
+ op->type = MKOP(LOAD_MULTI, 0, rb);
+ op->ea = 0;
+ if (ra)
+ op->ea = truncate_if_32bit(regs->msr,
+ regs->gpr[ra]);
+ break;
#ifdef CONFIG_PPC_FPU
case 535: /* lfsx */
case 567: /* lfsux */
if (!(regs->msr & MSR_FP))
- break;
- ea = xform_ea(instr, regs, u);
- err = do_fp_load(rd, do_lfs, ea, 4, regs);
- goto ldst_done;
+ goto fpunavail;
+ op->type = MKOP(LOAD_FP, u, 4);
+ break;
case 599: /* lfdx */
case 631: /* lfdux */
if (!(regs->msr & MSR_FP))
- break;
- ea = xform_ea(instr, regs, u);
- err = do_fp_load(rd, do_lfd, ea, 8, regs);
- goto ldst_done;
+ goto fpunavail;
+ op->type = MKOP(LOAD_FP, u, 8);
+ break;
case 663: /* stfsx */
case 695: /* stfsux */
if (!(regs->msr & MSR_FP))
- break;
- ea = xform_ea(instr, regs, u);
- err = do_fp_store(rd, do_stfs, ea, 4, regs);
- goto ldst_done;
+ goto fpunavail;
+ op->type = MKOP(STORE_FP, u, 4);
+ break;
case 727: /* stfdx */
case 759: /* stfdux */
if (!(regs->msr & MSR_FP))
- break;
- ea = xform_ea(instr, regs, u);
- err = do_fp_store(rd, do_stfd, ea, 8, regs);
- goto ldst_done;
+ goto fpunavail;
+ op->type = MKOP(STORE_FP, u, 8);
+ break;
#endif
#ifdef __powerpc64__
case 660: /* stdbrx */
- val = byterev_8(regs->gpr[rd]);
- err = write_mem(val, xform_ea(instr, regs, 0), 8, regs);
- goto ldst_done;
+ op->type = MKOP(STORE, BYTEREV, 8);
+ op->val = byterev_8(regs->gpr[rd]);
+ break;
#endif
+ case 661: /* stswx */
+ op->type = MKOP(STORE_MULTI, 0, regs->xer & 0x7f);
+ break;
+
case 662: /* stwbrx */
- val = byterev_4(regs->gpr[rd]);
- err = write_mem(val, xform_ea(instr, regs, 0), 4, regs);
- goto ldst_done;
+ op->type = MKOP(STORE, BYTEREV, 4);
+ op->val = byterev_4(regs->gpr[rd]);
+ break;
+
+ case 725:
+ if (rb == 0)
+ rb = 32; /* # bytes to store */
+ op->type = MKOP(STORE_MULTI, 0, rb);
+ op->ea = 0;
+ if (ra)
+ op->ea = truncate_if_32bit(regs->msr,
+ regs->gpr[ra]);
+ break;
case 790: /* lhbrx */
- err = read_mem(&val, xform_ea(instr, regs, 0), 2, regs);
- if (!err)
- regs->gpr[rd] = byterev_2(val);
- goto ldst_done;
+ op->type = MKOP(LOAD, BYTEREV, 2);
+ break;
case 918: /* sthbrx */
- val = byterev_2(regs->gpr[rd]);
- err = write_mem(val, xform_ea(instr, regs, 0), 2, regs);
- goto ldst_done;
+ op->type = MKOP(STORE, BYTEREV, 2);
+ op->val = byterev_2(regs->gpr[rd]);
+ break;
#ifdef CONFIG_VSX
case 844: /* lxvd2x */
case 876: /* lxvd2ux */
if (!(regs->msr & MSR_VSX))
- break;
- rd |= (instr & 1) << 5;
- ea = xform_ea(instr, regs, u);
- err = do_vsx_load(rd, do_lxvd2x, ea, regs);
- goto ldst_done;
+ goto vsxunavail;
+ op->reg = rd | ((instr & 1) << 5);
+ op->type = MKOP(LOAD_VSX, u, 16);
+ break;
case 972: /* stxvd2x */
case 1004: /* stxvd2ux */
if (!(regs->msr & MSR_VSX))
- break;
- rd |= (instr & 1) << 5;
- ea = xform_ea(instr, regs, u);
