#ifdef __DOXYGEN__
+/** @name Memory Barrier
+ */
+///@{
/**
* General memory barrier.
*
* Guarantees that the LOAD and STORE operations generated before the
* barrier occur before the LOAD and STORE operations generated after.
- * This function is architecture dependent.
*/
static inline void rte_mb(void);
*
* Guarantees that the STORE operations generated before the barrier
* occur before the STORE operations generated after.
- * This function is architecture dependent.
*/
static inline void rte_wmb(void);
*
* Guarantees that the LOAD operations generated before the barrier
* occur before the LOAD operations generated after.
- * This function is architecture dependent.
*/
static inline void rte_rmb(void);
+///@}
+/** @name SMP Memory Barrier
+ */
+///@{
/**
* General memory barrier between lcores
*
* before the LOAD operations that follows it.
*/
static inline void rte_smp_rmb(void);
+///@}
+/** @name I/O Memory Barrier
+ */
+///@{
/**
* General memory barrier for I/O device
*
* operations that follow it.
*/
static inline void rte_io_rmb(void);
+///@}
+
+/** @name Coherent I/O Memory Barrier
+ *
+ * Coherent I/O memory barrier is a lightweight version of I/O memory
+ * barriers which are system-wide data synchronization barriers. This
+ * is for only coherent memory domain between lcore and I/O device but
+ * it is same as the I/O memory barriers in most of architectures.
+ * However, some architecture provides even lighter barriers which are
+ * somewhere in between I/O memory barriers and SMP memory barriers.
+ * For example, in case of ARMv8, DMB(data memory barrier) instruction
+ * can have different shareability domains - inner-shareable and
+ * outer-shareable. And inner-shareable DMB fits for SMP memory
+ * barriers and outer-shareable DMB for coherent I/O memory barriers,
+ * which acts on coherent memory.
+ *
+ * In most cases, I/O memory barriers are safer but if operations are
+ * on coherent memory instead of incoherent MMIO region of a device,
+ * then coherent I/O memory barriers can be used and this could bring
+ * performance gain depending on architectures.
+ */
+///@{
+/**
+ * Write memory barrier for coherent memory between lcore and I/O device
+ *
+ * Guarantees that the STORE operations on coherent memory that
+ * precede the rte_cio_wmb() call are visible to I/O device before the
+ * STORE operations that follow it.
+ */
+static inline void rte_cio_wmb(void);
+
+/**
+ * Read memory barrier for coherent memory between lcore and I/O device
+ *
+ * Guarantees that the LOAD operations on coherent memory updated by
+ * I/O device that precede the rte_cio_rmb() call are visible to CPU
+ * before the LOAD operations that follow it.
+ */
+static inline void rte_cio_rmb(void);
+///@}
#endif /* __DOXYGEN__ */
}
#endif
+/**
+ * Atomic exchange.
+ *
+ * (atomic) equivalent to:
+ * ret = *dst
+ * *dst = val;
+ * return ret;
+ *
+ * @param dst
+ * The destination location into which the value will be written.
+ * @param val
+ * The new value.
+ * @return
+ * The original value at that location
+ */
+static inline uint16_t
+rte_atomic16_exchange(volatile uint16_t *dst, uint16_t val);
+
+#ifdef RTE_FORCE_INTRINSICS
+static inline uint16_t
+rte_atomic16_exchange(volatile uint16_t *dst, uint16_t val)
+{
+#if defined(__clang__)
+ return __atomic_exchange_n(dst, val, __ATOMIC_SEQ_CST);
+#else
+ return __atomic_exchange_2(dst, val, __ATOMIC_SEQ_CST);
+#endif
+}
+#endif
+
/**
* The atomic counter structure.
*/
}
#endif
+/**
+ * Atomic exchange.
+ *
+ * (atomic) equivalent to:
+ * ret = *dst
+ * *dst = val;
+ * return ret;
+ *
+ * @param dst
+ * The destination location into which the value will be written.
