ARM: sfi_breg assembler macro

5 files changed, 71 insertions, 44 deletions

diff --git a/ports/sysdeps/arm/armv6/rawmemchr.S b/ports/sysdeps/arm/armv6/rawmemchr.S
index 7877bcf6d6..b5e4a16f03 100644
--- a/ports/sysdeps/arm/armv6/rawmemchr.S
+++ b/ports/sysdeps/arm/armv6/rawmemchr.S
@@ -25,7 +25,8 @@ ENTRY (__rawmemchr)
 	@ r0 = start of string
 	@ r1 = character to match
 	@ returns a pointer to the match, which must be present.
-	ldrb	r2, [r0]		@ load first byte asap
+	sfi_breg r0, \
+	ldrb	r2, [\B]		@ load first byte asap
 
 	@ To cater to long strings, we want to search through a few
 	@ characters until we reach an aligned pointer.  To cater to
@@ -41,7 +42,8 @@ ENTRY (__rawmemchr)
 	bxeq	lr
 
 	@ Loop until we find ...
-1:	ldrb	r2, [r0, #1]!
+1:	sfi_breg r0, \
+	ldrb	r2, [\B, #1]!
 	subs	r3, r3, #1		@ ... the alignment point
 	it	ne
 	cmpne	r2, r1			@ ... or C
@@ -54,15 +56,16 @@ ENTRY (__rawmemchr)
 	add	r0, r0, #1
 
 	@ So now we're aligned.
-	ldrd	r2, r3, [r0], #8
+	sfi_breg r0, \
+	ldrd	r2, r3, [\B], #8
 	orr	r1, r1, r1, lsl #8	@ Replicate C to all bytes
 #ifdef ARCH_HAS_T2
 	movw	ip, #0x0101
-	pld	[r0, #64]
+	sfi_pld	r0, #64
 	movt	ip, #0x0101
 #else
 	ldr	ip, =0x01010101
-	pld	[r0, #64]
+	sfi_pld	r0, #64
 #endif
 	orr	r1, r1, r1, lsl #16
 
@@ -74,10 +77,11 @@ ENTRY (__rawmemchr)
 	eor	r3, r3, r1
 	uqsub8	r2, ip, r2		@ Find C
 	uqsub8	r3, ip, r3
-	pld	[r0, #128]
+	sfi_pld	r0, #128
 	orrs	r3, r3, r2		@ Test both words for found
 	it	eq
-	ldrdeq	r2, r3, [r0], #8
+	sfi_breg r0, \
+	ldrdeq	r2, r3, [\B], #8
 	beq	2b
 
 	@ Found something.  Disambiguate between first and second words.
diff --git a/ports/sysdeps/arm/armv6/strchr.S b/ports/sysdeps/arm/armv6/strchr.S
index c856283d53..936c2be666 100644
--- a/ports/sysdeps/arm/armv6/strchr.S
+++ b/ports/sysdeps/arm/armv6/strchr.S
@@ -25,7 +25,8 @@ ENTRY (strchr)
 	@ r0 = start of string
 	@ r1 = character to match
 	@ returns NULL for no match, or a pointer to the match
-	ldrb	r2, [r0]		@ load the first byte asap
+	sfi_breg r0, \
+	ldrb	r2, [\B]		@ load the first byte asap
 	uxtb	r1, r1
 
 	@ To cater to long strings, we want to search through a few
@@ -42,7 +43,8 @@ ENTRY (strchr)
 	beq	99f
 
 	@ Loop until we find ...
-1:	ldrb	r2, [r0, #1]!
+1:	sfi_breg r0, \
+	ldrb	r2, [\B, #1]!
 	subs	r3, r3, #1		@ ... the aligment point
 	it	ne
 	cmpne	r2, r1			@ ... or the character
@@ -65,15 +67,16 @@ ENTRY (strchr)
 	cfi_rel_offset (r6, 8)
 	cfi_rel_offset (r7, 12)
 
-	ldrd	r2, r3, [r0], #8
+	sfi_breg r0, \
+	ldrd	r2, r3, [\B], #8
 	orr	r1, r1, r1, lsl #8	@ Replicate C to all bytes
 #ifdef ARCH_HAS_T2
 	movw	ip, #0x0101
-	pld	[r0, #64]
+	sfi_pld	r0, #64
 	movt	ip, #0x0101
 #else
 	ldr	ip, =0x01010101
-	pld	[r0, #64]
+	sfi_pld	r0, #64
 #endif
 	orr	r1, r1, r1, lsl #16
 
