diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2013-03-02 07:58:56 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2013-03-02 07:58:56 -0800 |
commit | e23b62256a361611cbd45cd1456638f1a5106b5c (patch) | |
tree | 472968c961432a1d9d0c3634ca20433f1d9cd29b /arch/arc/lib/strchr-700.S | |
parent | aebb2afd5420c860b7fbc3882a323ef1247fbf16 (diff) | |
parent | 8ccfe6675fa974bd06d64f74d0fdee6a5267d2aa (diff) |
Merge tag 'arc-v3.9-rc1-late' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc
Pull new ARC architecture from Vineet Gupta:
"Initial ARC Linux port with some fixes on top for 3.9-rc1:
I would like to introduce the Linux port to ARC Processors (from
Synopsys) for 3.9-rc1. The patch-set has been discussed on the public
lists since Nov and has received a fair bit of review, specially from
Arnd, tglx, Al and other subsystem maintainers for DeviceTree, kgdb...
The arch bits are in arch/arc, some asm-generic changes (acked by
Arnd), a minor change to PARISC (acked by Helge).
The series is a touch bigger for a new port for 2 main reasons:
1. It enables a basic kernel in first sub-series and adds
ptrace/kgdb/.. later
2. Some of the fallout of review (DeviceTree support, multi-platform-
image support) were added on top of orig series, primarily to
record the revision history.
This updated pull request additionally contains
- fixes due to our GNU tools catching up with the new syscall/ptrace
ABI
- some (minor) cross-arch Kconfig updates."
* tag 'arc-v3.9-rc1-late' of git://git.kernel.org/pub/scm/linux/kernel/git/vgupta/arc: (82 commits)
ARC: split elf.h into uapi and export it for userspace
ARC: Fixup the current ABI version
ARC: gdbserver using regset interface possibly broken
ARC: Kconfig cleanup tracking cross-arch Kconfig pruning in merge window
ARC: make a copy of flat DT
ARC: [plat-arcfpga] DT arc-uart bindings change: "baud" => "current-speed"
ARC: Ensure CONFIG_VIRT_TO_BUS is not enabled
ARC: Fix pt_orig_r8 access
ARC: [3.9] Fallout of hlist iterator update
ARC: 64bit RTSC timestamp hardware issue
ARC: Don't fiddle with non-existent caches
ARC: Add self to MAINTAINERS
ARC: Provide a default serial.h for uart drivers needing BASE_BAUD
ARC: [plat-arcfpga] defconfig for fully loaded ARC Linux
ARC: [Review] Multi-platform image #8: platform registers SMP callbacks
ARC: [Review] Multi-platform image #7: SMP common code to use callbacks
ARC: [Review] Multi-platform image #6: cpu-to-dma-addr optional
ARC: [Review] Multi-platform image #5: NR_IRQS defined by ARC core
ARC: [Review] Multi-platform image #4: Isolate platform headers
ARC: [Review] Multi-platform image #3: switch to board callback
...
Diffstat (limited to 'arch/arc/lib/strchr-700.S')
-rw-r--r-- | arch/arc/lib/strchr-700.S | 123 |
1 files changed, 123 insertions, 0 deletions
diff --git a/arch/arc/lib/strchr-700.S b/arch/arc/lib/strchr-700.S new file mode 100644 index 00000000000..99c10475d47 --- /dev/null +++ b/arch/arc/lib/strchr-700.S @@ -0,0 +1,123 @@ +/* + * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com) + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +/* ARC700 has a relatively long pipeline and branch prediction, so we want + to avoid branches that are hard to predict. On the other hand, the + presence of the norm instruction makes it easier to operate on whole + words branch-free. */ + +#include <asm/linkage.h> + +ARC_ENTRY strchr + extb_s r1,r1 + asl r5,r1,8 + bmsk r2,r0,1 + or r5,r5,r1 + mov_s r3,0x01010101 + breq.d r2,r0,.Laligned + asl r4,r5,16 + sub_s r0,r0,r2 + asl r7,r2,3 + ld_s r2,[r0] +#ifdef __LITTLE_ENDIAN__ + asl r7,r3,r7 +#else + lsr r7,r3,r7 +#endif + or r5,r5,r4 + ror r4,r3 + sub r12,r2,r7 + bic_s r12,r12,r2 + and r12,r12,r4 + brne.d r12,0,.Lfound0_ua + xor r6,r2,r5 + ld.a r2,[r0,4] + sub r12,r6,r7 + bic r12,r12,r6 + and r7,r12,r4 + breq r7,0,.Loop ; For speed, we want this branch to be unaligned. + b .Lfound_char ; Likewise this one. +; /* We require this code address to be unaligned for speed... */ +.Laligned: + ld_s r2,[r0] + or r5,r5,r4 + ror r4,r3 +; /* ... so that this code address is aligned, for itself and ... */ +.Loop: + sub r12,r2,r3 + bic_s r12,r12,r2 + and r12,r12,r4 + brne.d r12,0,.Lfound0 + xor r6,r2,r5 + ld.a r2,[r0,4] + sub r12,r6,r3 + bic r12,r12,r6 + and r7,r12,r4 + breq r7,0,.Loop /* ... so that this branch is unaligned. */ + ; Found searched-for character. r0 has already advanced to next word. +#ifdef __LITTLE_ENDIAN__ +/* We only need the information about the first matching byte + (i.e. the least significant matching byte) to be exact, + hence there is no problem with carry effects. */ +.Lfound_char: + sub r3,r7,1 + bic r3,r3,r7 + norm r2,r3 + sub_s r0,r0,1 + asr_s r2,r2,3 + j.d [blink] + sub_s r0,r0,r2 + + .balign 4 +.Lfound0_ua: + mov r3,r7 +.Lfound0: + sub r3,r6,r3 + bic r3,r3,r6 + and r2,r3,r4 + or_s r12,r12,r2 + sub_s r3,r12,1 + bic_s r3,r3,r12 + norm r3,r3 + add_s r0,r0,3 + asr_s r12,r3,3 + asl.f 0,r2,r3 + sub_s r0,r0,r12 + j_s.d [blink] + mov.pl r0,0 +#else /* BIG ENDIAN */ +.Lfound_char: + lsr r7,r7,7 + + bic r2,r7,r6 + norm r2,r2 + sub_s r0,r0,4 + asr_s r2,r2,3 + j.d [blink] + add_s r0,r0,r2 + +.Lfound0_ua: + mov_s r3,r7 +.Lfound0: + asl_s r2,r2,7 + or r7,r6,r4 + bic_s r12,r12,r2 + sub r2,r7,r3 + or r2,r2,r6 + bic r12,r2,r12 + bic.f r3,r4,r12 + norm r3,r3 + + add.pl r3,r3,1 + asr_s r12,r3,3 + asl.f 0,r2,r3 + add_s r0,r0,r12 + j_s.d [blink] + mov.mi r0,0 +#endif /* ENDIAN */ +ARC_EXIT strchr |