arm: Use builtins for ffs/fls

Since ARMv5, the clz instruction allows for efficient implementation of
ffs/fls with builtins. Until ARMv7 (with Thumb-2), this instruction is
only available in ARM mode. LTO makes it difficult to force specific
functions to be in ARM mode, as it is effectively a form of very
aggressive inlining. To work around this, fls/ffs are implemented in
assembly for ARMv5 and ARMv6 when compiling U-Boot in Thumb mode.
Overall, this saves around 75 bytes per call.

This code is synced with v5.15 of the Linux kernel.

Signed-off-by: Sean Anderson <sean.anderson@seco.com>
Reviewed-by: Tom Rini <trini@konsulko.com>

4 files changed, 64 insertions, 0 deletions

diff --git a/include/asm-generic/bitops/builtin-__ffs.h b/include/asm-generic/bitops/builtin-__ffs.h
new file mode 100644
index 00000000000..87024da44d1
--- /dev/null
+++ b/include/asm-generic/bitops/builtin-__ffs.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_BITOPS_BUILTIN___FFS_H_
+#define _ASM_GENERIC_BITOPS_BUILTIN___FFS_H_
+
+/**
+ * __ffs - find first bit in word.
+ * @word: The word to search
+ *
+ * Undefined if no bit exists, so code should check against 0 first.
+ */
+static __always_inline unsigned long __ffs(unsigned long word)
+{
+	return __builtin_ctzl(word);
+}
+
+#endif
diff --git a/include/asm-generic/bitops/builtin-__fls.h b/include/asm-generic/bitops/builtin-__fls.h
new file mode 100644
index 00000000000..43a5aa9afbd
--- /dev/null
+++ b/include/asm-generic/bitops/builtin-__fls.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_BITOPS_BUILTIN___FLS_H_
+#define _ASM_GENERIC_BITOPS_BUILTIN___FLS_H_
+
+/**
+ * __fls - find last (most-significant) set bit in a long word
+ * @word: the word to search
+ *
+ * Undefined if no set bit exists, so code should check against 0 first.
+ */
+static __always_inline unsigned long __fls(unsigned long word)
+{
+	return (sizeof(word) * 8) - 1 - __builtin_clzl(word);
+}
+
+#endif
diff --git a/include/asm-generic/bitops/builtin-ffs.h b/include/asm-generic/bitops/builtin-ffs.h
new file mode 100644
index 00000000000..7b129329046
--- /dev/null
+++ b/include/asm-generic/bitops/builtin-ffs.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_BITOPS_BUILTIN_FFS_H_
+#define _ASM_GENERIC_BITOPS_BUILTIN_FFS_H_
+
+/**
+ * ffs - find first bit set
+ * @x: the word to search
+ *
+ * This is defined the same way as
+ * the libc and compiler builtin ffs routines, therefore
+ * differs in spirit from ffz (man ffs).
+ */
+#define ffs(x) __builtin_ffs(x)
+
+#endif
diff --git a/include/asm-generic/bitops/builtin-fls.h b/include/asm-generic/bitops/builtin-fls.h
new file mode 100644
index 00000000000..c8455cc2884
--- /dev/null
+++ b/include/asm-generic/bitops/builtin-fls.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_BITOPS_BUILTIN_FLS_H_
+#define _ASM_GENERIC_BITOPS_BUILTIN_FLS_H_
+
+/**
+ * fls - find last (most-significant) bit set
+ * @x: the word to search
+ *
+ * This is defined the same way as ffs.
+ * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
+ */
+static __always_inline int fls(unsigned int x)
+{
+	return x ? sizeof(x) * 8 - __builtin_clz(x) : 0;
+}
+
+#endif