- err = do_vsx_store(rd, do_stxvd2x, ea, regs);
- goto ldst_done;
+ goto vsxunavail;
+ op->reg = rd | ((instr & 1) << 5);
+ op->type = MKOP(STORE_VSX, u, 16);
+ break;
#endif /* CONFIG_VSX */
}
@@ -1552,178 +1539,123 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
case 32: /* lwz */
case 33: /* lwzu */
- err = read_mem(&regs->gpr[rd], dform_ea(instr, regs), 4, regs);
- goto ldst_done;
+ op->type = MKOP(LOAD, u, 4);
+ op->ea = dform_ea(instr, regs);
+ break;
case 34: /* lbz */
case 35: /* lbzu */
- err = read_mem(&regs->gpr[rd], dform_ea(instr, regs), 1, regs);
- goto ldst_done;
+ op->type = MKOP(LOAD, u, 1);
+ op->ea = dform_ea(instr, regs);
+ break;
case 36: /* stw */
- val = regs->gpr[rd];
- err = write_mem(val, dform_ea(instr, regs), 4, regs);
- goto ldst_done;
-
case 37: /* stwu */
- val = regs->gpr[rd];
- val3 = dform_ea(instr, regs);
- /*
- * For PPC32 we always use stwu to change stack point with r1. So
- * this emulated store may corrupt the exception frame, now we
- * have to provide the exception frame trampoline, which is pushed
- * below the kprobed function stack. So we only update gpr[1] but
- * don't emulate the real store operation. We will do real store
- * operation safely in exception return code by checking this flag.
- */
- if ((ra == 1) && !(regs->msr & MSR_PR) \
- && (val3 >= (regs->gpr[1] - STACK_INT_FRAME_SIZE))) {
-#ifdef CONFIG_PPC32
- /*
- * Check if we will touch kernel sack overflow
- */
- if (val3 - STACK_INT_FRAME_SIZE <= current->thread.ksp_limit) {
- printk(KERN_CRIT "Can't kprobe this since Kernel stack overflow.\n");
- err = -EINVAL;
- break;
- }
-#endif /* CONFIG_PPC32 */
- /*
- * Check if we already set since that means we'll
- * lose the previous value.
- */
- WARN_ON(test_thread_flag(TIF_EMULATE_STACK_STORE));
- set_thread_flag(TIF_EMULATE_STACK_STORE);
- err = 0;
- } else
- err = write_mem(val, val3, 4, regs);
- goto ldst_done;
+ op->type = MKOP(STORE, u, 4);
+ op->ea = dform_ea(instr, regs);
+ break;
case 38: /* stb */
case 39: /* stbu */
- val = regs->gpr[rd];
- err = write_mem(val, dform_ea(instr, regs), 1, regs);
- goto ldst_done;
+ op->type = MKOP(STORE, u, 1);
+ op->ea = dform_ea(instr, regs);
+ break;
case 40: /* lhz */
case 41: /* lhzu */
- err = read_mem(&regs->gpr[rd], dform_ea(instr, regs), 2, regs);
- goto ldst_done;
+ op->type = MKOP(LOAD, u, 2);
+ op->ea = dform_ea(instr, regs);
+ break;
case 42: /* lha */
case 43: /* lhau */
- err = read_mem(&regs->gpr[rd], dform_ea(instr, regs), 2, regs);
- if (!err)
- regs->gpr[rd] = (signed short) regs->gpr[rd];
- goto ldst_done;
+ op->type = MKOP(LOAD, SIGNEXT | u, 2);
+ op->ea = dform_ea(instr, regs);
+ break;
case 44: /* sth */
case 45: /* sthu */
- val = regs->gpr[rd];
- err = write_mem(val, dform_ea(instr, regs), 2, regs);
