[PATCH 1/3] ARM: pass -march=armv7-a when building NEON files with clang

Subsystems: arm port, library code, the rest

STALE3826d

3 messages, 1 author, 2016-02-08 · open the first message on its own page

[PATCH 1/3] ARM: pass -march=armv7-a when building NEON files with clang

From: Arnd Bergmann <arnd@arndb.de>
Date: 2016-02-08 14:27:27

clang ignores the -mfpu=neon flag when building with -march=armv6:

In file included from lib/raid6/neon1.c:27:
clang/3.8.0/include/arm_neon.h:28:2: error: "NEON support not enabled"

There is no real need to build the file with -march=armv6 in a
multi-CPU enabled kernel, as nothing in here will ever get called
on an ARMv6 CPU. Adding -march=armv7 doesn't hurt and can only
improve the code quality.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/lib/Makefile | 2 +-
 lib/raid6/Makefile    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index 6c7a5b715584..5f6c7eb62cc3 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile

@@ -39,7 +39,7 @@ $(obj)/csumpartialcopy.o:	$(obj)/csumpartialcopygeneric.S
 $(obj)/csumpartialcopyuser.o:	$(obj)/csumpartialcopygeneric.S
 
 ifeq ($(CONFIG_KERNEL_MODE_NEON),y)
-  NEON_FLAGS			:= -mfloat-abi=softfp -mfpu=neon
+  NEON_FLAGS			:= -mfloat-abi=softfp -mfpu=neon -march=armv7-a
   CFLAGS_xor-neon.o		+= $(NEON_FLAGS)
   obj-$(CONFIG_XOR_BLOCKS)	+= xor-neon.o
 endif

diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile
index 3b10a48fa040..4ef3e800fb39 100644
--- a/lib/raid6/Makefile
+++ b/lib/raid6/Makefile

@@ -23,7 +23,7 @@ endif
 ifeq ($(CONFIG_KERNEL_MODE_NEON),y)
 NEON_FLAGS := -ffreestanding
 ifeq ($(ARCH),arm)
-NEON_FLAGS += -mfloat-abi=softfp -mfpu=neon
+NEON_FLAGS += -mfloat-abi=softfp -mfpu=neon -march=armv7-a
 endif
 ifeq ($(ARCH),arm64)
 CFLAGS_REMOVE_neon1.o += -mgeneral-regs-only

-- 
2.7.0

[PATCH 2/3] ARM: fix copypage-*.c building with clang

From: Arnd Bergmann <arnd@arndb.de>
Date: 2016-02-08 14:27:52

clang does not allow inline assembly in __naked functions to
have any register parameters and throws an error:

arch/arm/mm/copypage-v4wb.c:47:9: error: parameter references not allowed in naked functions
        : "r" (kto), "r" (kfrom), "I" (PAGE_SIZE / 64));

Fortunately, all of these functions are trivial to convert to
using the registers directly.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/mm/copypage-feroceon.c |  4 ++--
 arch/arm/mm/copypage-v4mc.c     | 26 +++++++++++++-------------
 arch/arm/mm/copypage-v4wb.c     |  4 ++--
 arch/arm/mm/copypage-v4wt.c     |  4 ++--
 arch/arm/mm/copypage-xsc3.c     |  4 ++--
 arch/arm/mm/copypage-xscale.c   |  4 ++--
 6 files changed, 23 insertions(+), 23 deletions(-)

diff --git a/arch/arm/mm/copypage-feroceon.c b/arch/arm/mm/copypage-feroceon.c
index 49ee0c1a7209..e69bf2f15f32 100644
--- a/arch/arm/mm/copypage-feroceon.c
+++ b/arch/arm/mm/copypage-feroceon.c

@@ -18,7 +18,7 @@ feroceon_copy_user_page(void *kto, const void *kfrom)
 {
 	asm("\
 	stmfd	sp!, {r4-r9, lr}		\n\
-	mov	ip, %2				\n\
+	mov	ip, %0				\n\
 1:	mov	lr, r1				\n\
 	ldmia	r1!, {r2 - r9}			\n\
 	pld	[lr, #32]			\n\

@@ -64,7 +64,7 @@ feroceon_copy_user_page(void *kto, const void *kfrom)
 	mcr	p15, 0, ip, c7, c10, 4		@ drain WB\n\
 	ldmfd	sp!, {r4-r9, pc}"
 	:
-	: "r" (kto), "r" (kfrom), "I" (PAGE_SIZE));
+	: "I" (PAGE_SIZE));
 }
 
 void feroceon_copy_user_highpage(struct page *to, struct page *from,

diff --git a/arch/arm/mm/copypage-v4mc.c b/arch/arm/mm/copypage-v4mc.c
index 1267e64133b9..ea89722c00db 100644
--- a/arch/arm/mm/copypage-v4mc.c
+++ b/arch/arm/mm/copypage-v4mc.c

