The patch titled
Subject: ARM: Implement memset32 & memset64
has been added to the -mm tree. Its filename is
arm-implement-memset32-memset64.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/arm-implement-memset32-memset64.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/arm-implement-memset32-memset64.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Matthew Wilcox <mawilcox@xxxxxxxxxxxxx>
Subject: ARM: Implement memset32 & memset64
Reuse the existing optimised memset implementation to implement an
optimised memset32 and memset64.
Link: http://lkml.kernel.org/r/20170720184539.31609-5-willy@xxxxxxxxxxxxx
Signed-off-by: Matthew Wilcox <mawilcox@xxxxxxxxxxxxx>
Reviewed-by: Russell King <rmk+kernel@xxxxxxxxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: "James E.J. Bottomley" <jejb@xxxxxxxxxxxxxxxxxx>
Cc: "Martin K. Petersen" <martin.petersen@xxxxxxxxxx>
Cc: David Miller <davem@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxx>
Cc: Ivan Kokshaysky <ink@xxxxxxxxxxxxxxxxxxxx>
Cc: Matt Turner <mattst88@xxxxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Cc: Ralf Baechle <ralf@xxxxxxxxxxxxxx>
Cc: Richard Henderson <rth@xxxxxxxxxxx>
Cc: Sam Ravnborg <sam@xxxxxxxxxxxx>
Cc: Sergey Senozhatsky <sergey.senozhatsky@xxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
arch/arm/include/asm/string.h | 14 ++++++++++++++
arch/arm/kernel/armksyms.c | 2 ++
arch/arm/lib/memset.S | 24 ++++++++++++++++++------
3 files changed, 34 insertions(+), 6 deletions(-)
diff -puN arch/arm/include/asm/string.h~arm-implement-memset32-memset64 arch/arm/include/asm/string.h
--- a/arch/arm/include/asm/string.h~arm-implement-memset32-memset64
+++ a/arch/arm/include/asm/string.h
@@ -24,6 +24,20 @@ extern void * memchr(const void *, int,
#define __HAVE_ARCH_MEMSET
extern void * memset(void *, int, __kernel_size_t);
+#define __HAVE_ARCH_MEMSET32
+extern void *__memset32(uint32_t *, uint32_t v, __kernel_size_t);
+static inline void *memset32(uint32_t *p, uint32_t v, __kernel_size_t n)
+{
+ return __memset32(p, v, n * 4);
+}
+
+#define __HAVE_ARCH_MEMSET64
+extern void *__memset64(uint64_t *, uint32_t low, __kernel_size_t, uint32_t hi);
+static inline void *memset64(uint64_t *p, uint64_t v, __kernel_size_t n)
+{
+ return __memset64(p, v, n * 8, v >> 32);
+}
+
extern void __memzero(void *ptr, __kernel_size_t n);
#define memset(p,v,n) \
diff -puN arch/arm/kernel/armksyms.c~arm-implement-memset32-memset64 arch/arm/kernel/armksyms.c
--- a/arch/arm/kernel/armksyms.c~arm-implement-memset32-memset64
+++ a/arch/arm/kernel/armksyms.c
@@ -87,6 +87,8 @@ EXPORT_SYMBOL(__raw_writesl);
EXPORT_SYMBOL(strchr);
EXPORT_SYMBOL(strrchr);
EXPORT_SYMBOL(memset);
+EXPORT_SYMBOL(__memset32);
+EXPORT_SYMBOL(__memset64);
EXPORT_SYMBOL(memcpy);
EXPORT_SYMBOL(memmove);
EXPORT_SYMBOL(memchr);
diff -puN arch/arm/lib/memset.S~arm-implement-memset32-memset64 arch/arm/lib/memset.S
--- a/arch/arm/lib/memset.S~arm-implement-memset32-memset64
+++ a/arch/arm/lib/memset.S
@@ -28,7 +28,7 @@ UNWIND( .fnstart )
1: orr r1, r1, r1, lsl #8
orr r1, r1, r1, lsl #16
mov r3, r1
- cmp r2, #16
+7: cmp r2, #16
blt 4f
#if ! CALGN(1)+0
@@ -41,7 +41,7 @@ UNWIND( .fnend )
UNWIND( .fnstart )
UNWIND( .save {r8, lr} )
mov r8, r1
- mov lr, r1
+ mov lr, r3
2: subs r2, r2, #64
stmgeia ip!, {r1, r3, r8, lr} @ 64 bytes at a time.
@@ -73,11 +73,11 @@ UNWIND( .fnend )
UNWIND( .fnstart )
UNWIND( .save {r4-r8, lr} )
mov r4, r1
- mov r5, r1
+ mov r5, r3
mov r6, r1
- mov r7, r1
+ mov r7, r3
mov r8, r1
- mov lr, r1
+ mov lr, r3
cmp r2, #96
tstgt ip, #31
@@ -114,7 +114,7 @@ UNWIND( .fnstart )
tst r2, #4
strne r1, [ip], #4
/*
- * When we get here, we've got less than 4 bytes to zero. We
+ * When we get here, we've got less than 4 bytes to set. We
* may have an unaligned pointer as well.
*/
5: tst r2, #2
@@ -135,3 +135,15 @@ UNWIND( .fnstart )
UNWIND( .fnend )
ENDPROC(memset)
ENDPROC(mmioset)
+
+ENTRY(__memset32)
+UNWIND( .fnstart )
+ mov r3, r1 @ copy r1 to r3 and fall into memset64
+UNWIND( .fnend )
+ENDPROC(__memset32)
+ENTRY(__memset64)
+UNWIND( .fnstart )
+ mov ip, r0 @ preserve r0 as return value
+ b 7b @ jump into the middle of memset
+UNWIND( .fnend )
+ENDPROC(__memset64)
_
Patches currently in -mm which might be from mawilcox@xxxxxxxxxxxxx are
add-multibyte-memset-functions.patch
add-testcases-for-memset16-32-64.patch
x86-implement-memset16-memset32-memset64.patch
arm-implement-memset32-memset64.patch
alpha-add-support-for-memset16.patch
zram-convert-to-using-memset_l.patch
sym53c8xx_2-convert-to-use-memset32.patch
vga-optimise-console-scrolling.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
