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@infradead.org
Signed-off-by: Matthew Wilcox <mawilcox@microsoft.com>
Reviewed-by: Russell King <rmk+kernel@armlinux.org.uk>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: "James E.J. Bottomley" <jejb@linux.vnet.ibm.com>
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: David Miller <davem@davemloft.net>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Sam Ravnborg <sam@ravnborg.org>
Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 18 insertions, 6 deletions

diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S
index 3c65e3bd790f..ed6d35d9cdb5 100644
--- a/arch/arm/lib/memset.S
+++ b/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)