Support ARMv7 architecture

new file mode 100644
index 0000000..1815766
@@ -0,0 +1,256 @@
+/*-
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2015 RehiveTech. All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of RehiveTech nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _RTE_ATOMIC_ARM_H_
+#define _RTE_ATOMIC_ARM_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "generic/rte_atomic.h"
+
+/**
+ * General memory barrier.
+ *
+ * Guarantees that the LOAD and STORE operations generated before the
+ * barrier occur before the LOAD and STORE operations generated after.
+ */
+#define	rte_mb()  __sync_synchronize()
+
+/**
+ * Write memory barrier.
+ *
+ * Guarantees that the STORE operations generated before the barrier
+ * occur before the STORE operations generated after.
+ */
+#define	rte_wmb() do { asm volatile ("dmb st" : : : "memory"); } while(0)
+
+/**
+ * Read memory barrier.
+ *
+ * Guarantees that the LOAD operations generated before the barrier
+ * occur before the LOAD operations generated after.
+ */
+#define	rte_rmb() __sync_synchronize()
+
+/*------------------------- 16 bit atomic operations -------------------------*/
+
+#ifndef RTE_FORCE_INTRINSICS
+static inline int
+rte_atomic16_cmpset(volatile uint16_t *dst, uint16_t exp, uint16_t src)
+{
+	return __atomic_compare_exchange(dst, &exp, &src, 0, __ATOMIC_ACQUIRE,
+		__ATOMIC_ACQUIRE) ? 1 : 0;
+}
+
+static inline int rte_atomic16_test_and_set(rte_atomic16_t *v)
+{
+	return rte_atomic16_cmpset((volatile uint16_t *)&v->cnt, 0, 1);
+}
+
+static inline void
+rte_atomic16_inc(rte_atomic16_t *v)
+{
+	__atomic_add_fetch(&v->cnt, 1, __ATOMIC_ACQUIRE);
+}
+
+static inline void
+rte_atomic16_dec(rte_atomic16_t *v)
+{
+	__atomic_sub_fetch(&v->cnt, 1, __ATOMIC_ACQUIRE);
+}
+
+static inline int rte_atomic16_inc_and_test(rte_atomic16_t *v)
+{
+	return (__atomic_add_fetch(&v->cnt, 1, __ATOMIC_ACQUIRE) == 0);
+}
+
+static inline int rte_atomic16_dec_and_test(rte_atomic16_t *v)
+{
+	return (__atomic_sub_fetch(&v->cnt, 1, __ATOMIC_ACQUIRE) == 0);
+}
+
+/*------------------------- 32 bit atomic operations -------------------------*/
+
+static inline int
+rte_atomic32_cmpset(volatile uint32_t *dst, uint32_t exp, uint32_t src)
+{
+	return __atomic_compare_exchange(dst, &exp, &src, 0, __ATOMIC_ACQUIRE,
+		__ATOMIC_ACQUIRE) ? 1 : 0;
+}
+
+static inline int rte_atomic32_test_and_set(rte_atomic32_t *v)
+{
+	return rte_atomic32_cmpset((volatile uint32_t *)&v->cnt, 0, 1);
+}
+
+static inline void
+rte_atomic32_inc(rte_atomic32_t *v)
+{
+	__atomic_add_fetch(&v->cnt, 1, __ATOMIC_ACQUIRE);
+}
+
+static inline void
+rte_atomic32_dec(rte_atomic32_t *v)
+{
+	__atomic_sub_fetch(&v->cnt, 1, __ATOMIC_ACQUIRE);
+}
+
+static inline int rte_atomic32_inc_and_test(rte_atomic32_t *v)
+{
+	return (__atomic_add_fetch(&v->cnt, 1, __ATOMIC_ACQUIRE) == 0);
+}
+
+static inline int rte_atomic32_dec_and_test(rte_atomic32_t *v)
+{
+	return (__atomic_sub_fetch(&v->cnt, 1, __ATOMIC_ACQUIRE) == 0);
+}
+
+/*------------------------- 64 bit atomic operations -------------------------*/
+
+static inline int
+rte_atomic64_cmpset(volatile uint64_t *dst, uint64_t exp, uint64_t src)
+{
+	return __atomic_compare_exchange(dst, &exp, &src, 0, __ATOMIC_ACQUIRE,
+		__ATOMIC_ACQUIRE) ? 1 : 0;
+}
+
+static inline void
+rte_atomic64_init(rte_atomic64_t *v)
+{
+	int success = 0;
+	uint64_t tmp;
+
+	while (success == 0) {
+		tmp = v->cnt;
+		success = rte_atomic64_cmpset((volatile uint64_t *)&v->cnt,
+		                              tmp, 0);
+	}
+}
+
+static inline int64_t
+rte_atomic64_read(rte_atomic64_t *v)
+{
+	int success = 0;
+	uint64_t tmp;
+
+	while (success == 0) {
+		tmp = v->cnt;
+		/* replace the value by itself */
+		success = rte_atomic64_cmpset((volatile uint64_t *) &v->cnt,
+		                              tmp, tmp);
+	}
+	return tmp;
+}
+
+static inline void
+rte_atomic64_set(rte_atomic64_t *v, int64_t new_value)
+{
+	int success = 0;
+	uint64_t tmp;
+
+	while (success == 0) {
+		tmp = v->cnt;
+		success = rte_atomic64_cmpset((volatile uint64_t *)&v->cnt,
+		                              tmp, new_value);
+	}
+}
+
+static inline void
+rte_atomic64_add(rte_atomic64_t *v, int64_t inc)
+{
+	__atomic_fetch_add(&v->cnt, inc, __ATOMIC_ACQUIRE);
+}
+
+static inline void
+rte_atomic64_sub(rte_atomic64_t *v, int64_t dec)
+{
+	__atomic_fetch_sub(&v->cnt, dec, __ATOMIC_ACQUIRE);
+}
+
+static inline void
+rte_atomic64_inc(rte_atomic64_t *v)
+{
+	__atomic_fetch_add(&v->cnt, 1, __ATOMIC_ACQUIRE);
+}
+
+static inline void
+rte_atomic64_dec(rte_atomic64_t *v)
+{
+	__atomic_fetch_sub(&v->cnt, 1, __ATOMIC_ACQUIRE);
+}
+
+static inline int64_t
+rte_atomic64_add_return(rte_atomic64_t *v, int64_t inc)
+{
+	return __atomic_add_fetch(&v->cnt, inc, __ATOMIC_ACQUIRE);
+}
+
+static inline int64_t
+rte_atomic64_sub_return(rte_atomic64_t *v, int64_t dec)
+{
+	return __atomic_sub_fetch(&v->cnt, dec, __ATOMIC_ACQUIRE);
+}
+
+static inline int rte_atomic64_inc_and_test(rte_atomic64_t *v)
+{
+	return (__atomic_add_fetch(&v->cnt, 1, __ATOMIC_ACQUIRE) == 0);
+}
+
+static inline int rte_atomic64_dec_and_test(rte_atomic64_t *v)
+{
+	return (__atomic_sub_fetch(&v->cnt, 1, __ATOMIC_ACQUIRE) == 0);
+}
+
+static inline int rte_atomic64_test_and_set(rte_atomic64_t *v)
+{
+	return rte_atomic64_cmpset((volatile uint64_t *)&v->cnt, 0, 1);
+}
+
+/**
+ * Atomically set a 64-bit counter to 0.
+ *
+ * @param v
+ *   A pointer to the atomic counter.
+ */
+static inline void rte_atomic64_clear(rte_atomic64_t *v)
+{
+	rte_atomic64_set(v, 0);
+}
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_ATOMIC_ARM_H_ */

