summaryrefslogtreecommitdiffstats
path: root/arch/x86/include/asm/word-at-a-time.h
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-05-06 01:02:30 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-05-06 01:02:30 +0000
commit76cb841cb886eef6b3bee341a2266c76578724ad (patch)
treef5892e5ba6cc11949952a6ce4ecbe6d516d6ce58 /arch/x86/include/asm/word-at-a-time.h
parentInitial commit. (diff)
downloadlinux-76cb841cb886eef6b3bee341a2266c76578724ad.tar.xz
linux-76cb841cb886eef6b3bee341a2266c76578724ad.zip
Adding upstream version 4.19.249.upstream/4.19.249upstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'arch/x86/include/asm/word-at-a-time.h')
-rw-r--r--arch/x86/include/asm/word-at-a-time.h106
1 files changed, 106 insertions, 0 deletions
diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h
new file mode 100644
index 000000000..06006b035
--- /dev/null
+++ b/arch/x86/include/asm/word-at-a-time.h
@@ -0,0 +1,106 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_WORD_AT_A_TIME_H
+#define _ASM_WORD_AT_A_TIME_H
+
+#include <linux/kernel.h>
+
+/*
+ * This is largely generic for little-endian machines, but the
+ * optimal byte mask counting is probably going to be something
+ * that is architecture-specific. If you have a reliably fast
+ * bit count instruction, that might be better than the multiply
+ * and shift, for example.
+ */
+struct word_at_a_time {
+ const unsigned long one_bits, high_bits;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) }
+
+#ifdef CONFIG_64BIT
+
+/*
+ * Jan Achrenius on G+: microoptimized version of
+ * the simpler "(mask & ONEBYTES) * ONEBYTES >> 56"
+ * that works for the bytemasks without having to
+ * mask them first.
+ */
+static inline long count_masked_bytes(unsigned long mask)
+{
+ return mask*0x0001020304050608ul >> 56;
+}
+
+#else /* 32-bit case */
+
+/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */
+static inline long count_masked_bytes(long mask)
+{
+ /* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */
+ long a = (0x0ff0001+mask) >> 23;
+ /* Fix the 1 for 00 case */
+ return a & mask;
+}
+
+#endif
+
+/* Return nonzero if it has a zero */
+static inline unsigned long has_zero(unsigned long a, unsigned long *bits, const struct word_at_a_time *c)
+{
+ unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits;
+ *bits = mask;
+ return mask;
+}
+
+static inline unsigned long prep_zero_mask(unsigned long a, unsigned long bits, const struct word_at_a_time *c)
+{
+ return bits;
+}
+
+static inline unsigned long create_zero_mask(unsigned long bits)
+{
+ bits = (bits - 1) & ~bits;
+ return bits >> 7;
+}
+
+/* The mask we created is directly usable as a bytemask */
+#define zero_bytemask(mask) (mask)
+
+static inline unsigned long find_zero(unsigned long mask)
+{
+ return count_masked_bytes(mask);
+}
+
+/*
+ * Load an unaligned word from kernel space.
+ *
+ * In the (very unlikely) case of the word being a page-crosser
+ * and the next page not being mapped, take the exception and
+ * return zeroes in the non-existing part.
+ */
+static inline unsigned long load_unaligned_zeropad(const void *addr)
+{
+ unsigned long ret, dummy;
+
+ asm(
+ "1:\tmov %2,%0\n"
+ "2:\n"
+ ".section .fixup,\"ax\"\n"
+ "3:\t"
+ "lea %2,%1\n\t"
+ "and %3,%1\n\t"
+ "mov (%1),%0\n\t"
+ "leal %2,%%ecx\n\t"
+ "andl %4,%%ecx\n\t"
+ "shll $3,%%ecx\n\t"
+ "shr %%cl,%0\n\t"
+ "jmp 2b\n"
+ ".previous\n"
+ _ASM_EXTABLE(1b, 3b)
+ :"=&r" (ret),"=&c" (dummy)
+ :"m" (*(unsigned long *)addr),
+ "i" (-sizeof(unsigned long)),
+ "i" (sizeof(unsigned long)-1));
+ return ret;
+}
+
+#endif /* _ASM_WORD_AT_A_TIME_H */