17 files changed, 91 insertions, 40 deletions

diff --git a/lib/librte_eal/common/include/arch/ppc_64/rte_atomic.h b/lib/librte_eal/common/include/arch/ppc_64/rte_atomic.h
index ce38350b..797381c0 100644
--- a/lib/librte_eal/common/include/arch/ppc_64/rte_atomic.h
+++ b/lib/librte_eal/common/include/arch/ppc_64/rte_atomic.h
@@ -63,11 +63,7 @@ extern "C" {
  * Guarantees that the STORE operations generated before the barrier
  * occur before the STORE operations generated after.
  */
-#ifdef RTE_ARCH_64
-#define	rte_wmb() asm volatile("lwsync" : : : "memory")
-#else
 #define	rte_wmb() asm volatile("sync" : : : "memory")
-#endif
 
 /**
  * Read memory barrier.
@@ -75,11 +71,7 @@ extern "C" {
  * Guarantees that the LOAD operations generated before the barrier
  * occur before the LOAD operations generated after.
  */
-#ifdef RTE_ARCH_64
-#define	rte_rmb() asm volatile("lwsync" : : : "memory")
-#else
 #define	rte_rmb() asm volatile("sync" : : : "memory")
-#endif
 
 #define rte_smp_mb() rte_mb()
 
diff --git a/lib/librte_eal/common/include/generic/rte_cycles.h b/lib/librte_eal/common/include/generic/rte_cycles.h
index ac379e87..d318b91a 100644
--- a/lib/librte_eal/common/include/generic/rte_cycles.h
+++ b/lib/librte_eal/common/include/generic/rte_cycles.h
@@ -173,7 +173,7 @@ rte_delay_us_sleep(unsigned int us);
  *
  * @param userfunc
  *   User function which replaces rte_delay_us. rte_delay_us_block restores
- *   buildin block delay function.
+ *   builtin block delay function.
  */
 void rte_delay_us_callback_register(void(*userfunc)(unsigned int));
 
diff --git a/lib/librte_eal/common/include/generic/rte_rwlock.h b/lib/librte_eal/common/include/generic/rte_rwlock.h
index 5751a0e6..2c284f0b 100644
--- a/lib/librte_eal/common/include/generic/rte_rwlock.h
+++ b/lib/librte_eal/common/include/generic/rte_rwlock.h
@@ -64,14 +64,14 @@ rte_rwlock_read_lock(rte_rwlock_t *rwl)
 	int success = 0;
 
 	while (success == 0) {
-		x = rwl->cnt;
+		x = __atomic_load_n(&rwl->cnt, __ATOMIC_RELAXED);
 		/* write lock is held */
 		if (x < 0) {
 			rte_pause();
 			continue;
 		}
-		success = rte_atomic32_cmpset((volatile uint32_t *)&rwl->cnt,
-					      (uint32_t)x, (uint32_t)(x + 1));
+		success = __atomic_compare_exchange_n(&rwl->cnt, &x, x + 1, 1,
+					__ATOMIC_ACQUIRE, __ATOMIC_RELAXED);
 	}
 }
 
@@ -84,7 +84,7 @@ rte_rwlock_read_lock(rte_rwlock_t *rwl)
 static inline void
 rte_rwlock_read_unlock(rte_rwlock_t *rwl)
 {
-	rte_atomic32_dec((rte_atomic32_t *)(intptr_t)&rwl->cnt);
+	__atomic_fetch_sub(&rwl->cnt, 1, __ATOMIC_RELEASE);
 }
 
 /**
@@ -100,14 +100,14 @@ rte_rwlock_write_lock(rte_rwlock_t *rwl)
 	int success = 0;
 
 	while (success == 0) {
-		x = rwl->cnt;
+		x = __atomic_load_n(&rwl->cnt, __ATOMIC_RELAXED);
 		/* a lock is held */
 		if (x != 0) {
 			rte_pause();
 			continue;
 		}
-		success = rte_atomic32_cmpset((volatile uint32_t *)&rwl->cnt,
-					      0, (uint32_t)-1);
+		success = __atomic_compare_exchange_n(&rwl->cnt, &x, -1, 1,
+					__ATOMIC_ACQUIRE, __ATOMIC_RELAXED);
 	}
 }
 