new file mode 100644
index 0000000..04e7b87
@@ -0,0 +1,148 @@
+/*
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2015 RehiveTech. All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of RehiveTech nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _RTE_BYTEORDER_ARM_H_
+#define _RTE_BYTEORDER_ARM_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "generic/rte_byteorder.h"
+
+/*
+ * An architecture-optimized byte swap for a 16-bit value.
+ *
+ * Do not use this function directly. The preferred function is rte_bswap16().
+ */
+static inline uint16_t rte_arch_bswap16(uint16_t _x)
+{
+	register uint16_t x = _x;
+	asm volatile ("rev16 %[x1],%[x2]"
+		      : [x1] "=r" (x)
+		      : [x2] "r" (x)
+		      );
+	return x;
+}
+
+/*
+ * An architecture-optimized byte swap for a 32-bit value.
+ *
+ * Do not use this function directly. The preferred function is rte_bswap32().
+ */
+static inline uint32_t rte_arch_bswap32(uint32_t _x)
+{
+	register uint32_t x = _x;
+	asm volatile ("rev %[x1],%[x2]"
+		      : [x1] "=r" (x)
+		      : [x2] "r" (x)
+		      );
+	return x;
+}
+
+/*
+ * An architecture-optimized byte swap for a 64-bit value.
+ *
+  * Do not use this function directly. The preferred function is rte_bswap64().
+ */
+/* 64-bit mode */
+static inline uint64_t rte_arch_bswap64(uint64_t _x)
+{
+	return  __builtin_bswap64(_x);
+}
+
+#ifndef RTE_FORCE_INTRINSICS
+#define rte_bswap16(x) ((uint16_t)(__builtin_constant_p(x) ?		\
+				   rte_constant_bswap16(x) :		\
+				   rte_arch_bswap16(x)))
+
+#define rte_bswap32(x) ((uint32_t)(__builtin_constant_p(x) ?		\
+				   rte_constant_bswap32(x) :		\
+				   rte_arch_bswap32(x)))
+
+#define rte_bswap64(x) ((uint64_t)(__builtin_constant_p(x) ?		\
+				   rte_constant_bswap64(x) :		\
+				   rte_arch_bswap64(x)))
+#else
+/*
+ * __builtin_bswap16 is only available gcc 4.8 and upwards
+ */
+#if __GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ < 8)
+#define rte_bswap16(x) ((uint16_t)(__builtin_constant_p(x) ?		\
+				   rte_constant_bswap16(x) :		\
+				   rte_arch_bswap16(x)))
+#endif
+#endif
+
+/* ARM architecture is bi-endian (both big and little). */
+#if RTE_BYTE_ORDER == RTE_LITTLE_ENDIAN
+
+#define rte_cpu_to_le_16(x) (x)
+#define rte_cpu_to_le_32(x) (x)
+#define rte_cpu_to_le_64(x) (x)
+
+#define rte_cpu_to_be_16(x) rte_bswap16(x)
+#define rte_cpu_to_be_32(x) rte_bswap32(x)
+#define rte_cpu_to_be_64(x) rte_bswap64(x)
+
+#define rte_le_to_cpu_16(x) (x)
+#define rte_le_to_cpu_32(x) (x)
+#define rte_le_to_cpu_64(x) (x)
+
+#define rte_be_to_cpu_16(x) rte_bswap16(x)
+#define rte_be_to_cpu_32(x) rte_bswap32(x)
+#define rte_be_to_cpu_64(x) rte_bswap64(x)
+
+#else /* RTE_BIG_ENDIAN */
+
+#define rte_cpu_to_le_16(x) rte_bswap16(x)
+#define rte_cpu_to_le_32(x) rte_bswap32(x)
+#define rte_cpu_to_le_64(x) rte_bswap64(x)
+
+#define rte_cpu_to_be_16(x) (x)
+#define rte_cpu_to_be_32(x) (x)
+#define rte_cpu_to_be_64(x) (x)
+
+#define rte_le_to_cpu_16(x) rte_bswap16(x)
+#define rte_le_to_cpu_32(x) rte_bswap32(x)
+#define rte_le_to_cpu_64(x) rte_bswap64(x)
+
+#define rte_be_to_cpu_16(x) (x)
+#define rte_be_to_cpu_32(x) (x)
+#define rte_be_to_cpu_64(x) (x)
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_BYTEORDER_ARM_H_ */

new file mode 100644
index 0000000..ff66ae2
@@ -0,0 +1,85 @@
+/*
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2015 RehiveTech. All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of RehiveTech nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _RTE_CYCLES_ARM_H_
+#define _RTE_CYCLES_ARM_H_
+
+/* ARM v7 does not have suitable source of clock signals. The only clock counter
+   available in the core is 32 bit wide. Therefore it is unsuitable as the
+   counter overlaps every few seconds and probably is not accessible by
+   userspace programs. Therefore we use clock_gettime(CLOCK_MONOTONIC_RAW) to
+   simulate counter running at 1GHz.
+*/
+
+#include <time.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "generic/rte_cycles.h"
+
+/**
+ * Read the time base register.
+ *
+ * @return
+ *   The time base for this lcore.
+ */
+static inline uint64_t
+rte_rdtsc(void)
+{
+	struct timespec val;
+	uint64_t v;
+
+	while (clock_gettime(CLOCK_MONOTONIC_RAW, &val) != 0)
+		/* no body */;
+
+	v  = (uint64_t) val.tv_sec * 1000000000LL;
+	v += (uint64_t) val.tv_nsec;
+	return v;
+}
+
+static inline uint64_t
+rte_rdtsc_precise(void)
+{
+	rte_mb();
+	return rte_rdtsc();
+}
+
+static inline uint64_t
+rte_get_tsc_cycles(void) { return rte_rdtsc(); }
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_CYCLES_ARM_H_ */

index ff66ae2..5dcef25 100644
@@ -54,8 +54,14 @@ extern "C" {
  * @return
  *   The time base for this lcore.
  */
+#ifndef CONFIG_RTE_ARM_EAL_RDTSC_USE_PMU
+
+/**
+ * This call is easily portable to any ARM architecture, however,
+ * it may be damn slow and inprecise for some tasks.
+ */
 static inline uint64_t
-rte_rdtsc(void)
+__rte_rdtsc_syscall(void)
 {
 	struct timespec val;
 	uint64_t v;

@@ -67,6 +73,36 @@ rte_rdtsc(void)
 	v += (uint64_t) val.tv_nsec;
 	return v;
 }
+#define rte_rdtsc __rte_rdtsc_syscall
+
+#else
+
+/**
+ * This function requires to configure the PMCCNTR and enable
+ * userspace access to it:
+ *
+ *      asm volatile("mcr p15, 0, %0, c9, c14, 0" : : "r"(1));
+ *      asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r"(29));
+ *      asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r"(0x8000000f));
+ *
+ * which is possible only from the priviledged mode (kernel space).
+ */
+static inline uint64_t
+__rte_rdtsc_pmccntr(void)
+{
+	unsigned tsc;
+	uint64_t final_tsc;
+
+	/* Read PMCCNTR */
+	asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r"(tsc));
+	/* 1 tick = 64 clocks */
+	final_tsc = ((uint64_t)tsc) << 6;
+
+	return (uint64_t)final_tsc;
+}
+#define rte_rdtsc __rte_rdtsc_pmccntr
+
+#endif /* RTE_ARM_EAL_RDTSC_USE_PMU */
 
 static inline uint64_t
 rte_rdtsc_precise(void)

new file mode 100644
index 0000000..8d75fe6
@@ -0,0 +1,61 @@
+/*
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2015 RehiveTech. All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of RehiveTech nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _RTE_PREFETCH_ARM_H_
+#define _RTE_PREFETCH_ARM_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "generic/rte_prefetch.h"
+
+static inline void rte_prefetch0(const volatile void *p)
+{
+	asm volatile ("pld [%[p]]" : : [p] "r" (p));
+}
+
+static inline void rte_prefetch1(const volatile void *p)
+{
+	asm volatile ("pld [%[p]]" : : [p] "r" (p));
+}
+
+static inline void rte_prefetch2(const volatile void *p)
+{
+	asm volatile ("pld [%[p]]" : : [p] "r" (p));
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_PREFETCH_ARM_H_ */