@@ -87,13 +90,14 @@ ENTRY (strchr)
 	uqsub8	r5, ip, r3
 	eor	r7, r3, r1
 	uqsub8	r6, ip, r6		@ Find C
-	pld	[r0, #128]		@ Prefetch 2 lines ahead
+	sfi_pld	r0, #128		@ Prefetch 2 lines ahead
 	uqsub8	r7, ip, r7
 	orr	r4, r4, r6		@ Combine found for EOS and C
 	orr	r5, r5, r7
 	orrs	r6, r4, r5		@ Combine the two words
 	it	eq
-	ldrdeq	r2, r3, [r0], #8
+	sfi_breg r0, \
+	ldrdeq	r2, r3, [\B], #8
 	beq	2b
 
 	@ Found something.  Disambiguate between first and second words.
diff --git a/ports/sysdeps/arm/armv6/strcpy.S b/ports/sysdeps/arm/armv6/strcpy.S
index 41f6443319..cd13ff7ecf 100644
--- a/ports/sysdeps/arm/armv6/strcpy.S
+++ b/ports/sysdeps/arm/armv6/strcpy.S
@@ -44,8 +44,8 @@ ENTRY (strcpy)
 	@ Signal strcpy with DEST in IP.
 	mov	ip, r0
 0:
-	pld	[r0]
-	pld	[r1]
+	sfi_pld	r0
+	sfi_pld	r1
 
 	@ To cater to long strings, we want 8 byte alignment in the source.
 	@ To cater to small strings, we don't want to start that right away.
@@ -54,9 +54,11 @@ ENTRY (strcpy)
 	rsb	r3, r3, #16
 
 	@ Loop until we find ...
-1:	ldrb	r2, [r1], #1
+1:	sfi_breg r1, \
+	ldrb	r2, [\B], #1
 	subs	r3, r3, #1		@ ... the alignment point
-	strb	r2, [r0], #1
+	sfi_breg r0, \
+	strb	r2, [\B], #1
 	it	ne
 	cmpne	r2, #0			@ ... or EOS
 	bne	1b
@@ -66,9 +68,10 @@ ENTRY (strcpy)
 	beq	.Lreturn
 
 	@ Load the next two words asap
-	ldrd	r2, r3, [r1], #8
-	pld	[r0, #64]
-	pld	[r1, #64]
+	sfi_breg r1, \
+	ldrd	r2, r3, [\B], #8
+	sfi_pld	r0, #64
+	sfi_pld	r1, #64
 
 	@ For longer strings, we actaully need a stack frame.
 	push	{ r4, r5, r6, r7 }
@@ -96,15 +99,18 @@ ENTRY (strcpy)
 	.balign	16
 2:	uqsub8	r4, r7, r2		@ Find EOS
 	uqsub8	r5, r7, r3
-	pld	[r1, #128]
+	sfi_pld	r1, #128
 	cmp	r4, #0			@ EOS in first word?
-	pld	[r0, #128]
+	sfi_pld	r0, #128
 	bne	3f
-	str	r2, [r0], #4
+	sfi_breg r0, \
+	str	r2, [\B], #4
 	cmp	r5, #0			@ EOS in second word?
 	bne	4f
-	str	r3, [r0], #4
-	ldrd	r2, r3, [r1], #8
+	sfi_breg r0, \
+	str	r3, [\B], #4
+	sfi_breg r1, \
+	ldrd	r2, r3, [\B], #8
 	b	2b
 
 3:	sub	r1, r1, #4		@ backup to first word
@@ -114,9 +120,11 @@ ENTRY (strcpy)
 	@ Note that we generally back up and re-read source bytes,
 	@ but we'll not re-write dest bytes.
 .Lbyte_loop:
-	ldrb	r2, [r1], #1
+	sfi_breg r1, \
+	ldrb	r2, [\B], #1
 	cmp	r2, #0
-	strb	r2, [r0], #1
+	sfi_breg r0, \
+	strb	r2, [\B], #1
 	bne	.Lbyte_loop
 