@@ -120,7 +120,7 @@ rte_rwlock_write_lock(rte_rwlock_t *rwl)
 static inline void
 rte_rwlock_write_unlock(rte_rwlock_t *rwl)
 {
-	rte_atomic32_inc((rte_atomic32_t *)(intptr_t)&rwl->cnt);
+	__atomic_store_n(&rwl->cnt, 0, __ATOMIC_RELEASE);
 }
 
 /**
diff --git a/lib/librte_eal/common/include/generic/rte_spinlock.h b/lib/librte_eal/common/include/generic/rte_spinlock.h
index c4c3fc31..87ae7a4f 100644
--- a/lib/librte_eal/common/include/generic/rte_spinlock.h
+++ b/lib/librte_eal/common/include/generic/rte_spinlock.h
@@ -61,9 +61,14 @@ rte_spinlock_lock(rte_spinlock_t *sl);
 static inline void
 rte_spinlock_lock(rte_spinlock_t *sl)
 {
-	while (__sync_lock_test_and_set(&sl->locked, 1))
-		while(sl->locked)
+	int exp = 0;
+
+	while (!__atomic_compare_exchange_n(&sl->locked, &exp, 1, 0,
+				__ATOMIC_ACQUIRE, __ATOMIC_RELAXED)) {
+		while (__atomic_load_n(&sl->locked, __ATOMIC_RELAXED))
 			rte_pause();
+		exp = 0;
+	}
 }
 #endif
 
@@ -80,7 +85,7 @@ rte_spinlock_unlock (rte_spinlock_t *sl);
 static inline void
 rte_spinlock_unlock (rte_spinlock_t *sl)
 {
-	__sync_lock_release(&sl->locked);
+	__atomic_store_n(&sl->locked, 0, __ATOMIC_RELEASE);
 }
 #endif
 
@@ -99,7 +104,10 @@ rte_spinlock_trylock (rte_spinlock_t *sl);
 static inline int
 rte_spinlock_trylock (rte_spinlock_t *sl)
 {
-	return __sync_lock_test_and_set(&sl->locked,1) == 0;
+	int exp = 0;
+	return __atomic_compare_exchange_n(&sl->locked, &exp, 1,
+				0, /* disallow spurious failure */
+				__ATOMIC_ACQUIRE, __ATOMIC_RELAXED);
 }
 #endif
 
@@ -113,7 +121,7 @@ rte_spinlock_trylock (rte_spinlock_t *sl)
  */
 static inline int rte_spinlock_is_locked (rte_spinlock_t *sl)
 {
-	return sl->locked;
+	return __atomic_load_n(&sl->locked, __ATOMIC_ACQUIRE);
 }
 
 /**
diff --git a/lib/librte_eal/common/include/generic/rte_vect.h b/lib/librte_eal/common/include/generic/rte_vect.h
index 11c6475b..3fc47979 100644
--- a/lib/librte_eal/common/include/generic/rte_vect.h
+++ b/lib/librte_eal/common/include/generic/rte_vect.h
@@ -55,7 +55,7 @@ typedef uint16_t rte_v128u16_t __attribute__((vector_size(16), aligned(16)));
 /**
  * 128 bits vector size to use with unsigned 32 bits elements.
  *
- * a = (rte_v128u32_t){ a0, a1, a2, a3, a4 }
+ * a = (rte_v128u32_t){ a0, a1, a2, a3 }
  */
 typedef uint32_t rte_v128u32_t __attribute__((vector_size(16), aligned(16)));
 
diff --git a/lib/librte_eal/common/include/rte_class.h b/lib/librte_eal/common/include/rte_class.h
index 276c91e9..856d09b2 100644
--- a/lib/librte_eal/common/include/rte_class.h
+++ b/lib/librte_eal/common/include/rte_class.h
@@ -15,7 +15,7 @@
  *
  * A device class defines the type of function a device
  * will be used for e.g.: Ethernet adapter (eth),
- * cryptographic coprocessor (crypto), etc.
+ * cryptographic co-processor (crypto), etc.
  */
 