new file mode 100644
index 0000000..cd5ab8b
@@ -0,0 +1,114 @@
+/*
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2015 RehiveTech. All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of RehiveTech nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _RTE_SPINLOCK_ARM_H_
+#define _RTE_SPINLOCK_ARM_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include <rte_common.h>
+#include "generic/rte_spinlock.h"
+
+/* Intrinsics are used to implement the spinlock on ARM architecture */
+
+#ifndef RTE_FORCE_INTRINSICS
+
+static inline void
+rte_spinlock_lock(rte_spinlock_t *sl)
+{
+	while (__sync_lock_test_and_set(&sl->locked, 1))
+		while (sl->locked)
+			rte_pause();
+}
+
+static inline void
+rte_spinlock_unlock(rte_spinlock_t *sl)
+{
+	__sync_lock_release(&sl->locked);
+}
+
+static inline int
+rte_spinlock_trylock(rte_spinlock_t *sl)
+{
+	return (__sync_lock_test_and_set(&sl->locked, 1) == 0);
+}
+
+#endif
+
+static inline int rte_tm_supported(void)
+{
+	return 0;
+}
+
+static inline void
+rte_spinlock_lock_tm(rte_spinlock_t *sl)
+{
+	rte_spinlock_lock(sl); /* fall-back */
+}
+
+static inline int
+rte_spinlock_trylock_tm(rte_spinlock_t *sl)
+{
+	return rte_spinlock_trylock(sl);
+}
+
+static inline void
+rte_spinlock_unlock_tm(rte_spinlock_t *sl)
+{
+	rte_spinlock_unlock(sl);
+}
+
+static inline void
+rte_spinlock_recursive_lock_tm(rte_spinlock_recursive_t *slr)
+{
+	rte_spinlock_recursive_lock(slr); /* fall-back */
+}
+
+static inline void
+rte_spinlock_recursive_unlock_tm(rte_spinlock_recursive_t *slr)
+{
+	rte_spinlock_recursive_unlock(slr);
+}
+
+static inline int
+rte_spinlock_recursive_trylock_tm(rte_spinlock_recursive_t *slr)
+{
+	return rte_spinlock_recursive_trylock(slr);
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_SPINLOCK_ARM_H_ */

new file mode 100644
index 0000000..ac885e9
@@ -0,0 +1,270 @@
+/*
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2015 RehiveTech. All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of RehiveTech nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _RTE_MEMCPY_ARM_H_
+#define _RTE_MEMCPY_ARM_H_
+
+#include <stdint.h>
+#include <string.h>
+/* ARM NEON Intrinsics are used to copy data */
+#include <arm_neon.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "generic/rte_memcpy.h"
+
+static inline void
+rte_mov16(uint8_t *dst, const uint8_t *src)
+{
+	vst1q_u8(dst, vld1q_u8(src));
+}
+
+static inline void
+rte_mov32(uint8_t *dst, const uint8_t *src)
+{
+	asm volatile ("vld1.8 {d0-d3}, [%[src]]\n\t"
+	              "vst1.8 {d0-d3}, [%[dst]]\n\t"
+	              : [src] "+r" (src), [dst] "+r" (dst)
+	              : : "memory", "d0", "d1", "d2", "d3");
+}
+
+static inline void
+rte_mov48(uint8_t *dst, const uint8_t *src)
+{
+	asm volatile ("vld1.8 {d0-d3}, [%[src]]!\n\t"
+	              "vld1.8 {d4-d5}, [%[src]]\n\t"
+	              "vst1.8 {d0-d3}, [%[dst]]!\n\t"
+	              "vst1.8 {d4-d5}, [%[dst]]\n\t"
+	              : [src] "+r" (src), [dst] "+r" (dst)
+	              : : "memory", "d0", "d1", "d2", "d3", "d4", "d5");
+}
+
+static inline void
+rte_mov64(uint8_t *dst, const uint8_t *src)
+{
+	asm volatile ("vld1.8 {d0-d3}, [%[src]]!\n\t"
+	              "vld1.8 {d4-d7}, [%[src]]\n\t"
+	              "vst1.8 {d0-d3}, [%[dst]]!\n\t"
+	              "vst1.8 {d4-d7}, [%[dst]]\n\t"
+	              : [src] "+r" (src), [dst] "+r" (dst)
+	              : : "memory", "d0", "d1", "d2", "d3", "d4", "d5", "d6", "d7");
+}
+
+static inline void
+rte_mov128(uint8_t *dst, const uint8_t *src)
+{
+	asm volatile ("pld [%[src], #64]" : : [src] "r" (src));
+	asm volatile ("vld1.8 {d0-d3},   [%[src]]!\n\t"
+	              "vld1.8 {d4-d7},   [%[src]]!\n\t"
+	              "vld1.8 {d8-d11},  [%[src]]!\n\t"
+	              "vld1.8 {d12-d15}, [%[src]]\n\t"
+	              "vst1.8 {d0-d3},   [%[dst]]!\n\t"
+	              "vst1.8 {d4-d7},   [%[dst]]!\n\t"
+	              "vst1.8 {d8-d11},  [%[dst]]!\n\t"
+	              "vst1.8 {d12-d15}, [%[dst]]\n\t"
+	              : [src] "+r" (src), [dst] "+r" (dst)
+	              : : "memory", "d0", "d1", "d2", "d3", "d4", "d5", "d6", "d7",
+	                  "d8", "d9", "d10", "d11", "d12", "d13", "d14", "d15");
+}
+
+static inline void
+rte_mov256(uint8_t *dst, const uint8_t *src)
+{
+	asm volatile ("pld [%[src], #64]" : : [src] "r" (src));
+	asm volatile ("pld [%[src], #128]" : : [src] "r" (src));
+	asm volatile ("pld [%[src], #192]" : : [src] "r" (src));
+	asm volatile ("pld [%[src], #256]" : : [src] "r" (src));
+	asm volatile ("pld [%[src], #320]" : : [src] "r" (src));
+	asm volatile ("pld [%[src], #384]" : : [src] "r" (src));
+	asm volatile ("pld [%[src], #448]" : : [src] "r" (src));
+	asm volatile ("vld1.8 {d0-d3},   [%[src]]!\n\t"
+	              "vld1.8 {d4-d7},   [%[src]]!\n\t"
+	              "vld1.8 {d8-d11},  [%[src]]!\n\t"
+	              "vld1.8 {d12-d15}, [%[src]]!\n\t"
+	              "vld1.8 {d16-d19}, [%[src]]!\n\t"
+	              "vld1.8 {d20-d23}, [%[src]]!\n\t"
+	              "vld1.8 {d24-d27}, [%[src]]!\n\t"
+	              "vld1.8 {d28-d31}, [%[src]]\n\t"
+	              "vst1.8 {d0-d3},   [%[dst]]!\n\t"
+	              "vst1.8 {d4-d7},   [%[dst]]!\n\t"
+	              "vst1.8 {d8-d11},  [%[dst]]!\n\t"
+	              "vst1.8 {d12-d15}, [%[dst]]!\n\t"
+	              "vst1.8 {d16-d19}, [%[dst]]!\n\t"
+	              "vst1.8 {d20-d23}, [%[dst]]!\n\t"
+	              "vst1.8 {d24-d27}, [%[dst]]!\n\t"
+	              "vst1.8 {d28-d31}, [%[dst]]!\n\t"
+	              : [src] "+r" (src), [dst] "+r" (dst)
+	              : : "memory", "d0", "d1", "d2", "d3", "d4", "d5", "d6", "d7",
+	                  "d8", "d9", "d10", "d11", "d12", "d13", "d14", "d15",
+	                  "d16", "d17", "d18", "d19", "d20", "d21", "d22", "d23",
+	                  "d24", "d25", "d26", "d27", "d28", "d29", "d30", "d31");
+}
+
+#define rte_memcpy(dst, src, n)              \
+	({ (__builtin_constant_p(n)) ?       \
+	memcpy((dst), (src), (n)) :          \
+	rte_memcpy_func((dst), (src), (n)); })
+
+static inline void *
+rte_memcpy_func(void *dst, const void *src, size_t n)
+{
+	void *ret = dst;
+
+	/* We can't copy < 16 bytes using XMM registers so do it manually. */
+	if (n < 16) {
+		if (n & 0x01) {
+			*(uint8_t *)dst = *(const uint8_t *)src;
+			dst = (uint8_t *)dst + 1;
+			src = (const uint8_t *)src + 1;
+		}
+		if (n & 0x02) {
+			*(uint16_t *)dst = *(const uint16_t *)src;
+			dst = (uint16_t *)dst + 1;
+			src = (const uint16_t *)src + 1;
+		}
+		if (n & 0x04) {
+			*(uint32_t *)dst = *(const uint32_t *)src;
+			dst = (uint32_t *)dst + 1;
+			src = (const uint32_t *)src + 1;
+		}
+		if (n & 0x08) {
+			/* ARMv7 can not handle unaligned access to long long
+			 * (uint64_t). Therefore two uint32_t operations are used.
+			 * TODO: use NEON too?
+			 */
+			*(uint32_t *)dst = *(const uint32_t *)src;
+			dst = (uint32_t *)dst + 1;
+			src = (const uint32_t *)src + 1;
+			*(uint32_t *)dst = *(const uint32_t *)src;
+		}
+		return ret;
+	}
+
+	/* Special fast cases for <= 128 bytes */
+	if (n <= 32) {
+		rte_mov16((uint8_t *)dst, (const uint8_t *)src);
+		rte_mov16((uint8_t *)dst - 16 + n,
+			(const uint8_t *)src - 16 + n);
+		return ret;
+	}
+
+	if (n <= 64) {
+		rte_mov32((uint8_t *)dst, (const uint8_t *)src);
+		rte_mov32((uint8_t *)dst - 32 + n,
+			(const uint8_t *)src - 32 + n);
+		return ret;
+	}
+
+	if (n <= 128) {
+		rte_mov64((uint8_t *)dst, (const uint8_t *)src);
+		rte_mov64((uint8_t *)dst - 64 + n,
+			(const uint8_t *)src - 64 + n);
+		return ret;
+	}
+
+	/*
+	 * For large copies > 128 bytes. This combination of 256, 64 and 16 byte
+	 * copies was found to be faster than doing 128 and 32 byte copies as
+	 * well.
+	 */
+	for ( ; n >= 256; n -= 256) {
+		rte_mov256((uint8_t *)dst, (const uint8_t *)src);
+		dst = (uint8_t *)dst + 256;
+		src = (const uint8_t *)src + 256;
+	}
+
+	/*
+	 * We split the remaining bytes (which will be less than 256) into
+	 * 64byte (2^6) chunks.
+	 * Using incrementing integers in the case labels of a switch statement
+	 * enourages the compiler to use a jump table. To get incrementing
+	 * integers, we shift the 2 relevant bits to the LSB position to first
+	 * get decrementing integers, and then subtract.
+	 */
+	switch (3 - (n >> 6)) {
+	case 0x00:
+		rte_mov64((uint8_t *)dst, (const uint8_t *)src);
+		n -= 64;
+		dst = (uint8_t *)dst + 64;
+		src = (const uint8_t *)src + 64;      /* fallthrough */
+	case 0x01:
+		rte_mov64((uint8_t *)dst, (const uint8_t *)src);
+		n -= 64;
+		dst = (uint8_t *)dst + 64;
+		src = (const uint8_t *)src + 64;      /* fallthrough */
+	case 0x02:
+		rte_mov64((uint8_t *)dst, (const uint8_t *)src);
+		n -= 64;
+		dst = (uint8_t *)dst + 64;
+		src = (const uint8_t *)src + 64;      /* fallthrough */
+	default:
+		;
+	}
+
+	/*
+	 * We split the remaining bytes (which will be less than 64) into
+	 * 16byte (2^4) chunks, using the same switch structure as above.
+	 */
+	switch (3 - (n >> 4)) {
+	case 0x00:
+		rte_mov16((uint8_t *)dst, (const uint8_t *)src);
+		n -= 16;
+		dst = (uint8_t *)dst + 16;
+		src = (const uint8_t *)src + 16;      /* fallthrough */
+	case 0x01:
+		rte_mov16((uint8_t *)dst, (const uint8_t *)src);
+		n -= 16;
+		dst = (uint8_t *)dst + 16;
+		src = (const uint8_t *)src + 16;      /* fallthrough */
+	case 0x02:
+		rte_mov16((uint8_t *)dst, (const uint8_t *)src);
+		n -= 16;
+		dst = (uint8_t *)dst + 16;
+		src = (const uint8_t *)src + 16;      /* fallthrough */
+	default:
+		;
+	}
+
+	/* Copy any remaining bytes, without going beyond end of buffers */
+	if (n != 0)
+		rte_mov16((uint8_t *)dst - 16 + n,
+			(const uint8_t *)src - 16 + n);
+	return ret;
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_MEMCPY_ARM_H_ */