- goto ldst_done;
+ op->type = MKOP(STORE, u, 2);
+ op->ea = dform_ea(instr, regs);
+ break;
case 46: /* lmw */
- ra = (instr >> 16) & 0x1f;
if (ra >= rd)
break; /* invalid form, ra in range to load */
- ea = dform_ea(instr, regs);
- do {
- err = read_mem(&regs->gpr[rd], ea, 4, regs);
- if (err)
- return 0;
- ea += 4;
- } while (++rd < 32);
- goto instr_done;
+ op->type = MKOP(LOAD_MULTI, 0, 4 * (32 - rd));
+ op->ea = dform_ea(instr, regs);
+ break;
case 47: /* stmw */
- ea = dform_ea(instr, regs);
- do {
- err = write_mem(regs->gpr[rd], ea, 4, regs);
- if (err)
- return 0;
- ea += 4;
- } while (++rd < 32);
- goto instr_done;
+ op->type = MKOP(STORE_MULTI, 0, 4 * (32 - rd));
+ op->ea = dform_ea(instr, regs);
+ break;
#ifdef CONFIG_PPC_FPU
case 48: /* lfs */
case 49: /* lfsu */
if (!(regs->msr & MSR_FP))
- break;
- ea = dform_ea(instr, regs);
- err = do_fp_load(rd, do_lfs, ea, 4, regs);
- goto ldst_done;
+ goto fpunavail;
+ op->type = MKOP(LOAD_FP, u, 4);
+ op->ea = dform_ea(instr, regs);
+ break;
case 50: /* lfd */
case 51: /* lfdu */
if (!(regs->msr & MSR_FP))
- break;
- ea = dform_ea(instr, regs);
- err = do_fp_load(rd, do_lfd, ea, 8, regs);
- goto ldst_done;
+ goto fpunavail;
+ op->type = MKOP(LOAD_FP, u, 8);
+ op->ea = dform_ea(instr, regs);
+ break;
case 52: /* stfs */
case 53: /* stfsu */
if (!(regs->msr & MSR_FP))
- break;
- ea = dform_ea(instr, regs);
- err = do_fp_store(rd, do_stfs, ea, 4, regs);
- goto ldst_done;
+ goto fpunavail;
+ op->type = MKOP(STORE_FP, u, 4);
+ op->ea = dform_ea(instr, regs);
+ break;
case 54: /* stfd */
case 55: /* stfdu */
if (!(regs->msr & MSR_FP))
- break;
- ea = dform_ea(instr, regs);
- err = do_fp_store(rd, do_stfd, ea, 8, regs);
- goto ldst_done;
+ goto fpunavail;
+ op->type = MKOP(STORE_FP, u, 8);
+ op->ea = dform_ea(instr, regs);
+ break;
#endif
#ifdef __powerpc64__
case 58: /* ld[u], lwa */
+ op->ea = dsform_ea(instr, regs);
switch (instr & 3) {
case 0: /* ld */
- err = read_mem(&regs->gpr[rd], dsform_ea(instr, regs),
- 8, regs);
- goto ldst_done;
+ op->type = MKOP(LOAD, 0, 8);
+ break;
case 1: /* ldu */
- err = read_mem(&regs->gpr[rd], dsform_ea(instr, regs),
- 8, regs);
- goto ldst_done;
+ op->type = MKOP(LOAD, UPDATE, 8);
+ break;
case 2: /* lwa */
- err = read_mem(&regs->gpr[rd], dsform_ea(instr, regs),
- 4, regs);
- if (!err)
- regs->gpr[rd] = (signed int) regs->gpr[rd];
- goto ldst_done;
+ op->type = MKOP(LOAD, SIGNEXT, 4);
+ break;
}
break;
case 62: /* std[u] */
- val = regs->gpr[rd];
+ op->ea = dsform_ea(instr, regs);
switch (instr & 3) {
case 0: /* std */
- err = write_mem(val, dsform_ea(instr, regs), 8, regs);
- goto ldst_done;
+ op->type = MKOP(STORE, 0, 8);
+ break;
case 1: /* stdu */
- err = write_mem(val, dsform_ea(instr, regs), 8, regs);
- goto ldst_done;