@@ -45,23 +45,23 @@ mc_copy_user_page(void *from, void *to)
 {
 	asm volatile(
 	"stmfd	sp!, {r4, lr}			@ 2\n\
-	mov	r4, %2				@ 1\n\
-	ldmia	%0!, {r2, r3, ip, lr}		@ 4\n\
-1:	mcr	p15, 0, %1, c7, c6, 1		@ 1   invalidate D line\n\
-	stmia	%1!, {r2, r3, ip, lr}		@ 4\n\
-	ldmia	%0!, {r2, r3, ip, lr}		@ 4+1\n\
-	stmia	%1!, {r2, r3, ip, lr}		@ 4\n\
-	ldmia	%0!, {r2, r3, ip, lr}		@ 4\n\
-	mcr	p15, 0, %1, c7, c6, 1		@ 1   invalidate D line\n\
-	stmia	%1!, {r2, r3, ip, lr}		@ 4\n\
-	ldmia	%0!, {r2, r3, ip, lr}		@ 4\n\
+	mov	r4, %0				@ 1\n\
+	ldmia	r0!, {r2, r3, ip, lr}		@ 4\n\
+1:	mcr	p15, 0, r1, c7, c6, 1		@ 1   invalidate D line\n\
+	stmia	r1!, {r2, r3, ip, lr}		@ 4\n\
+	ldmia	r0!, {r2, r3, ip, lr}		@ 4+1\n\
+	stmia	r1!, {r2, r3, ip, lr}		@ 4\n\
+	ldmia	r0!, {r2, r3, ip, lr}		@ 4\n\
+	mcr	p15, 0, r1, c7, c6, 1		@ 1   invalidate D line\n\
+	stmia	r1!, {r2, r3, ip, lr}		@ 4\n\
+	ldmia	r0!, {r2, r3, ip, lr}		@ 4\n\
 	subs	r4, r4, #1			@ 1\n\
-	stmia	%1!, {r2, r3, ip, lr}		@ 4\n\
-	ldmneia	%0!, {r2, r3, ip, lr}		@ 4\n\
+	stmia	r1!, {r2, r3, ip, lr}		@ 4\n\
+	ldmneia	r0!, {r2, r3, ip, lr}		@ 4\n\
 	bne	1b				@ 1\n\
 	ldmfd	sp!, {r4, pc}			@ 3"
 	:
-	: "r" (from), "r" (to), "I" (PAGE_SIZE / 64));
+	: "I" (PAGE_SIZE / 64));
 }
 
 void v4_mc_copy_user_highpage(struct page *to, struct page *from,

diff --git a/arch/arm/mm/copypage-v4wb.c b/arch/arm/mm/copypage-v4wb.c
index 067d0fdd630c..7ea9cf07bd5c 100644
--- a/arch/arm/mm/copypage-v4wb.c
+++ b/arch/arm/mm/copypage-v4wb.c

@@ -27,7 +27,7 @@ v4wb_copy_user_page(void *kto, const void *kfrom)
 {
 	asm("\
 	stmfd	sp!, {r4, lr}			@ 2\n\
-	mov	r2, %2				@ 1\n\
+	mov	r2, %0				@ 1\n\
 	ldmia	r1!, {r3, r4, ip, lr}		@ 4\n\
 1:	mcr	p15, 0, r0, c7, c6, 1		@ 1   invalidate D line\n\
 	stmia	r0!, {r3, r4, ip, lr}		@ 4\n\

@@ -44,7 +44,7 @@ v4wb_copy_user_page(void *kto, const void *kfrom)
 	mcr	p15, 0, r1, c7, c10, 4		@ 1   drain WB\n\
 	ldmfd	 sp!, {r4, pc}			@ 3"
 	:
-	: "r" (kto), "r" (kfrom), "I" (PAGE_SIZE / 64));
+	: "I" (PAGE_SIZE / 64));
 }
 
 void v4wb_copy_user_highpage(struct page *to, struct page *from,

diff --git a/arch/arm/mm/copypage-v4wt.c b/arch/arm/mm/copypage-v4wt.c
index b85c5da2e510..c742ab24efd6 100644
--- a/arch/arm/mm/copypage-v4wt.c
+++ b/arch/arm/mm/copypage-v4wt.c

@@ -25,7 +25,7 @@ v4wt_copy_user_page(void *kto, const void *kfrom)
 {
 	asm("\
 	stmfd	sp!, {r4, lr}			@ 2\n\
-	mov	r2, %2				@ 1\n\
+	mov	r2, %0				@ 1\n\
 	ldmia	r1!, {r3, r4, ip, lr}		@ 4\n\
 1:	stmia	r0!, {r3, r4, ip, lr}		@ 4\n\
 	ldmia	r1!, {r3, r4, ip, lr}		@ 4+1\n\