index ac885e9..75e8bda 100644
@@ -35,8 +35,6 @@
 
 #include <stdint.h>
 #include <string.h>
-/* ARM NEON Intrinsics are used to copy data */
-#include <arm_neon.h>
 
 #ifdef __cplusplus
 extern "C" {

@@ -44,6 +42,11 @@ extern "C" {
 
 #include "generic/rte_memcpy.h"
 
+#ifdef __ARM_NEON_FP
+
+/* ARM NEON Intrinsics are used to copy data */
+#include <arm_neon.h>
+
 static inline void
 rte_mov16(uint8_t *dst, const uint8_t *src)
 {

@@ -263,6 +266,58 @@ rte_memcpy_func(void *dst, const void *src, size_t n)
 	return ret;
 }
 
+#else
+
+static inline void
+rte_mov16(uint8_t *dst, const uint8_t *src)
+{
+	memcpy(dst, src, 16);
+}
+
+static inline void
+rte_mov32(uint8_t *dst, const uint8_t *src)
+{
+	memcpy(dst, src, 32);
+}
+
+static inline void
+rte_mov48(uint8_t *dst, const uint8_t *src)
+{
+	memcpy(dst, src, 48);
+}
+
+static inline void
+rte_mov64(uint8_t *dst, const uint8_t *src)
+{
+	memcpy(dst, src, 64);
+}
+
+static inline void
+rte_mov128(uint8_t *dst, const uint8_t *src)
+{
+	memcpy(dst, src, 128);
+}
+
+static inline void
+rte_mov256(uint8_t *dst, const uint8_t *src)
+{
+	memcpy(dst, src, 256);
+}
+
+static inline void *
+rte_memcpy(void *dst, const void *src, size_t n)
+{
+	return memcpy(dst, src, n);
+}
+
+static inline void *
+rte_memcpy_func(void *dst, const void *src, size_t n)
+{
+	return memcpy(dst, src, n);
+}
+
+#endif /* __ARM_NEON_FP */
+
 #ifdef __cplusplus
 }
 #endif

index 5b92061..557458f 100644
@@ -115,6 +115,11 @@ test_cpuflags(void)
 	CHECK_FOR_FLAG(RTE_CPUFLAG_ICACHE_SNOOP);
 #endif
 
+#if defined(RTE_ARCH_ARM)
+	printf("Check for NEON:\t\t");
+	CHECK_FOR_FLAG(RTE_CPUFLAG_NEON);
+#endif
+
 #if defined(RTE_ARCH_X86_64) || defined(RTE_ARCH_I686)
 	printf("Check for SSE:\t\t");
 	CHECK_FOR_FLAG(RTE_CPUFLAG_SSE);

177 lines not on this page · raw message

index 1eadb33..17e13fc 100644
@@ -52,10 +52,15 @@ extern "C" {
 #define AT_HWCAP2 26
 #endif
 
+#ifndef AT_PLATFORM
+#define AT_PLATFORM 15
+#endif
+
 /* software based registers */
 enum cpu_register_t {
 	REG_HWCAP = 0,
 	REG_HWCAP2,
+	REG_PLATFORM,
 };
 
 /**

@@ -89,6 +94,8 @@ enum rte_cpu_flag_t {
 	RTE_CPUFLAG_SHA1,
 	RTE_CPUFLAG_SHA2,
 	RTE_CPUFLAG_CRC32,
+	RTE_CPUFLAG_AARCH32,
+	RTE_CPUFLAG_AARCH64,
 	/* The last item */
 	RTE_CPUFLAG_NUMFLAGS,/**< This should always be the last! */
 };

