summaryrefslogtreecommitdiffstats
path: root/arch/mips/lib/memset.S
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2013-05-10 16:48:05 +0200
committerLinus Torvalds <torvalds@linux-foundation.org>2013-05-10 16:48:05 +0200
commitdaf799cca8abbf7f3e253ecf1d41d244070773d7 (patch)
tree6fb27ff60b820ae0eeb906c8a5d8d7f93f89cd8b /arch/mips/lib/memset.S
parentMerge tag 'arc-v3.10-rc1-part2' of git://git.kernel.org/pub/scm/linux/kernel/... (diff)
parentMerge branch 'mti-next' of git://git.linux-mips.org/pub/scm/sjhill/linux-sjhi... (diff)
downloadlinux-daf799cca8abbf7f3e253ecf1d41d244070773d7.tar.xz
linux-daf799cca8abbf7f3e253ecf1d41d244070773d7.zip
Merge branch 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus
Pull MIPS updates from Ralf Baechle: - More work on DT support for various platforms - Various fixes that were to late to make it straight into 3.9 - Improved platform support, in particular the Netlogic XLR and BCM63xx, and the SEAD3 and Malta eval boards. - Support for several Ralink SOC families. - Complete support for the microMIPS ASE which basically reencodes the existing MIPS32/MIPS64 ISA to use non-constant size instructions. - Some fallout from LTO work which remove old cruft and will generally make the MIPS kernel easier to maintain and resistant to compiler optimization, even in absence of LTO. - KVM support. While MIPS has announced hardware virtualization extensions this KVM extension uses trap and emulate mode for virtualization of MIPS32. More KVM work to add support for VZ hardware virtualizaiton extensions and MIPS64 will probably already be merged for 3.11. Most of this has been sitting in -next for a long time. All defconfigs have been build or run time tested except three for which fixes are being sent by other maintainers. Semantic conflict with kvm updates done as per Ralf * 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus: (118 commits) MIPS: Add new GIC clockevent driver. MIPS: Formatting clean-ups for clocksources. MIPS: Refactor GIC clocksource code. MIPS: Move 'gic_frequency' to common location. MIPS: Move 'gic_present' to common location. MIPS: MIPS16e: Add unaligned access support. MIPS: MIPS16e: Support handling of delay slots. MIPS: MIPS16e: Add instruction formats. MIPS: microMIPS: Optimise 'strnlen' core library function. MIPS: microMIPS: Optimise 'strlen' core library function. MIPS: microMIPS: Optimise 'strncpy' core library function. MIPS: microMIPS: Optimise 'memset' core library function. MIPS: microMIPS: Add configuration option for microMIPS kernel. MIPS: microMIPS: Disable LL/SC and fix linker bug. MIPS: microMIPS: Add vdso support. MIPS: microMIPS: Add unaligned access support. MIPS: microMIPS: Support handling of delay slots. MIPS: microMIPS: Add support for exception handling. MIPS: microMIPS: Floating point support. MIPS: microMIPS: Fix macro naming in micro-assembler. ...
Diffstat (limited to 'arch/mips/lib/memset.S')
-rw-r--r--arch/mips/lib/memset.S84
1 files changed, 54 insertions, 30 deletions
diff --git a/arch/mips/lib/memset.S b/arch/mips/lib/memset.S
index 053d3b0b0317..0580194e7402 100644
--- a/arch/mips/lib/memset.S
+++ b/arch/mips/lib/memset.S
@@ -5,7 +5,8 @@
*
* Copyright (C) 1998, 1999, 2000 by Ralf Baechle
* Copyright (C) 1999, 2000 Silicon Graphics, Inc.
- * Copyright (C) 2007 Maciej W. Rozycki
+ * Copyright (C) 2007 by Maciej W. Rozycki
+ * Copyright (C) 2011, 2012 MIPS Technologies, Inc.
*/
#include <asm/asm.h>
#include <asm/asm-offsets.h>
@@ -19,6 +20,20 @@
#define LONG_S_R sdr
#endif
+#ifdef CONFIG_CPU_MICROMIPS
+#define STORSIZE (LONGSIZE * 2)
+#define STORMASK (STORSIZE - 1)
+#define FILL64RG t8
+#define FILLPTRG t7
+#undef LONG_S
+#define LONG_S LONG_SP
+#else
+#define STORSIZE LONGSIZE
+#define STORMASK LONGMASK
+#define FILL64RG a1
+#define FILLPTRG t0
+#endif
+
#define EX(insn,reg,addr,handler) \
9: insn reg, addr; \
.section __ex_table,"a"; \
@@ -26,23 +41,25 @@
.previous
.macro f_fill64 dst, offset, val, fixup
- EX(LONG_S, \val, (\offset + 0 * LONGSIZE)(\dst), \fixup)
