summaryrefslogtreecommitdiff
path: root/lib/raid6/neon.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2013-09-05 18:07:32 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2013-09-05 18:07:32 -0700
commit2e032852245b3dcfe5461d7353e34eb6da095ccf (patch)
tree69f9fdf03b54d76bb539096e0ec96e91ea8216b1 /lib/raid6/neon.c
parent356f9e74ffaafd11741589a9aa21d6c9d2721417 (diff)
parent141b97433d77e39ac3ac111a7b3852192035259c (diff)
Merge branch 'for-linus' of git://git.linaro.org/people/rmk/linux-arm
Pull ARM updates from Russell King: "This set includes adding support for Neon acceleration of RAID6 XOR code from Ard Biesheuvel, cache flushing and barrier updates from Will Deacon, and a cleanup to the ARM debug code which reduces the amount of code by about 500 lines. A few other cleanups, such as constifying the machine descriptors which already shouldn't be written to, cleaning up the printing of the L2 cache size" * 'for-linus' of git://git.linaro.org/people/rmk/linux-arm: (55 commits) ARM: 7826/1: debug: support debug ll on hisilicon soc ARM: 7830/1: delay: don't bother reporting bogomips in /proc/cpuinfo ARM: 7829/1: Add ".text.unlikely" and ".text.hot" to arm unwind tables ARM: 7828/1: ARMv7-M: implement restart routine common to all v7-M machines ARM: 7827/1: highbank: fix debug uart virtual address for LPAE ARM: 7823/1: errata: workaround Cortex-A15 erratum 773022 ARM: 7806/1: allow DEBUG_UNCOMPRESS for Tegra ARM: 7793/1: debug: use generic option for ep93xx PL10x debug port ARM: debug: move SPEAr debug to generic PL01x code ARM: debug: move davinci debug to generic 8250 code ARM: debug: move keystone debug to generic 8250 code ARM: debug: remove DEBUG_ROCKCHIP_UART ARM: debug: provide generic option choices for 8250 and PL01x ports ARM: debug: move PL01X debug include into arch/arm/include/debug/ ARM: debug: provide PL01x debug uart phys/virt address configuration options ARM: debug: add support for word accesses to debug/8250.S ARM: debug: move 8250 debug include into arch/arm/include/debug/ ARM: debug: provide 8250 debug uart phys/virt address configuration options ARM: debug: provide 8250 debug uart register shift configuration option ARM: debug: provide 8250 debug uart flow control configuration option ...
Diffstat (limited to 'lib/raid6/neon.c')
-rw-r--r--lib/raid6/neon.c58
1 files changed, 58 insertions, 0 deletions
diff --git a/lib/raid6/neon.c b/lib/raid6/neon.c
new file mode 100644
index 000000000000..36ad4705df1a
--- /dev/null
+++ b/lib/raid6/neon.c
@@ -0,0 +1,58 @@
+/*
+ * linux/lib/raid6/neon.c - RAID6 syndrome calculation using ARM NEON intrinsics
+ *
+ * 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 <linux/raid/pq.h>
+
+#ifdef __KERNEL__
+#include <asm/neon.h>
+#else
+#define kernel_neon_begin()
+#define kernel_neon_end()
+#define cpu_has_neon() (1)
+#endif
+
+/*
+ * There are 2 reasons these wrappers are kept in a separate compilation unit
+ * from the actual implementations in neonN.c (generated from neon.uc by
+ * unroll.awk):
+ * - the actual implementations use NEON intrinsics, and the GCC support header
+ * (arm_neon.h) is not fully compatible (type wise) with the kernel;
+ * - the neonN.c files are compiled with -mfpu=neon and optimization enabled,
+ * and we have to make sure that we never use *any* NEON/VFP instructions
+ * outside a kernel_neon_begin()/kernel_neon_end() pair.
+ */
+
+#define RAID6_NEON_WRAPPER(_n) \
+ static void raid6_neon ## _n ## _gen_syndrome(int disks, \
+ size_t bytes, void **ptrs) \
+ { \
+ void raid6_neon ## _n ## _gen_syndrome_real(int, \
+ unsigned long, void**); \
+ kernel_neon_begin(); \
+ raid6_neon ## _n ## _gen_syndrome_real(disks, \
+ (unsigned long)bytes, ptrs); \
+ kernel_neon_end(); \
+ } \
+ struct raid6_calls const raid6_neonx ## _n = { \
+ raid6_neon ## _n ## _gen_syndrome, \
+ raid6_have_neon, \
+ "neonx" #_n, \
+ 0 \
+ }
+
+static int raid6_have_neon(void)
+{
+ return cpu_has_neon();
+}
+
+RAID6_NEON_WRAPPER(1);
+RAID6_NEON_WRAPPER(2);
+RAID6_NEON_WRAPPER(4);
+RAID6_NEON_WRAPPER(8);