@@ -121,6 +128,8 @@ static const struct feature_entry cpu_feature_table[] = {
 	FEAT_DEF(SHA1,      0x00000001, 0, REG_HWCAP2,  2)
 	FEAT_DEF(SHA2,      0x00000001, 0, REG_HWCAP2,  3)
 	FEAT_DEF(CRC32,     0x00000001, 0, REG_HWCAP2,  4)
+	FEAT_DEF(AARCH32,   0x00000001, 0, REG_PLATFORM, 0)
+	FEAT_DEF(AARCH64,   0x00000001, 0, REG_PLATFORM, 1)
 };
 
 /*

@@ -141,6 +150,12 @@ rte_cpu_get_features(__attribute__((unused)) uint32_t leaf,
 			out[REG_HWCAP] = auxv.a_un.a_val;
 		else if (auxv.a_type == AT_HWCAP2)
 			out[REG_HWCAP2] = auxv.a_un.a_val;
+		else if (auxv.a_type == AT_PLATFORM) {
+			if (!strcmp((const char *)auxv.a_un.a_val, "aarch32"))
+				out[REG_PLATFORM] = 0x0001;
+			else if (!strcmp((const char *)auxv.a_un.a_val, "aarch64"))
+				out[REG_PLATFORM] = 0x0002;
+		}
 	}
 }
 

new file mode 100644
index 0000000..664bec8
@@ -0,0 +1,40 @@
+/* copied from ppc_64 */
+
+#ifndef _RTE_RWLOCK_ARM_H_
+#define _RTE_RWLOCK_ARM_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "generic/rte_rwlock.h"
+
+static inline void
+rte_rwlock_read_lock_tm(rte_rwlock_t *rwl)
+{
+	rte_rwlock_read_lock(rwl);
+}
+
+static inline void
+rte_rwlock_read_unlock_tm(rte_rwlock_t *rwl)
+{
+	rte_rwlock_read_unlock(rwl);
+}
+
+static inline void
+rte_rwlock_write_lock_tm(rte_rwlock_t *rwl)
+{
+	rte_rwlock_write_lock(rwl);
+}
+
+static inline void
+rte_rwlock_write_unlock_tm(rte_rwlock_t *rwl)
+{
+	rte_rwlock_write_unlock(rwl);
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_RWLOCK_ARM_H_ */

90 lines not on this page · raw message

new file mode 100644
index 0000000..1815766
@@ -0,0 +1,256 @@
+/*-
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2015 RehiveTech. All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of RehiveTech nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _RTE_ATOMIC_ARM_H_
+#define _RTE_ATOMIC_ARM_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "generic/rte_atomic.h"
+
+/**
+ * General memory barrier.
+ *
+ * Guarantees that the LOAD and STORE operations generated before the
+ * barrier occur before the LOAD and STORE operations generated after.
+ */
+#define	rte_mb()  __sync_synchronize()
+
+/**
+ * Write memory barrier.
+ *
+ * Guarantees that the STORE operations generated before the barrier
+ * occur before the STORE operations generated after.
+ */
+#define	rte_wmb() do { asm volatile ("dmb st" : : : "memory"); } while(0)
+
+/**
+ * Read memory barrier.
+ *
+ * Guarantees that the LOAD operations generated before the barrier
+ * occur before the LOAD operations generated after.
+ */
+#define	rte_rmb() __sync_synchronize()
+
+/*------------------------- 16 bit atomic operations -------------------------*/
+
+#ifndef RTE_FORCE_INTRINSICS
+static inline int
+rte_atomic16_cmpset(volatile uint16_t *dst, uint16_t exp, uint16_t src)
+{
+	return __atomic_compare_exchange(dst, &exp, &src, 0, __ATOMIC_ACQUIRE,
+		__ATOMIC_ACQUIRE) ? 1 : 0;
+}
+
+static inline int rte_atomic16_test_and_set(rte_atomic16_t *v)
+{
+	return rte_atomic16_cmpset((volatile uint16_t *)&v->cnt, 0, 1);
+}
+
+static inline void
+rte_atomic16_inc(rte_atomic16_t *v)
+{
+	__atomic_add_fetch(&v->cnt, 1, __ATOMIC_ACQUIRE);
+}
+
+static inline void
+rte_atomic16_dec(rte_atomic16_t *v)
+{
+	__atomic_sub_fetch(&v->cnt, 1, __ATOMIC_ACQUIRE);
+}
+
+static inline int rte_atomic16_inc_and_test(rte_atomic16_t *v)
+{
+	return (__atomic_add_fetch(&v->cnt, 1, __ATOMIC_ACQUIRE) == 0);
+}
+
+static inline int rte_atomic16_dec_and_test(rte_atomic16_t *v)
+{
+	return (__atomic_sub_fetch(&v->cnt, 1, __ATOMIC_ACQUIRE) == 0);
+}
+
+/*------------------------- 32 bit atomic operations -------------------------*/
+
+static inline int
+rte_atomic32_cmpset(volatile uint32_t *dst, uint32_t exp, uint32_t src)
+{
+	return __atomic_compare_exchange(dst, &exp, &src, 0, __ATOMIC_ACQUIRE,
+		__ATOMIC_ACQUIRE) ? 1 : 0;
+}
+
+static inline int rte_atomic32_test_and_set(rte_atomic32_t *v)
+{
+	return rte_atomic32_cmpset((volatile uint32_t *)&v->cnt, 0, 1);
+}
+
+static inline void
+rte_atomic32_inc(rte_atomic32_t *v)
+{
+	__atomic_add_fetch(&v->cnt, 1, __ATOMIC_ACQUIRE);
+}
+
+static inline void
+rte_atomic32_dec(rte_atomic32_t *v)
+{
+	__atomic_sub_fetch(&v->cnt, 1, __ATOMIC_ACQUIRE);
+}
+
+static inline int rte_atomic32_inc_and_test(rte_atomic32_t *v)
+{
+	return (__atomic_add_fetch(&v->cnt, 1, __ATOMIC_ACQUIRE) == 0);
+}
+
+static inline int rte_atomic32_dec_and_test(rte_atomic32_t *v)
+{
+	return (__atomic_sub_fetch(&v->cnt, 1, __ATOMIC_ACQUIRE) == 0);
+}
+
+/*------------------------- 64 bit atomic operations -------------------------*/
+
+static inline int
+rte_atomic64_cmpset(volatile uint64_t *dst, uint64_t exp, uint64_t src)
+{
+	return __atomic_compare_exchange(dst, &exp, &src, 0, __ATOMIC_ACQUIRE,
+		__ATOMIC_ACQUIRE) ? 1 : 0;
+}
+
+static inline void
+rte_atomic64_init(rte_atomic64_t *v)
+{
+	int success = 0;
+	uint64_t tmp;
+
+	while (success == 0) {
+		tmp = v->cnt;
+		success = rte_atomic64_cmpset((volatile uint64_t *)&v->cnt,
+		                              tmp, 0);
+	}
+}
+
+static inline int64_t
+rte_atomic64_read(rte_atomic64_t *v)
+{
+	int success = 0;
+	uint64_t tmp;
+
+	while (success == 0) {
+		tmp = v->cnt;
+		/* replace the value by itself */
+		success = rte_atomic64_cmpset((volatile uint64_t *) &v->cnt,
+		                              tmp, tmp);
+	}
+	return tmp;
+}
+
+static inline void
+rte_atomic64_set(rte_atomic64_t *v, int64_t new_value)
+{
+	int success = 0;
+	uint64_t tmp;
+
+	while (success == 0) {
+		tmp = v->cnt;
+		success = rte_atomic64_cmpset((volatile uint64_t *)&v->cnt,
+		                              tmp, new_value);
+	}
+}
+
+static inline void
+rte_atomic64_add(rte_atomic64_t *v, int64_t inc)
+{
+	__atomic_fetch_add(&v->cnt, inc, __ATOMIC_ACQUIRE);
+}
+
+static inline void
+rte_atomic64_sub(rte_atomic64_t *v, int64_t dec)
+{
+	__atomic_fetch_sub(&v->cnt, dec, __ATOMIC_ACQUIRE);
+}
+
+static inline void
+rte_atomic64_inc(rte_atomic64_t *v)
+{
+	__atomic_fetch_add(&v->cnt, 1, __ATOMIC_ACQUIRE);
+}
+
+static inline void
+rte_atomic64_dec(rte_atomic64_t *v)
+{
+	__atomic_fetch_sub(&v->cnt, 1, __ATOMIC_ACQUIRE);
+}
+
+static inline int64_t
+rte_atomic64_add_return(rte_atomic64_t *v, int64_t inc)
+{
+	return __atomic_add_fetch(&v->cnt, inc, __ATOMIC_ACQUIRE);
+}
+
+static inline int64_t
+rte_atomic64_sub_return(rte_atomic64_t *v, int64_t dec)
+{
+	return __atomic_sub_fetch(&v->cnt, dec, __ATOMIC_ACQUIRE);
+}
+
+static inline int rte_atomic64_inc_and_test(rte_atomic64_t *v)
+{
+	return (__atomic_add_fetch(&v->cnt, 1, __ATOMIC_ACQUIRE) == 0);
+}
+
+static inline int rte_atomic64_dec_and_test(rte_atomic64_t *v)
+{
+	return (__atomic_sub_fetch(&v->cnt, 1, __ATOMIC_ACQUIRE) == 0);
+}
+
+static inline int rte_atomic64_test_and_set(rte_atomic64_t *v)
+{
+	return rte_atomic64_cmpset((volatile uint64_t *)&v->cnt, 0, 1);
+}
+
+/**
+ * Atomically set a 64-bit counter to 0.
+ *
+ * @param v
+ *   A pointer to the atomic counter.
+ */
+static inline void rte_atomic64_clear(rte_atomic64_t *v)
+{
+	rte_atomic64_set(v, 0);
+}
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_ATOMIC_ARM_H_ */