- EX(LONG_S, \val, (\offset + 1 * LONGSIZE)(\dst), \fixup)
- EX(LONG_S, \val, (\offset + 2 * LONGSIZE)(\dst), \fixup)
- EX(LONG_S, \val, (\offset + 3 * LONGSIZE)(\dst), \fixup)
- EX(LONG_S, \val, (\offset + 4 * LONGSIZE)(\dst), \fixup)
- EX(LONG_S, \val, (\offset + 5 * LONGSIZE)(\dst), \fixup)
- EX(LONG_S, \val, (\offset + 6 * LONGSIZE)(\dst), \fixup)
- EX(LONG_S, \val, (\offset + 7 * LONGSIZE)(\dst), \fixup)
-#if LONGSIZE == 4
- EX(LONG_S, \val, (\offset + 8 * LONGSIZE)(\dst), \fixup)
- EX(LONG_S, \val, (\offset + 9 * LONGSIZE)(\dst), \fixup)
- EX(LONG_S, \val, (\offset + 10 * LONGSIZE)(\dst), \fixup)
- EX(LONG_S, \val, (\offset + 11 * LONGSIZE)(\dst), \fixup)
- EX(LONG_S, \val, (\offset + 12 * LONGSIZE)(\dst), \fixup)
- EX(LONG_S, \val, (\offset + 13 * LONGSIZE)(\dst), \fixup)
- EX(LONG_S, \val, (\offset + 14 * LONGSIZE)(\dst), \fixup)
- EX(LONG_S, \val, (\offset + 15 * LONGSIZE)(\dst), \fixup)
+ EX(LONG_S, \val, (\offset + 0 * STORSIZE)(\dst), \fixup)
+ EX(LONG_S, \val, (\offset + 1 * STORSIZE)(\dst), \fixup)
+ EX(LONG_S, \val, (\offset + 2 * STORSIZE)(\dst), \fixup)
+ EX(LONG_S, \val, (\offset + 3 * STORSIZE)(\dst), \fixup)
+#if ((defined(CONFIG_CPU_MICROMIPS) && (LONGSIZE == 4)) || !defined(CONFIG_CPU_MICROMIPS))
+ EX(LONG_S, \val, (\offset + 4 * STORSIZE)(\dst), \fixup)
+ EX(LONG_S, \val, (\offset + 5 * STORSIZE)(\dst), \fixup)
+ EX(LONG_S, \val, (\offset + 6 * STORSIZE)(\dst), \fixup)
+ EX(LONG_S, \val, (\offset + 7 * STORSIZE)(\dst), \fixup)
+#endif
+#if (!defined(CONFIG_CPU_MICROMIPS) && (LONGSIZE == 4))
+ EX(LONG_S, \val, (\offset + 8 * STORSIZE)(\dst), \fixup)
+ EX(LONG_S, \val, (\offset + 9 * STORSIZE)(\dst), \fixup)
+ EX(LONG_S, \val, (\offset + 10 * STORSIZE)(\dst), \fixup)
+ EX(LONG_S, \val, (\offset + 11 * STORSIZE)(\dst), \fixup)
+ EX(LONG_S, \val, (\offset + 12 * STORSIZE)(\dst), \fixup)
+ EX(LONG_S, \val, (\offset + 13 * STORSIZE)(\dst), \fixup)
+ EX(LONG_S, \val, (\offset + 14 * STORSIZE)(\dst), \fixup)
+ EX(LONG_S, \val, (\offset + 15 * STORSIZE)(\dst), \fixup)
#endif
.endm
@@ -71,16 +88,20 @@ LEAF(memset)
1:
FEXPORT(__bzero)
- sltiu t0, a2, LONGSIZE /* very small region? */
+ sltiu t0, a2, STORSIZE /* very small region? */
bnez t0, .Lsmall_memset
- andi t0, a0, LONGMASK /* aligned? */
+ andi t0, a0, STORMASK /* aligned? */
+#ifdef CONFIG_CPU_MICROMIPS
+ move t8, a1 /* used by 'swp' instruction */
+ move t9, a1
+#endif
#ifndef CONFIG_CPU_DADDI_WORKAROUNDS
beqz t0, 1f
- PTR_SUBU t0, LONGSIZE /* alignment in bytes */
+ PTR_SUBU t0, STORSIZE /* alignment in bytes */
#else
.set noat
- li AT, LONGSIZE
+ li AT, STORSIZE
beqz t0, 1f
PTR_SUBU t0, AT /* alignment in bytes */
.set at
@@ -99,24 +120,27 @@ FEXPORT(__bzero)
1: ori t1, a2, 0x3f /* # of full blocks */
xori t1, 0x3f
beqz t1, .Lmemset_partial /* no block to fill */
- andi t0, a2, 0x40-LONGSIZE
+ andi t0, a2, 0x40-STORSIZE
PTR_ADDU t1, a0 /* end address */
.set reorder
1: PTR_ADDIU a0, 64
R10KCBARRIER(0(ra))
- f_fill64 a0, -64, a1, .Lfwd_fixup
+ f_fill64 a0, -64, FILL64RG, .Lfwd_fixup
bne t1, a0, 1b
.set noreorder
.Lmemset_partial:
R10KCBARRIER(0(ra))
PTR_LA t1, 2f /* where to start */
+#ifdef CONFIG_CPU_MICROMIPS
+ LONG_SRL t7, t0, 1
+#endif
#if LONGSIZE == 4
- PTR_SUBU t1, t0
+ PTR_SUBU t1, FILLPTRG
#else
.set noat
- LONG_SRL AT, t0, 1
+ LONG_SRL AT, FILLPTRG, 1
PTR_SUBU t1, AT
.set at
#endif
@@ -126,9 +150,9 @@ FEXPORT(__bzero)
.set push
.set noreorder
.set nomacro
- f_fill64 a0, -64, a1, .Lpartial_fixup /* ... but first do longs ... */
+ f_fill64 a0, -64, FILL64RG, .Lpartial_fixup /* ... but first do longs ... */
2: .set pop
- andi a2, LONGMASK /* At most one long to go */
+ andi a2, STORMASK /* At most one long to go */
beqz a2, 1f
PTR_ADDU a0, a2 /* What's left */
@@ -169,7 +193,7 @@ FEXPORT(__bzero)
.Lpartial_fixup:
PTR_L t0, TI_TASK($28)
- andi a2, LONGMASK
+ andi a2, STORMASK
LONG_L t0, THREAD_BUADDR(t0)
LONG_ADDU a2, t1
jr ra
@@ -177,4 +201,4 @@ FEXPORT(__bzero)
.Llast_fixup:
jr ra
- andi v1, a2, LONGMASK
+ andi v1, a2, STORMASK