 	pop	{ r4, r5, r6, r7 }
@@ -161,7 +169,8 @@ ENTRY (strcpy)
 	@ Store a few bytes from the first word.
 	@ At the same time we align r0 and shift out bytes from r2.
 .rept	4-\unalign
-	strb	r2, [r0], #1
+	sfi_breg r0, \
+	strb	r2, [\B], #1
 	lsr	r2, r2, #8
 .endr
 #ifdef __ARMEB__
@@ -176,20 +185,23 @@ ENTRY (strcpy)
 	orr	r2, r2, r3, lsh_gt #(\unalign*8)
 	@ Save leftover bytes from the two words
 	lsh_ls	r6, r3, #((4-\unalign)*8)
-	str	r2, [r0], #4
+	sfi_breg r0, \
+	str	r2, [\B], #4
 	@ The "real" start of the unaligned copy loop.
-	ldrd	r2, r3, [r1], #8	@ Load 8 more bytes
+	sfi_breg r1, \
+	ldrd	r2, r3, [\B], #8	@ Load 8 more bytes
 	uqsub8	r4, r7, r2		@ Find EOS
-	pld	[r1, #128]
+	sfi_pld	r1, #128
 	uqsub8	r5, r7, r3
-	pld	[r0, #128]
+	sfi_pld	r0, #128
 	mvns	r4, r4			@ EOS in first word?
 	bne	3f
 	@ Combine the leftover and the first word
 	orr	r6, r6, r2, lsh_gt #(\unalign*8)
 	@ Discard used bytes from the first word.
 	lsh_ls	r2, r2, #((4-\unalign)*8)
-	str	r6, [r0], #4
+	sfi_breg r0, \
+	str	r6, [\B], #4
 	b	1b
 	@ Found EOS in one of the words; adjust backward
 3:	sub	r1, r1, #4
@@ -200,7 +212,8 @@ ENTRY (strcpy)
 	rev	r2, r2
 #endif
 .rept	\unalign
-	strb	r2, [r0], #1
+	sfi_breg r0, \
+	strb	r2, [\B], #1
 	lsr	r2, r2, #8
 .endr
 	b	.Lbyte_loop
diff --git a/ports/sysdeps/arm/armv6/strlen.S b/ports/sysdeps/arm/armv6/strlen.S
index a53d41418a..59ff6b5d93 100644
--- a/ports/sysdeps/arm/armv6/strlen.S
+++ b/ports/sysdeps/arm/armv6/strlen.S
@@ -23,7 +23,8 @@
 
 ENTRY (strlen)
 	@ r0 = start of string
-	ldrb	r2, [r0]		@ load the first byte asap
+	sfi_breg r0, \
+	ldrb	r2, [\B]		@ load the first byte asap
 
 	@ To cater to long strings, we want to search through a few
 	@ characters until we reach an aligned pointer.  To cater to
@@ -38,7 +39,8 @@ ENTRY (strlen)
 	beq	99f
 
 	@ Loop until we find ...
-1:	ldrb	r2, [r0, #1]!
+1:	sfi_breg r0, \
+	ldrb	r2, [\B, #1]!
 	subs	r3, r3, #1		@ ... the aligment point
 	it	ne
 	cmpne	r2, #0			@ ... or EOS
@@ -50,14 +52,15 @@ ENTRY (strlen)
 	add	r0, r0, #1
 
 	@ So now we're aligned.
-	ldrd	r2, r3, [r0], #8
+	sfi_breg r0, \
+	ldrd	r2, r3, [\B], #8
 #ifdef ARCH_HAS_T2
 	movw	ip, #0x0101
-	pld	[r0, #64]
+	sfi_pld	r0, #64
 	movt	ip, #0x0101
 #else
 	ldr	ip, =0x01010101
-	pld	[r0, #64]
+	sfi_pld	r0, #64
 #endif
 
 	@ Loop searching for EOS, 8 bytes at a time.
@@ -67,10 +70,11 @@ ENTRY (strlen)
 	.balign	16
 2:	uqsub8	r2, ip, r2		@ Find EOS
 	uqsub8	r3, ip, r3
-	pld	[r0, #128]		@ Prefetch 2 lines ahead
+	sfi_pld	r0, #128		@ Prefetch 2 lines ahead
 	orrs	r3, r3, r2		@ Combine the two words
 	it	eq
-	ldrdeq	r2, r3, [r0], #8
+	sfi_breg r0, \
+	ldrdeq	r2, r3, [\B], #8
 	beq	2b
 
 	@ Found something.  Disambiguate between first and second words.
diff --git a/ports/sysdeps/arm/armv6/strrchr.S b/ports/sysdeps/arm/armv6/strrchr.S
index ddd4f7fc06..e40df90a72 100644
--- a/ports/sysdeps/arm/armv6/strrchr.S
+++ b/ports/sysdeps/arm/armv6/strrchr.S
@@ -33,7 +33,8 @@ ENTRY (strrchr)
 	@ Loop a few times until we're aligned.
 	tst	r3, #7
 	beq	2f
-1:	ldrb	r2, [r3], #1
+1:	sfi_breg r3, \
+	ldrb	r2, [\B], #1
 	cmp	r2, r1			@ Find the character
 	it	eq
 	subeq	r0, r3, #1
@@ -64,7 +65,8 @@ ENTRY (strrchr)
 	@ Loop searching for EOS and C, 8 bytes at a time.
 	@ Any time we find a match in a word, we copy the address of
 	@ the word to r0, and the found bits to r2.
-3:	ldrd	r4, r5, [r3], #8
+3:	sfi_breg r3, \
+	ldrd	r4, r5, [\B], #8
 	@ Subtracting (unsigned saturating) from 1 means result of 1 for
 	@ any byte that was originally zero and 0 otherwise.  Therefore
 	@ we consider the lsb of each byte the "found" bit.