+ op->type = MKOP(STORE, UPDATE, 8);
+ break;
}
break;
#endif /* __powerpc64__ */
}
- err = -EINVAL;
-
- ldst_done:
- if (err) {
- regs->gpr[ra] = old_ra;
- return 0; /* invoke DSI if -EFAULT? */
- }
- instr_done:
- regs->nip = truncate_if_32bit(regs->msr, regs->nip + 4);
- return 1;
+ return 0;
logical_done:
if (instr & 1)
@@ -1733,5 +1665,351 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
arith_done:
if (instr & 1)
set_cr0(regs, rd);
- goto instr_done;
+
+ instr_done:
+ regs->nip = truncate_if_32bit(regs->msr, regs->nip + 4);
+ return 1;
+
+ priv:
+ op->type = INTERRUPT | 0x700;
+ op->val = SRR1_PROGPRIV;
+ return 0;
+
+ trap:
+ op->type = INTERRUPT | 0x700;
+ op->val = SRR1_PROGTRAP;
+ return 0;
+
+#ifdef CONFIG_PPC_FPU
+ fpunavail:
+ op->type = INTERRUPT | 0x800;
+ return 0;
+#endif
+
+#ifdef CONFIG_ALTIVEC
+ vecunavail:
+ op->type = INTERRUPT | 0xf20;
+ return 0;
+#endif
+
+#ifdef CONFIG_VSX
+ vsxunavail:
+ op->type = INTERRUPT | 0xf40;
+ return 0;
+#endif
+}
+EXPORT_SYMBOL_GPL(analyse_instr);
+
+/*
+ * For PPC32 we always use stwu with r1 to change the stack pointer.
+ * So this emulated store may corrupt the exception frame, now we
+ * have to provide the exception frame trampoline, which is pushed
+ * below the kprobed function stack. So we only update gpr[1] but
+ * don't emulate the real store operation. We will do real store
+ * operation safely in exception return code by checking this flag.
+ */
+static __kprobes int handle_stack_update(unsigned long ea, struct pt_regs *regs)
+{
+#ifdef CONFIG_PPC32
+ /*
+ * Check if we will touch kernel stack overflow
+ */
+ if (ea - STACK_INT_FRAME_SIZE <= current->thread.ksp_limit) {
+ printk(KERN_CRIT "Can't kprobe this since kernel stack would overflow.\n");
+ return -EINVAL;
+ }
+#endif /* CONFIG_PPC32 */
+ /*
+ * Check if we already set since that means we'll
+ * lose the previous value.
+ */
+ WARN_ON(test_thread_flag(TIF_EMULATE_STACK_STORE));
+ set_thread_flag(TIF_EMULATE_STACK_STORE);
+ return 0;
+}
+
+static __kprobes void do_signext(unsigned long *valp, int size)
+{
+ switch (size) {
+ case 2:
+ *valp = (signed short) *valp;
+ break;
+ case 4:
+ *valp = (signed int) *valp;
+ break;
+ }
+}
+
+static __kprobes void do_byterev(unsigned long *valp, int size)
+{
+ switch (size) {
+ case 2:
+ *valp = byterev_2(*valp);
+ break;
+ case 4:
+ *valp = byterev_4(*valp);
+ break;
+#ifdef __powerpc64__
+ case 8:
+ *valp = byterev_8(*valp);
+ break;
+#endif
+ }
+}
+
+/*
+ * Emulate instructions that cause a transfer of control,
+ * loads and stores, and a few other instructions.
+ * Returns 1 if the step was emulated, 0 if not,
+ * or -1 if the instruction is one that should not be stepped,
+ * such as an rfid, or a mtmsrd that would clear MSR_RI.