new file mode 100644
index 0000000..04e7b87
@@ -0,0 +1,148 @@
+/*
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2015 RehiveTech. All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of RehiveTech nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _RTE_BYTEORDER_ARM_H_
+#define _RTE_BYTEORDER_ARM_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "generic/rte_byteorder.h"
+
+/*
+ * An architecture-optimized byte swap for a 16-bit value.
+ *
+ * Do not use this function directly. The preferred function is rte_bswap16().
+ */
+static inline uint16_t rte_arch_bswap16(uint16_t _x)
+{
+	register uint16_t x = _x;
+	asm volatile ("rev16 %[x1],%[x2]"
+		      : [x1] "=r" (x)
+		      : [x2] "r" (x)
+		      );
+	return x;
+}
+
+/*
+ * An architecture-optimized byte swap for a 32-bit value.
+ *
+ * Do not use this function directly. The preferred function is rte_bswap32().
+ */
+static inline uint32_t rte_arch_bswap32(uint32_t _x)
+{
+	register uint32_t x = _x;
+	asm volatile ("rev %[x1],%[x2]"
+		      : [x1] "=r" (x)
+		      : [x2] "r" (x)
+		      );
+	return x;
+}
+
+/*
+ * An architecture-optimized byte swap for a 64-bit value.
+ *
+  * Do not use this function directly. The preferred function is rte_bswap64().
+ */
+/* 64-bit mode */
+static inline uint64_t rte_arch_bswap64(uint64_t _x)
+{
+	return  __builtin_bswap64(_x);
+}
+
+#ifndef RTE_FORCE_INTRINSICS
+#define rte_bswap16(x) ((uint16_t)(__builtin_constant_p(x) ?		\
+				   rte_constant_bswap16(x) :		\
+				   rte_arch_bswap16(x)))
+
+#define rte_bswap32(x) ((uint32_t)(__builtin_constant_p(x) ?		\
+				   rte_constant_bswap32(x) :		\
+				   rte_arch_bswap32(x)))
+
+#define rte_bswap64(x) ((uint64_t)(__builtin_constant_p(x) ?		\
+				   rte_constant_bswap64(x) :		\
+				   rte_arch_bswap64(x)))
+#else
+/*
+ * __builtin_bswap16 is only available gcc 4.8 and upwards
+ */
+#if __GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ < 8)
+#define rte_bswap16(x) ((uint16_t)(__builtin_constant_p(x) ?		\
+				   rte_constant_bswap16(x) :		\
+				   rte_arch_bswap16(x)))
+#endif
+#endif
+
+/* ARM architecture is bi-endian (both big and little). */
+#if RTE_BYTE_ORDER == RTE_LITTLE_ENDIAN
+
+#define rte_cpu_to_le_16(x) (x)
+#define rte_cpu_to_le_32(x) (x)
+#define rte_cpu_to_le_64(x) (x)
+
+#define rte_cpu_to_be_16(x) rte_bswap16(x)
+#define rte_cpu_to_be_32(x) rte_bswap32(x)
+#define rte_cpu_to_be_64(x) rte_bswap64(x)
+
+#define rte_le_to_cpu_16(x) (x)
+#define rte_le_to_cpu_32(x) (x)
+#define rte_le_to_cpu_64(x) (x)
+
+#define rte_be_to_cpu_16(x) rte_bswap16(x)
+#define rte_be_to_cpu_32(x) rte_bswap32(x)
+#define rte_be_to_cpu_64(x) rte_bswap64(x)
+
+#else /* RTE_BIG_ENDIAN */
+
+#define rte_cpu_to_le_16(x) rte_bswap16(x)
+#define rte_cpu_to_le_32(x) rte_bswap32(x)
+#define rte_cpu_to_le_64(x) rte_bswap64(x)
+
+#define rte_cpu_to_be_16(x) (x)
+#define rte_cpu_to_be_32(x) (x)
+#define rte_cpu_to_be_64(x) (x)
+
+#define rte_le_to_cpu_16(x) rte_bswap16(x)
+#define rte_le_to_cpu_32(x) rte_bswap32(x)
+#define rte_le_to_cpu_64(x) rte_bswap64(x)
+
+#define rte_be_to_cpu_16(x) (x)
+#define rte_be_to_cpu_32(x) (x)
+#define rte_be_to_cpu_64(x) (x)
+#endif
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_BYTEORDER_ARM_H_ */

new file mode 100644
index 0000000..ff66ae2
@@ -0,0 +1,85 @@
+/*
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2015 RehiveTech. All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of RehiveTech nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _RTE_CYCLES_ARM_H_
+#define _RTE_CYCLES_ARM_H_
+
+/* ARM v7 does not have suitable source of clock signals. The only clock counter
+   available in the core is 32 bit wide. Therefore it is unsuitable as the
+   counter overlaps every few seconds and probably is not accessible by
+   userspace programs. Therefore we use clock_gettime(CLOCK_MONOTONIC_RAW) to
+   simulate counter running at 1GHz.
+*/
+
+#include <time.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "generic/rte_cycles.h"
+
+/**
+ * Read the time base register.
+ *
+ * @return
+ *   The time base for this lcore.
+ */
+static inline uint64_t
+rte_rdtsc(void)
+{
+	struct timespec val;
+	uint64_t v;
+
+	while (clock_gettime(CLOCK_MONOTONIC_RAW, &val) != 0)
+		/* no body */;
+
+	v  = (uint64_t) val.tv_sec * 1000000000LL;
+	v += (uint64_t) val.tv_nsec;
+	return v;
+}
+
+static inline uint64_t
+rte_rdtsc_precise(void)
+{
+	rte_mb();
+	return rte_rdtsc();
+}
+
+static inline uint64_t
+rte_get_tsc_cycles(void) { return rte_rdtsc(); }
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_CYCLES_ARM_H_ */

index ff66ae2..5dcef25 100644
@@ -54,8 +54,14 @@ extern "C" {
  * @return
  *   The time base for this lcore.
  */
+#ifndef CONFIG_RTE_ARM_EAL_RDTSC_USE_PMU
+
+/**
+ * This call is easily portable to any ARM architecture, however,
+ * it may be damn slow and inprecise for some tasks.
+ */
 static inline uint64_t
-rte_rdtsc(void)
+__rte_rdtsc_syscall(void)
 {
 	struct timespec val;
 	uint64_t v;