 #ifdef __cplusplus
diff --git a/lib/librte_eal/common/include/rte_common.h b/lib/librte_eal/common/include/rte_common.h
index 66cdf60b..48bf28ca 100644
--- a/lib/librte_eal/common/include/rte_common.h
+++ b/lib/librte_eal/common/include/rte_common.h
@@ -340,7 +340,7 @@ rte_is_power_of_2(uint32_t n)
  * Aligns input parameter to the next power of 2
  *
  * @param x
- *   The integer value to algin
+ *   The integer value to align
  *
  * @return
  *   Input parameter aligned to the next power of 2
@@ -358,7 +358,7 @@ rte_align32pow2(uint32_t x)
  * Aligns input parameter to the previous power of 2
  *
  * @param x
- *   The integer value to algin
+ *   The integer value to align
  *
  * @return
  *   Input parameter aligned to the previous power of 2
diff --git a/lib/librte_eal/common/include/rte_eal.h b/lib/librte_eal/common/include/rte_eal.h
index a0cedd57..9951228e 100644
--- a/lib/librte_eal/common/include/rte_eal.h
+++ b/lib/librte_eal/common/include/rte_eal.h
@@ -228,6 +228,13 @@ struct rte_mp_reply {
  *
  * As we create  socket channel for primary/secondary communication, use
  * this function typedef to register action for coming messages.
+ *
+ * @note When handling IPC request callbacks, the reply must be sent even in
+ *   cases of error handling. Simply returning success or failure will *not*
+ *   send a response to the requestor.
+ *   Implementation of error signalling mechanism is up to the application.
+ *
+ * @note No memory allocations should take place inside the callback.
  */
 typedef int (*rte_mp_t)(const struct rte_mp_msg *msg, const void *peer);
 
@@ -237,6 +244,13 @@ typedef int (*rte_mp_t)(const struct rte_mp_msg *msg, const void *peer);
  * As we create socket channel for primary/secondary communication, use
  * this function typedef to register action for coming responses to asynchronous
  * requests.
+ *
+ * @note When handling IPC request callbacks, the reply must be sent even in
+ *   cases of error handling. Simply returning success or failure will *not*
+ *   send a response to the requestor.
+ *   Implementation of error signalling mechanism is up to the application.
+ *
+ * @note No memory allocations should take place inside the callback.
  */
 typedef int (*rte_mp_async_reply_t)(const struct rte_mp_msg *request,
 		const struct rte_mp_reply *reply);
@@ -287,7 +301,7 @@ rte_mp_action_unregister(const char *name);
  *
  * Send a message to the peer process.
  *
- * This function will send a message which will be responsed by the action
+ * This function will send a message which will be responded by the action
  * identified by name in the peer process.
  *
  * @param msg
@@ -311,6 +325,9 @@ rte_mp_sendmsg(struct rte_mp_msg *msg);
  *
  * @note The caller is responsible to free reply->replies.
  *
+ * @note This API must not be used inside memory-related or IPC callbacks, and
+ *   no memory allocations should take place inside such callback.
+ *
  * @param req
  *   The req argument contains the customized request message.
  *
@@ -364,6 +381,11 @@ rte_mp_request_async(struct rte_mp_msg *req, const struct timespec *ts,
  * This function will send a reply message in response to a request message
  * received previously.
  *
+ * @note When handling IPC request callbacks, the reply must be sent even in
+ *   cases of error handling. Simply returning success or failure will *not*
+ *   send a response to the requestor.
+ *   Implementation of error signalling mechanism is up to the application.
+ *
  * @param msg
  *   The msg argument contains the customized message.
  *
@@ -424,7 +446,7 @@ rte_set_application_usage_hook(rte_usage_hook_t usage_func);
 #define RTE_EAL_TAILQ_RWLOCK         (&rte_eal_get_configuration()->mem_config->qlock)
 
 /**
- * macro to get the multiple lock of mempool shared by mutiple-instance
+ * macro to get the multiple lock of mempool shared by multiple-instance
  */
 #define RTE_EAL_MEMPOOL_RWLOCK            (&rte_eal_get_configuration()->mem_config->mplock)
 
diff --git a/lib/librte_eal/common/include/rte_lcore.h b/lib/librte_eal/common/include/rte_lcore.h
index 6e09d918..dea17f50 100644
--- a/lib/librte_eal/common/include/rte_lcore.h
+++ b/lib/librte_eal/common/include/rte_lcore.h
@@ -23,10 +23,18 @@ extern "C" {
 #define LCORE_ID_ANY     UINT32_MAX       /**< Any lcore. */
 