+ */
+int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
+{
+ struct instruction_op op;
+ int r, err, size;
+ unsigned long val;
+ unsigned int cr;
+ int i, rd, nb;
+
+ r = analyse_instr(&op, regs, instr);
+ if (r != 0)
+ return r;
+
+ err = 0;
+ size = GETSIZE(op.type);
+ switch (op.type & INSTR_TYPE_MASK) {
+ case CACHEOP:
+ if (!address_ok(regs, op.ea, 8))
+ return 0;
+ switch (op.type & CACHEOP_MASK) {
+ case DCBST:
+ __cacheop_user_asmx(op.ea, err, "dcbst");
+ break;
+ case DCBF:
+ __cacheop_user_asmx(op.ea, err, "dcbf");
+ break;
+ case DCBTST:
+ if (op.reg == 0)
+ prefetchw((void *) op.ea);
+ break;
+ case DCBT:
+ if (op.reg == 0)
+ prefetch((void *) op.ea);
+ break;
+ case ICBI:
+ __cacheop_user_asmx(op.ea, err, "icbi");
+ break;
+ }
+ if (err)
+ return 0;
+ goto instr_done;
+
+ case LARX:
+ if (regs->msr & MSR_LE)
+ return 0;
+ if (op.ea & (size - 1))
+ break; /* can't handle misaligned */
+ err = -EFAULT;
+ if (!address_ok(regs, op.ea, size))
+ goto ldst_done;
+ err = 0;
+ switch (size) {
+ case 4:
+ __get_user_asmx(val, op.ea, err, "lwarx");
+ break;
+ case 8:
+ __get_user_asmx(val, op.ea, err, "ldarx");
+ break;
+ default:
+ return 0;
+ }
+ if (!err)
+ regs->gpr[op.reg] = val;
+ goto ldst_done;
+
+ case STCX:
+ if (regs->msr & MSR_LE)
+ return 0;
+ if (op.ea & (size - 1))
+ break; /* can't handle misaligned */
+ err = -EFAULT;
+ if (!address_ok(regs, op.ea, size))
+ goto ldst_done;
+ err = 0;
+ switch (size) {
+ case 4:
+ __put_user_asmx(op.val, op.ea, err, "stwcx.", cr);
+ break;
+ case 8:
+ __put_user_asmx(op.val, op.ea, err, "stdcx.", cr);
+ break;
+ default:
+ return 0;
+ }
+ if (!err)
+ regs->ccr = (regs->ccr & 0x0fffffff) |
+ (cr & 0xe0000000) |
+ ((regs->xer >> 3) & 0x10000000);
+ goto ldst_done;
+
+ case LOAD:
+ if (regs->msr & MSR_LE)
+ return 0;
+ err = read_mem(&regs->gpr[op.reg], op.ea, size, regs);
+ if (!err) {
+ if (op.type & SIGNEXT)
+ do_signext(&regs->gpr[op.reg], size);
+ if (op.type & BYTEREV)
+ do_byterev(&regs->gpr[op.reg], size);
+ }
+ goto ldst_done;
+
+#ifdef CONFIG_PPC_FPU
+ case LOAD_FP:
+ if (regs->msr & MSR_LE)
+ return 0;
+ if (size == 4)
+ err = do_fp_load(op.reg, do_lfs, op.ea, size, regs);
+ else
+ err = do_fp_load(op.reg, do_lfd, op.ea, size, regs);
+ goto ldst_done;
+#endif
+#ifdef CONFIG_ALTIVEC
+ case LOAD_VMX:
+ if (regs->msr & MSR_LE)
+ return 0;
+ err = do_vec_load(op.reg, do_lvx, op.ea & ~0xfUL, regs);
+ goto ldst_done;
+#endif
+#ifdef CONFIG_VSX
+ case LOAD_VSX:
+ if (regs->msr & MSR_LE)
+ return 0;
+ err = do_vsx_load(op.reg, do_lxvd2x, op.ea, regs);
+ goto ldst_done;
+#endif
+ case LOAD_MULTI:
+ if (regs->msr & MSR_LE)
+ return 0;
+ rd = op.reg;
+ for (i = 0; i < size; i += 4) {
+ nb = size - i;
+ if (nb > 4)
+ nb = 4;
+ err = read_mem(&regs->gpr[rd], op.ea, nb, regs);
+ if (err)
+ return 0;
+ if (nb < 4) /* left-justify last bytes */
+ regs->gpr[rd] <<= 32 - 8 * nb;