@@ -67,6 +73,36 @@ rte_rdtsc(void)
 	v += (uint64_t) val.tv_nsec;
 	return v;
 }
+#define rte_rdtsc __rte_rdtsc_syscall
+
+#else
+
+/**
+ * This function requires to configure the PMCCNTR and enable
+ * userspace access to it:
+ *
+ *      asm volatile("mcr p15, 0, %0, c9, c14, 0" : : "r"(1));
+ *      asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r"(29));
+ *      asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r"(0x8000000f));
+ *
+ * which is possible only from the priviledged mode (kernel space).
+ */
+static inline uint64_t
+__rte_rdtsc_pmccntr(void)
+{
+	unsigned tsc;
+	uint64_t final_tsc;
+
+	/* Read PMCCNTR */
+	asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r"(tsc));
+	/* 1 tick = 64 clocks */
+	final_tsc = ((uint64_t)tsc) << 6;
+
+	return (uint64_t)final_tsc;
+}
+#define rte_rdtsc __rte_rdtsc_pmccntr
+
+#endif /* RTE_ARM_EAL_RDTSC_USE_PMU */
 
 static inline uint64_t
 rte_rdtsc_precise(void)

new file mode 100644
index 0000000..8d75fe6
@@ -0,0 +1,61 @@
+/*
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2015 RehiveTech. All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of RehiveTech nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _RTE_PREFETCH_ARM_H_
+#define _RTE_PREFETCH_ARM_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "generic/rte_prefetch.h"
+
+static inline void rte_prefetch0(const volatile void *p)
+{
+	asm volatile ("pld [%[p]]" : : [p] "r" (p));
+}
+
+static inline void rte_prefetch1(const volatile void *p)
+{
+	asm volatile ("pld [%[p]]" : : [p] "r" (p));
+}
+
+static inline void rte_prefetch2(const volatile void *p)
+{
+	asm volatile ("pld [%[p]]" : : [p] "r" (p));
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_PREFETCH_ARM_H_ */

new file mode 100644
index 0000000..cd5ab8b
@@ -0,0 +1,114 @@
+/*
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2015 RehiveTech. All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of RehiveTech nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _RTE_SPINLOCK_ARM_H_
+#define _RTE_SPINLOCK_ARM_H_
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include <rte_common.h>
+#include "generic/rte_spinlock.h"
+
+/* Intrinsics are used to implement the spinlock on ARM architecture */
+
+#ifndef RTE_FORCE_INTRINSICS
+
+static inline void
+rte_spinlock_lock(rte_spinlock_t *sl)
+{
+	while (__sync_lock_test_and_set(&sl->locked, 1))
+		while (sl->locked)
+			rte_pause();
+}
+
+static inline void
+rte_spinlock_unlock(rte_spinlock_t *sl)
+{
+	__sync_lock_release(&sl->locked);
+}
+
+static inline int
+rte_spinlock_trylock(rte_spinlock_t *sl)
+{
+	return (__sync_lock_test_and_set(&sl->locked, 1) == 0);
+}
+
+#endif
+
+static inline int rte_tm_supported(void)
+{
+	return 0;
+}
+
+static inline void
+rte_spinlock_lock_tm(rte_spinlock_t *sl)
+{
+	rte_spinlock_lock(sl); /* fall-back */
+}
+
+static inline int
+rte_spinlock_trylock_tm(rte_spinlock_t *sl)
+{
+	return rte_spinlock_trylock(sl);
+}
+
+static inline void
+rte_spinlock_unlock_tm(rte_spinlock_t *sl)
+{
+	rte_spinlock_unlock(sl);
+}
+
+static inline void
+rte_spinlock_recursive_lock_tm(rte_spinlock_recursive_t *slr)
+{
+	rte_spinlock_recursive_lock(slr); /* fall-back */
+}
+
+static inline void
+rte_spinlock_recursive_unlock_tm(rte_spinlock_recursive_t *slr)
+{
+	rte_spinlock_recursive_unlock(slr);
+}
+
+static inline int
+rte_spinlock_recursive_trylock_tm(rte_spinlock_recursive_t *slr)
+{
+	return rte_spinlock_recursive_trylock(slr);
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_SPINLOCK_ARM_H_ */