+ * @param val
+ * The new value.
+ * @return
+ * The original value at that location
+ */
+static inline uint32_t
+rte_atomic32_exchange(volatile uint32_t *dst, uint32_t val);
+
+#ifdef RTE_FORCE_INTRINSICS
+static inline uint32_t
+rte_atomic32_exchange(volatile uint32_t *dst, uint32_t val)
+{
+#if defined(__clang__)
+ return __atomic_exchange_n(dst, val, __ATOMIC_SEQ_CST);
+#else
+ return __atomic_exchange_4(dst, val, __ATOMIC_SEQ_CST);
+#endif
+}
+#endif
+
/**
* The atomic counter structure.
*/
}
#endif
+/**
+ * Atomic exchange.
+ *
+ * (atomic) equivalent to:
+ * ret = *dst
+ * *dst = val;
+ * return ret;
+ *
+ * @param dst
+ * The destination location into which the value will be written.
+ * @param val
+ * The new value.
+ * @return
+ * The original value at that location
+ */
+static inline uint64_t
+rte_atomic64_exchange(volatile uint64_t *dst, uint64_t val);
+
+#ifdef RTE_FORCE_INTRINSICS
+static inline uint64_t
+rte_atomic64_exchange(volatile uint64_t *dst, uint64_t val)
+{
+#if defined(__clang__)
+ return __atomic_exchange_n(dst, val, __ATOMIC_SEQ_CST);
+#else
+ return __atomic_exchange_8(dst, val, __ATOMIC_SEQ_CST);
+#endif
+}
+#endif
+
/**
* The atomic counter structure.
*/
}
#endif
+/*------------------------ 128 bit atomic operations -------------------------*/
+
+/**
+ * 128-bit integer structure.
+ */
+RTE_STD_C11
+typedef struct {
+ RTE_STD_C11
+ union {
+ uint64_t val[2];
+#ifdef RTE_ARCH_64
+ __extension__ __int128 int128;
+#endif
+ };
+} __rte_aligned(16) rte_int128_t;
+
+#ifdef __DOXYGEN__
+
+/**
+ * An atomic compare and set function used by the mutex functions.
+ * (Atomically) Equivalent to:
+ * @code
+ * if (*dst == *exp)
+ * *dst = *src
+ * else
+ * *exp = *dst
+ * @endcode
+ *
+ * @note This function is currently available for the x86-64 and aarch64
+ * platforms.
+ *
+ * @note The success and failure arguments must be one of the __ATOMIC_* values
+ * defined in the C++11 standard. For details on their behavior, refer to the
+ * standard.
+ *
+ * @param dst
+ * The destination into which the value will be written.
+ * @param exp
+ * Pointer to the expected value. If the operation fails, this memory is
+ * updated with the actual value.
+ * @param src
+ * Pointer to the new value.
+ * @param weak
+ * A value of true allows the comparison to spuriously fail and allows the
+ * 'exp' update to occur non-atomically (i.e. a torn read may occur).
+ * Implementations may ignore this argument and only implement the strong
+ * variant.
+ * @param success
+ * If successful, the operation's memory behavior conforms to this (or a
+ * stronger) model.
+ * @param failure
+ * If unsuccessful, the operation's memory behavior conforms to this (or a
+ * stronger) model. This argument cannot be __ATOMIC_RELEASE,
+ * __ATOMIC_ACQ_REL, or a stronger model than success.
+ * @return
+ * Non-zero on success; 0 on failure.
+ */
+__rte_experimental
+static inline int
+rte_atomic128_cmp_exchange(rte_int128_t *dst,
+ rte_int128_t *exp,
+ const rte_int128_t *src,
+ unsigned int weak,
+ int success,
+ int failure);
+
+#endif /* __DOXYGEN__ */
+
#endif /* _RTE_ATOMIC_H_ */