 #if defined(__linux__)
-	typedef	cpu_set_t rte_cpuset_t;
+typedef	cpu_set_t rte_cpuset_t;
+#define RTE_CPU_AND(dst, src1, src2) CPU_AND(dst, src1, src2)
 #elif defined(__FreeBSD__)
 #include <pthread_np.h>
-	typedef cpuset_t rte_cpuset_t;
+typedef cpuset_t rte_cpuset_t;
+#define RTE_CPU_AND(dst, src1, src2) do \
+{ \
+	cpuset_t tmp; \
+	CPU_COPY(src1, &tmp); \
+	CPU_AND(&tmp, src2); \
+	CPU_COPY(&tmp, dst); \
+} while (0)
 #endif
 
 /**
@@ -280,8 +288,9 @@ int rte_thread_setname(pthread_t id, const char *name);
  * Create a control thread.
  *
  * Wrapper to pthread_create(), pthread_setname_np() and
- * pthread_setaffinity_np(). The dataplane and service lcores are
- * excluded from the affinity of the new thread.
+ * pthread_setaffinity_np(). The affinity of the new thread is based
+ * on the CPU affinity retrieved at the time rte_eal_init() was called,
+ * the dataplane and service lcores are then excluded.
  *
  * @param thread
  *   Filled with the thread id of the new created thread.
diff --git a/lib/librte_eal/common/include/rte_log.h b/lib/librte_eal/common/include/rte_log.h
index 2f789cb9..213043c4 100644
--- a/lib/librte_eal/common/include/rte_log.h
+++ b/lib/librte_eal/common/include/rte_log.h
@@ -36,7 +36,7 @@ struct rte_logs {
 	struct rte_log_dynamic_type *dynamic_types;
 };
 
-/** Global log informations */
+/** Global log information */
 extern struct rte_logs rte_logs;
 
 /* SDK log type */
diff --git a/lib/librte_eal/common/include/rte_malloc.h b/lib/librte_eal/common/include/rte_malloc.h
index 54a12467..e0be13ca 100644
--- a/lib/librte_eal/common/include/rte_malloc.h
+++ b/lib/librte_eal/common/include/rte_malloc.h
@@ -111,7 +111,7 @@ rte_calloc(const char *type, size_t num, size_t size, unsigned align);
 /**
  * Replacement function for realloc(), using huge-page memory. Reserved area
  * memory is resized, preserving contents. In NUMA systems, the new area
- * resides on the same NUMA socket as the old area.
+ * may not reside on the same NUMA node as the old one.
  *
  * @param ptr
  *   Pointer to already allocated memory
diff --git a/lib/librte_eal/common/include/rte_service.h b/lib/librte_eal/common/include/rte_service.h
index 34b41aff..11f67350 100644
--- a/lib/librte_eal/common/include/rte_service.h
+++ b/lib/librte_eal/common/include/rte_service.h
@@ -337,7 +337,7 @@ int32_t rte_service_set_stats_enable(uint32_t id, int32_t enable);
 int32_t rte_service_lcore_list(uint32_t array[], uint32_t n);
 
 /**
- * Get the numer of services running on the supplied lcore.
+ * Get the number of services running on the supplied lcore.
  *
  * @param lcore Id of the service core.
  * @retval >=0 Number of services registered to this core.
diff --git a/lib/librte_eal/common/include/rte_string_fns.h b/lib/librte_eal/common/include/rte_string_fns.h
index 9a2a1ff9..35c6b003 100644
--- a/lib/librte_eal/common/include/rte_string_fns.h
+++ b/lib/librte_eal/common/include/rte_string_fns.h
@@ -59,10 +59,25 @@ rte_strlcpy(char *dst, const char *src, size_t size)
 	return (size_t)snprintf(dst, size, "%s", src);
 }
 
