Merge git://git.kernel.org/pub/scm/linux/kernel/git/cmetcalf/linux-tile

* git://git.kernel.org/pub/scm/linux/kernel/git/cmetcalf/linux-tile:
  arch/tile: check kmalloc() result
  arch/tile: catch up on various minor cleanups.
  arch/tile: avoid erroneous error return for PTRACE_POKEUSR.
  tile: set ARCH_KMALLOC_MINALIGN
  tile: remove homegrown L1_CACHE_ALIGN macro
  arch/tile: Miscellaneous cleanup changes.
  arch/tile: Split the icache flush code off to a generic <arch> header.
  arch/tile: Fix bug in support for atomic64_xx() ops.
  arch/tile: Shrink the tile-opcode files considerably.
  arch/tile: Add driver to enable access to the user dynamic network.
  arch/tile: Enable more sophisticated IRQ model for 32-bit chips.
  Move list types from <linux/list.h> to <linux/types.h>.
  Add wait4() back to the set of <asm-generic/unistd.h> syscalls.
  Revert adding some arch-specific signal syscalls to <linux/syscalls.h>.
  arch/tile: Do not use GFP_KERNEL for dma_alloc_coherent(). Feedback from fujita.tomonori@lab.ntt.co.jp.
  arch/tile: core support for Tilera 32-bit chips.
  Fix up the "generic" unistd.h ABI to be more useful.

1 files changed, 66 insertions, 0 deletions

diff --git a/arch/tile/lib/strchr_32.c b/arch/tile/lib/strchr_32.c
new file mode 100644
index 0000000..c94e6f7
--- /dev/null
+++ b/arch/tile/lib/strchr_32.c
@@ -0,0 +1,66 @@
+/*
+ * Copyright 2010 Tilera Corporation. All Rights Reserved.
+ *
+ *   This program is free software; you can redistribute it and/or
+ *   modify it under the terms of the GNU General Public License
+ *   as published by the Free Software Foundation, version 2.
+ *
+ *   This program is distributed in the hope that it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ *   NON INFRINGEMENT.  See the GNU General Public License for
+ *   more details.
+ */
+
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/module.h>
+
+#undef strchr
+
+char *strchr(const char *s, int c)
+{
+	int z, g;
+
+	/* Get an aligned pointer. */
+	const uintptr_t s_int = (uintptr_t) s;
+	const uint32_t *p = (const uint32_t *)(s_int & -4);
+
+	/* Create four copies of the byte for which we are looking. */
+	const uint32_t goal = 0x01010101 * (uint8_t) c;
+
+	/* Read the first aligned word, but force bytes before the string to
+	 * match neither zero nor goal (we make sure the high bit of each
+	 * byte is 1, and the low 7 bits are all the opposite of the goal
+	 * byte).
+	 *
+	 * Note that this shift count expression works because we know shift
+	 * counts are taken mod 32.
+	 */
+	const uint32_t before_mask = (1 << (s_int << 3)) - 1;
+	uint32_t v = (*p | before_mask) ^ (goal & __insn_shrib(before_mask, 1));
+
+	uint32_t zero_matches, goal_matches;
+	while (1) {
+		/* Look for a terminating '\0'. */
+		zero_matches = __insn_seqb(v, 0);
+
+		/* Look for the goal byte. */
+		goal_matches = __insn_seqb(v, goal);
+
+		if (__builtin_expect(zero_matches | goal_matches, 0))
+			break;
+
+		v = *++p;
+	}
+
+	z = __insn_ctz(zero_matches);
+	g = __insn_ctz(goal_matches);
+
+	/* If we found c before '\0' we got a match. Note that if c == '\0'
+	 * then g == z, and we correctly return the address of the '\0'
+	 * rather than NULL.
+	 */
+	return (g <= z) ? ((char *)p) + (g >> 3) : NULL;
+}
+EXPORT_SYMBOL(strchr);