+ op.ea += 4;
+ ++rd;
+ }
+ goto instr_done;
+
+ case STORE:
+ if (regs->msr & MSR_LE)
+ return 0;
+ if ((op.type & UPDATE) && size == sizeof(long) &&
+ op.reg == 1 && op.update_reg == 1 &&
+ !(regs->msr & MSR_PR) &&
+ op.ea >= regs->gpr[1] - STACK_INT_FRAME_SIZE) {
+ err = handle_stack_update(op.ea, regs);
+ goto ldst_done;
+ }
+ err = write_mem(op.val, op.ea, size, regs);
+ goto ldst_done;
+
+#ifdef CONFIG_PPC_FPU
+ case STORE_FP:
+ if (regs->msr & MSR_LE)
+ return 0;
+ if (size == 4)
+ err = do_fp_store(op.reg, do_stfs, op.ea, size, regs);
+ else
+ err = do_fp_store(op.reg, do_stfd, op.ea, size, regs);
+ goto ldst_done;
+#endif
+#ifdef CONFIG_ALTIVEC
+ case STORE_VMX:
+ if (regs->msr & MSR_LE)
+ return 0;
+ err = do_vec_store(op.reg, do_stvx, op.ea & ~0xfUL, regs);
+ goto ldst_done;
+#endif
+#ifdef CONFIG_VSX
+ case STORE_VSX:
+ if (regs->msr & MSR_LE)
+ return 0;
+ err = do_vsx_store(op.reg, do_stxvd2x, op.ea, regs);
+ goto ldst_done;
+#endif
+ case STORE_MULTI:
+ if (regs->msr & MSR_LE)
+ return 0;
+ rd = op.reg;
+ for (i = 0; i < size; i += 4) {
+ val = regs->gpr[rd];
+ nb = size - i;
+ if (nb > 4)
+ nb = 4;
+ else
+ val >>= 32 - 8 * nb;
+ err = write_mem(val, op.ea, nb, regs);
+ if (err)
+ return 0;
+ op.ea += 4;
+ ++rd;
+ }
+ goto instr_done;
+
+ case MFMSR:
+ regs->gpr[op.reg] = regs->msr & MSR_MASK;
+ goto instr_done;
+
+ case MTMSR:
+ val = regs->gpr[op.reg];
+ if ((val & MSR_RI) == 0)
+ /* can't step mtmsr[d] that would clear MSR_RI */
+ return -1;
+ /* here op.val is the mask of bits to change */
+ regs->msr = (regs->msr & ~op.val) | (val & op.val);
+ goto instr_done;
+
+#ifdef CONFIG_PPC64
+ case SYSCALL: /* sc */
+ /*
+ * N.B. this uses knowledge about how the syscall
+ * entry code works. If that is changed, this will
+ * need to be changed also.
+ */
+ if (regs->gpr[0] == 0x1ebe &&
+ cpu_has_feature(CPU_FTR_REAL_LE)) {
+ regs->msr ^= MSR_LE;
+ goto instr_done;
+ }
+ regs->gpr[9] = regs->gpr[13];
+ regs->gpr[10] = MSR_KERNEL;
+ regs->gpr[11] = regs->nip + 4;
+ regs->gpr[12] = regs->msr & MSR_MASK;
+ regs->gpr[13] = (unsigned long) get_paca();
+ regs->nip = (unsigned long) &system_call_common;
+ regs->msr = MSR_KERNEL;
+ return 1;
+
+ case RFI:
+ return -1;
+#endif
+ }
+ return 0;
+
+ ldst_done:
+ if (err)
+ return 0;
+ if (op.type & UPDATE)
+ regs->gpr[op.update_reg] = op.ea;
+
+ instr_done:
+ regs->nip = truncate_if_32bit(regs->msr, regs->nip + 4);
+ return 1;
}
diff --git a/arch/powerpc/lib/string.S b/arch/powerpc/lib/string.S
index 1b5a0a09d609..c80fb49ce607 100644
--- a/arch/powerpc/lib/string.S
+++ b/arch/powerpc/lib/string.S
@@ -93,6 +93,7 @@ _GLOBAL(strlen)
subf r3,r3,r4
blr
+#ifdef CONFIG_PPC32
_GLOBAL(memcmp)
PPC_LCMPI 0,r5,0
beq- 2f
@@ -106,6 +107,7 @@ _GLOBAL(memcmp)
blr
2: li r3,0
blr
+#endif
_GLOBAL(memchr)
PPC_LCMPI 0,r5,0
generated by cgit v1.2.3 (git 2.39.0) at 2025-03-03 08:01:47 +0300