2 files changed, 109 insertions, 0 deletions

diff --git a/arch/arm/include/asm/neon.h b/arch/arm/include/asm/neon.h
new file mode 100644
index 000000000000..8f730fe70093
--- /dev/null
+++ b/arch/arm/include/asm/neon.h
@@ -0,0 +1,36 @@
+/*
+ * linux/arch/arm/include/asm/neon.h
+ *
+ * Copyright (C) 2013 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * 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.
+ */
+
+#include <asm/hwcap.h>
+
+#define cpu_has_neon()          (!!(elf_hwcap & HWCAP_NEON))
+
+#ifdef __ARM_NEON__
+
+/*
+ * If you are affected by the BUILD_BUG below, it probably means that you are
+ * using NEON code /and/ calling the kernel_neon_begin() function from the same
+ * compilation unit. To prevent issues that may arise from GCC reordering or
+ * generating(1) NEON instructions outside of these begin/end functions, the
+ * only supported way of using NEON code in the kernel is by isolating it in a
+ * separate compilation unit, and calling it from another unit from inside a
+ * kernel_neon_begin/kernel_neon_end pair.
+ *
+ * (1) Current GCC (4.7) might generate NEON instructions at O3 level if
+ *     -mpfu=neon is set.
+ */
+
+#define kernel_neon_begin() \
+        BUILD_BUG_ON_MSG(1, "kernel_neon_begin() called from NEON code")
+
+#else
+void kernel_neon_begin(void);
+#endif
+void kernel_neon_end(void);
diff --git a/arch/arm/include/asm/xor.h b/arch/arm/include/asm/xor.h
index 7604673dc427..4ffb26d4cad8 100644
--- a/arch/arm/include/asm/xor.h
+++ b/arch/arm/include/asm/xor.h
@@ -7,7 +7,10 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+#include <linux/hardirq.h>
 #include <asm-generic/xor.h>
+#include <asm/hwcap.h>
+#include <asm/neon.h>
 
 #define __XOR(a1, a2) a1 ^= a2
 
@@ -138,4 +141,74 @@ static struct xor_block_template xor_block_arm4regs = {
                 xor_speed(&xor_block_arm4regs); \
                 xor_speed(&xor_block_8regs);    \
                 xor_speed(&xor_block_32regs);   \
+                NEON_TEMPLATES;                 \
         } while (0)
+
+#ifdef CONFIG_KERNEL_MODE_NEON
+
+extern struct xor_block_template const xor_block_neon_inner;
+
+static void
+xor_neon_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+        if (in_interrupt()) {
+                xor_arm4regs_2(bytes, p1, p2);
+        } else {
+                kernel_neon_begin();
+                xor_block_neon_inner.do_2(bytes, p1, p2);
+                kernel_neon_end();
+        }
+}
+
+static void
+xor_neon_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+                unsigned long *p3)
+{
+        if (in_interrupt()) {
+                xor_arm4regs_3(bytes, p1, p2, p3);
+        } else {
+                kernel_neon_begin();
+                xor_block_neon_inner.do_3(bytes, p1, p2, p3);
+                kernel_neon_end();
+        }
+}
+
+static void
+xor_neon_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+                unsigned long *p3, unsigned long *p4)
+{
+        if (in_interrupt()) {
+                xor_arm4regs_4(bytes, p1, p2, p3, p4);
+        } else {
+                kernel_neon_begin();
+                xor_block_neon_inner.do_4(bytes, p1, p2, p3, p4);
+                kernel_neon_end();
+        }
+}
+
+static void
+xor_neon_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+                unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+        if (in_interrupt()) {
+                xor_arm4regs_5(bytes, p1, p2, p3, p4, p5);
+        } else {
+                kernel_neon_begin();
+                xor_block_neon_inner.do_5(bytes, p1, p2, p3, p4, p5);
+                kernel_neon_end();
+        }
+}
+
+static struct xor_block_template xor_block_neon = {
+        .name   = "neon",
+        .do_2   = xor_neon_2,
+        .do_3   = xor_neon_3,
+        .do_4   = xor_neon_4,
+        .do_5   = xor_neon_5
+};
+
+#define NEON_TEMPLATES  \
+        do { if (cpu_has_neon()) xor_speed(&xor_block_neon); } while (0)
+#else
+#define NEON_TEMPLATES
+#endif