new file mode 100644
index 0000000..ac885e9
@@ -0,0 +1,270 @@
+/*
+ *   BSD LICENSE
+ *
+ *   Copyright(c) 2015 RehiveTech. All rights reserved.
+ *
+ *   Redistribution and use in source and binary forms, with or without
+ *   modification, are permitted provided that the following conditions
+ *   are met:
+ *
+ *     * Redistributions of source code must retain the above copyright
+ *       notice, this list of conditions and the following disclaimer.
+ *     * Redistributions in binary form must reproduce the above copyright
+ *       notice, this list of conditions and the following disclaimer in
+ *       the documentation and/or other materials provided with the
+ *       distribution.
+ *     * Neither the name of RehiveTech nor the names of its
+ *       contributors may be used to endorse or promote products derived
+ *       from this software without specific prior written permission.
+ *
+ *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _RTE_MEMCPY_ARM_H_
+#define _RTE_MEMCPY_ARM_H_
+
+#include <stdint.h>
+#include <string.h>
+/* ARM NEON Intrinsics are used to copy data */
+#include <arm_neon.h>
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+#include "generic/rte_memcpy.h"
+
+static inline void
+rte_mov16(uint8_t *dst, const uint8_t *src)
+{
+	vst1q_u8(dst, vld1q_u8(src));
+}
+
+static inline void
+rte_mov32(uint8_t *dst, const uint8_t *src)
+{
+	asm volatile ("vld1.8 {d0-d3}, [%[src]]\n\t"
+	              "vst1.8 {d0-d3}, [%[dst]]\n\t"
+	              : [src] "+r" (src), [dst] "+r" (dst)
+	              : : "memory", "d0", "d1", "d2", "d3");
+}
+
+static inline void
+rte_mov48(uint8_t *dst, const uint8_t *src)
+{
+	asm volatile ("vld1.8 {d0-d3}, [%[src]]!\n\t"
+	              "vld1.8 {d4-d5}, [%[src]]\n\t"
+	              "vst1.8 {d0-d3}, [%[dst]]!\n\t"
+	              "vst1.8 {d4-d5}, [%[dst]]\n\t"
+	              : [src] "+r" (src), [dst] "+r" (dst)
+	              : : "memory", "d0", "d1", "d2", "d3", "d4", "d5");
+}
+
+static inline void
+rte_mov64(uint8_t *dst, const uint8_t *src)
+{
+	asm volatile ("vld1.8 {d0-d3}, [%[src]]!\n\t"
+	              "vld1.8 {d4-d7}, [%[src]]\n\t"
+	              "vst1.8 {d0-d3}, [%[dst]]!\n\t"
+	              "vst1.8 {d4-d7}, [%[dst]]\n\t"
+	              : [src] "+r" (src), [dst] "+r" (dst)
+	              : : "memory", "d0", "d1", "d2", "d3", "d4", "d5", "d6", "d7");
+}
+
+static inline void
+rte_mov128(uint8_t *dst, const uint8_t *src)
+{
+	asm volatile ("pld [%[src], #64]" : : [src] "r" (src));
+	asm volatile ("vld1.8 {d0-d3},   [%[src]]!\n\t"
+	              "vld1.8 {d4-d7},   [%[src]]!\n\t"
+	              "vld1.8 {d8-d11},  [%[src]]!\n\t"
+	              "vld1.8 {d12-d15}, [%[src]]\n\t"
+	              "vst1.8 {d0-d3},   [%[dst]]!\n\t"
+	              "vst1.8 {d4-d7},   [%[dst]]!\n\t"
+	              "vst1.8 {d8-d11},  [%[dst]]!\n\t"
+	              "vst1.8 {d12-d15}, [%[dst]]\n\t"
+	              : [src] "+r" (src), [dst] "+r" (dst)
+	              : : "memory", "d0", "d1", "d2", "d3", "d4", "d5", "d6", "d7",
+	                  "d8", "d9", "d10", "d11", "d12", "d13", "d14", "d15");
+}
+
+static inline void
+rte_mov256(uint8_t *dst, const uint8_t *src)
+{
+	asm volatile ("pld [%[src], #64]" : : [src] "r" (src));
+	asm volatile ("pld [%[src], #128]" : : [src] "r" (src));
+	asm volatile ("pld [%[src], #192]" : : [src] "r" (src));
+	asm volatile ("pld [%[src], #256]" : : [src] "r" (src));
+	asm volatile ("pld [%[src], #320]" : : [src] "r" (src));
+	asm volatile ("pld [%[src], #384]" : : [src] "r" (src));
+	asm volatile ("pld [%[src], #448]" : : [src] "r" (src));
+	asm volatile ("vld1.8 {d0-d3},   [%[src]]!\n\t"
+	              "vld1.8 {d4-d7},   [%[src]]!\n\t"
+	              "vld1.8 {d8-d11},  [%[src]]!\n\t"
+	              "vld1.8 {d12-d15}, [%[src]]!\n\t"
+	              "vld1.8 {d16-d19}, [%[src]]!\n\t"
+	              "vld1.8 {d20-d23}, [%[src]]!\n\t"
+	              "vld1.8 {d24-d27}, [%[src]]!\n\t"
+	              "vld1.8 {d28-d31}, [%[src]]\n\t"
+	              "vst1.8 {d0-d3},   [%[dst]]!\n\t"
+	              "vst1.8 {d4-d7},   [%[dst]]!\n\t"
+	              "vst1.8 {d8-d11},  [%[dst]]!\n\t"
+	              "vst1.8 {d12-d15}, [%[dst]]!\n\t"
+	              "vst1.8 {d16-d19}, [%[dst]]!\n\t"
+	              "vst1.8 {d20-d23}, [%[dst]]!\n\t"
+	              "vst1.8 {d24-d27}, [%[dst]]!\n\t"
+	              "vst1.8 {d28-d31}, [%[dst]]!\n\t"
+	              : [src] "+r" (src), [dst] "+r" (dst)
+	              : : "memory", "d0", "d1", "d2", "d3", "d4", "d5", "d6", "d7",
+	                  "d8", "d9", "d10", "d11", "d12", "d13", "d14", "d15",
+	                  "d16", "d17", "d18", "d19", "d20", "d21", "d22", "d23",
+	                  "d24", "d25", "d26", "d27", "d28", "d29", "d30", "d31");
+}
+
+#define rte_memcpy(dst, src, n)              \
+	({ (__builtin_constant_p(n)) ?       \
+	memcpy((dst), (src), (n)) :          \
+	rte_memcpy_func((dst), (src), (n)); })
+
+static inline void *
+rte_memcpy_func(void *dst, const void *src, size_t n)
+{
+	void *ret = dst;
+
+	/* We can't copy < 16 bytes using XMM registers so do it manually. */
+	if (n < 16) {
+		if (n & 0x01) {
+			*(uint8_t *)dst = *(const uint8_t *)src;
+			dst = (uint8_t *)dst + 1;
+			src = (const uint8_t *)src + 1;
+		}
+		if (n & 0x02) {
+			*(uint16_t *)dst = *(const uint16_t *)src;
+			dst = (uint16_t *)dst + 1;
+			src = (const uint16_t *)src + 1;
+		}
+		if (n & 0x04) {
+			*(uint32_t *)dst = *(const uint32_t *)src;
+			dst = (uint32_t *)dst + 1;
+			src = (const uint32_t *)src + 1;
+		}
+		if (n & 0x08) {
+			/* ARMv7 can not handle unaligned access to long long
+			 * (uint64_t). Therefore two uint32_t operations are used.
+			 * TODO: use NEON too?
+			 */
+			*(uint32_t *)dst = *(const uint32_t *)src;
+			dst = (uint32_t *)dst + 1;
+			src = (const uint32_t *)src + 1;
+			*(uint32_t *)dst = *(const uint32_t *)src;
+		}
+		return ret;
+	}
+
+	/* Special fast cases for <= 128 bytes */
+	if (n <= 32) {
+		rte_mov16((uint8_t *)dst, (const uint8_t *)src);
+		rte_mov16((uint8_t *)dst - 16 + n,
+			(const uint8_t *)src - 16 + n);
+		return ret;
+	}
+
+	if (n <= 64) {
+		rte_mov32((uint8_t *)dst, (const uint8_t *)src);
+		rte_mov32((uint8_t *)dst - 32 + n,
+			(const uint8_t *)src - 32 + n);
+		return ret;
+	}
+
+	if (n <= 128) {
+		rte_mov64((uint8_t *)dst, (const uint8_t *)src);
+		rte_mov64((uint8_t *)dst - 64 + n,
+			(const uint8_t *)src - 64 + n);
+		return ret;
+	}
+
+	/*
+	 * For large copies > 128 bytes. This combination of 256, 64 and 16 byte
+	 * copies was found to be faster than doing 128 and 32 byte copies as
+	 * well.
+	 */
+	for ( ; n >= 256; n -= 256) {
+		rte_mov256((uint8_t *)dst, (const uint8_t *)src);
+		dst = (uint8_t *)dst + 256;
+		src = (const uint8_t *)src + 256;
+	}
+
+	/*
+	 * We split the remaining bytes (which will be less than 256) into
+	 * 64byte (2^6) chunks.
+	 * Using incrementing integers in the case labels of a switch statement
+	 * enourages the compiler to use a jump table. To get incrementing
+	 * integers, we shift the 2 relevant bits to the LSB position to first
+	 * get decrementing integers, and then subtract.
+	 */
+	switch (3 - (n >> 6)) {
+	case 0x00:
+		rte_mov64((uint8_t *)dst, (const uint8_t *)src);
+		n -= 64;
+		dst = (uint8_t *)dst + 64;
+		src = (const uint8_t *)src + 64;      /* fallthrough */
+	case 0x01:
+		rte_mov64((uint8_t *)dst, (const uint8_t *)src);
+		n -= 64;
+		dst = (uint8_t *)dst + 64;
+		src = (const uint8_t *)src + 64;      /* fallthrough */
+	case 0x02:
+		rte_mov64((uint8_t *)dst, (const uint8_t *)src);
+		n -= 64;
+		dst = (uint8_t *)dst + 64;
+		src = (const uint8_t *)src + 64;      /* fallthrough */
+	default:
+		;
+	}
+
+	/*
+	 * We split the remaining bytes (which will be less than 64) into
+	 * 16byte (2^4) chunks, using the same switch structure as above.
+	 */
+	switch (3 - (n >> 4)) {
+	case 0x00:
+		rte_mov16((uint8_t *)dst, (const uint8_t *)src);
+		n -= 16;
+		dst = (uint8_t *)dst + 16;
+		src = (const uint8_t *)src + 16;      /* fallthrough */
+	case 0x01:
+		rte_mov16((uint8_t *)dst, (const uint8_t *)src);
+		n -= 16;
+		dst = (uint8_t *)dst + 16;
+		src = (const uint8_t *)src + 16;      /* fallthrough */
+	case 0x02:
+		rte_mov16((uint8_t *)dst, (const uint8_t *)src);
+		n -= 16;
+		dst = (uint8_t *)dst + 16;
+		src = (const uint8_t *)src + 16;      /* fallthrough */
+	default:
+		;
+	}
+
+	/* Copy any remaining bytes, without going beyond end of buffers */
+	if (n != 0)
+		rte_mov16((uint8_t *)dst - 16 + n,
+			(const uint8_t *)src - 16 + n);
+	return ret;
+}
+
+#ifdef __cplusplus
+}
+#endif
+
+#endif /* _RTE_MEMCPY_ARM_H_ */