@@ -40,7 +40,7 @@ v4wt_copy_user_page(void *kto, const void *kfrom)
 	mcr	p15, 0, r2, c7, c7, 0		@ flush ID cache\n\
 	ldmfd	sp!, {r4, pc}			@ 3"
 	:
-	: "r" (kto), "r" (kfrom), "I" (PAGE_SIZE / 64));
+	: "I" (PAGE_SIZE / 64));
 }
 
 void v4wt_copy_user_highpage(struct page *to, struct page *from,

diff --git a/arch/arm/mm/copypage-xsc3.c b/arch/arm/mm/copypage-xsc3.c
index 03a2042aced5..17e4e11c4612 100644
--- a/arch/arm/mm/copypage-xsc3.c
+++ b/arch/arm/mm/copypage-xsc3.c

@@ -34,7 +34,7 @@ xsc3_mc_copy_user_page(void *kto, const void *kfrom)
 {
 	asm("\
 	stmfd	sp!, {r4, r5, lr}		\n\
-	mov	lr, %2				\n\
+	mov	lr, %0				\n\
 						\n\
 	pld	[r1, #0]			\n\
 	pld	[r1, #32]			\n\

@@ -67,7 +67,7 @@ xsc3_mc_copy_user_page(void *kto, const void *kfrom)
 						\n\
 	ldmfd	sp!, {r4, r5, pc}"
 	:
-	: "r" (kto), "r" (kfrom), "I" (PAGE_SIZE / 64 - 1));
+	: "I" (PAGE_SIZE / 64 - 1));
 }
 
 void xsc3_mc_copy_user_highpage(struct page *to, struct page *from,

diff --git a/arch/arm/mm/copypage-xscale.c b/arch/arm/mm/copypage-xscale.c
index 0fb85025344d..1034b4ce80cc 100644
--- a/arch/arm/mm/copypage-xscale.c
+++ b/arch/arm/mm/copypage-xscale.c

@@ -45,7 +45,7 @@ mc_copy_user_page(void *from, void *to)
 	 */
 	asm volatile(
 	"stmfd	sp!, {r4, r5, lr}		\n\
-	mov	lr, %2				\n\
+	mov	lr, %0				\n\
 	pld	[r0, #0]			\n\
 	pld	[r0, #32]			\n\
 	pld	[r1, #0]			\n\

@@ -81,7 +81,7 @@ mc_copy_user_page(void *from, void *to)
 	beq	2b				\n\
 	ldmfd	sp!, {r4, r5, pc}		"
 	:
-	: "r" (from), "r" (to), "I" (PAGE_SIZE / 64 - 1));
+	: "I" (PAGE_SIZE / 64 - 1));
 }
 
 void xscale_mc_copy_user_highpage(struct page *to, struct page *from,

-- 
2.7.0

[PATCH 3/3] ARM: kprobes: use "I" constraint for inline assembly offsets

From: Arnd Bergmann <arnd@arndb.de>
Date: 2016-02-08 14:27:57

build-testing with clang showed that the "J" constraint does not take
positive arguments on clang when building in for Thumb-2:

core.c:540:3: error: invalid operand for inline asm constraint 'J'

This has been reported as llvm bug https://llvm.org/bugs/show_bug.cgi?id=26061

However, looking at the source code in depth, I found that the
kernel is also wrong, and it should not use "J" at all, but should
use "I" to pass an immediate argument to the inline assembly when that
is used as an offset to an 'ldr' instruction rather than the 'sub'
argument.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/probes/kprobes/core.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c
index a4ec240ee7ba..4b34b40ca917 100644
--- a/arch/arm/probes/kprobes/core.c
+++ b/arch/arm/probes/kprobes/core.c

@@ -570,10 +570,10 @@ void __kprobes jprobe_return(void)
 		:
 		: "r" (kcb->jprobe_saved_regs.ARM_sp),
 		  "I" (sizeof(struct pt_regs) * 2),
-		  "J" (offsetof(struct pt_regs, ARM_sp)),
-		  "J" (offsetof(struct pt_regs, ARM_pc)),
-		  "J" (offsetof(struct pt_regs, ARM_cpsr)),
-		  "J" (offsetof(struct pt_regs, ARM_lr))
+		  "I" (offsetof(struct pt_regs, ARM_sp)),
+		  "I" (offsetof(struct pt_regs, ARM_pc)),
+		  "I" (offsetof(struct pt_regs, ARM_cpsr)),
+		  "I" (offsetof(struct pt_regs, ARM_lr))
 		: "memory", "cc");
 }

-- 
2.7.0

`h`	back out one level
`j`	next message in thread
`k`	previous message in thread
`l`	drill in
`Esc`	close help / fold thread tree
`?`	toggle this help