+/**
+ * @internal
+ * DPDK-specific version of strlcat for systems without
+ * libc or libbsd copies of the function
+ */
+static inline size_t
+rte_strlcat(char *dst, const char *src, size_t size)
+{
+	size_t l = strnlen(dst, size);
+	if (l < size)
+		return l + rte_strlcpy(&dst[l], src, size - l);
+	return l + strlen(src);
+}
+
 /* pull in a strlcpy function */
 #ifdef RTE_EXEC_ENV_BSDAPP
 #ifndef __BSD_VISIBLE /* non-standard functions are hidden */
 #define strlcpy(dst, src, size) rte_strlcpy(dst, src, size)
+#define strlcat(dst, src, size) rte_strlcat(dst, src, size)
 #endif
 
 #else /* non-BSD platforms */
@@ -71,6 +86,7 @@ rte_strlcpy(char *dst, const char *src, size_t size)
 
 #else /* no BSD header files, create own */
 #define strlcpy(dst, src, size) rte_strlcpy(dst, src, size)
+#define strlcat(dst, src, size) rte_strlcat(dst, src, size)
 
 #endif /* RTE_USE_LIBBSD */
 #endif /* BSDAPP */
diff --git a/lib/librte_eal/common/include/rte_tailq.h b/lib/librte_eal/common/include/rte_tailq.h
index 9b01abb2..b6fe4e5f 100644
--- a/lib/librte_eal/common/include/rte_tailq.h
+++ b/lib/librte_eal/common/include/rte_tailq.h
@@ -53,7 +53,7 @@ struct rte_tailq_elem {
 };
 
 /**
- * Return the first tailq entry casted to the right struct.
+ * Return the first tailq entry cast to the right struct.
  */
 #define RTE_TAILQ_CAST(tailq_entry, struct_name) \
 	(struct struct_name *)&(tailq_entry)->tailq_head
diff --git a/lib/librte_eal/common/include/rte_uuid.h b/lib/librte_eal/common/include/rte_uuid.h
index 2c846b5f..16bbed32 100644
--- a/lib/librte_eal/common/include/rte_uuid.h
+++ b/lib/librte_eal/common/include/rte_uuid.h
@@ -43,7 +43,7 @@ extern "C" {
 #include <stdbool.h>
 
 /**
- * Struct describing a Universal Unique Identifer
+ * Struct describing a Universal Unique Identifier
  */
 typedef unsigned char rte_uuid_t[16];
 
@@ -105,7 +105,7 @@ int	rte_uuid_compare(const rte_uuid_t a, const rte_uuid_t b);
  * @param uu
  *    Destination UUID
  * @return
- *    Returns 0 on succes, and -1 if string is not a valid UUID.
+ *    Returns 0 on success, and -1 if string is not a valid UUID.
  */
 int	rte_uuid_parse(const char *in, rte_uuid_t uu);
 
diff --git a/lib/librte_eal/common/include/rte_version.h b/lib/librte_eal/common/include/rte_version.h
index b4c6dd3c..7c0b13b5 100644
--- a/lib/librte_eal/common/include/rte_version.h
+++ b/lib/librte_eal/common/include/rte_version.h
@@ -37,7 +37,7 @@ extern "C" {
 /**
  * Patch level number i.e. the z in yy.mm.z
  */
-#define RTE_VER_MINOR 1
+#define RTE_VER_MINOR 2
 
 /**
  * Extra string to be appended to version number
diff --git a/lib/librte_eal/common/include/rte_vfio.h b/lib/librte_eal/common/include/rte_vfio.h
index cae96fab..d837f1e7 100644
--- a/lib/librte_eal/common/include/rte_vfio.h
+++ b/lib/librte_eal/common/include/rte_vfio.h
@@ -178,7 +178,7 @@ int rte_vfio_noiommu_is_enabled(void);
  * an error on BSD.
  *
  * @param vfio_group_fd
- *   VFIO Grouup FD.
+ *   VFIO Group FD.
  *
  * @return
  *   0 on success.
@@ -291,6 +291,10 @@ rte_vfio_get_group_fd(int iommu_group_num);
  *       containers by default, user needs to manage DMA mappings for
  *       any container created by this API.
  *
+ * @note When creating containers using this API, the container will only be
+ *       available in the process that has created it. Sharing containers and
+ *       devices between multiple processes is not supported.
+ *
  * @return
  *   the container fd if successful
  *   <0 if failed