New upstream version 16.11.5upstream/16.11.5

Change-Id: I47171042629a57c6958d50251351e668ca5f3d8b
Signed-off-by: Luca Boccassi <luca.boccassi@gmail.com>

10 files changed, 75 insertions, 22 deletions

diff --git a/lib/librte_eal/common/eal_common_memzone.c b/lib/librte_eal/common/eal_common_memzone.c
index 64f4e0ad..b58d85b7 100644
--- a/lib/librte_eal/common/eal_common_memzone.c
+++ b/lib/librte_eal/common/eal_common_memzone.c
@@ -236,7 +236,7 @@ memzone_reserve_aligned_thread_unsafe(const char *name, size_t len,
 		return NULL;
 	}
 
-	const struct malloc_elem *elem = malloc_elem_from_data(mz_addr);
+	struct malloc_elem *elem = malloc_elem_from_data(mz_addr);
 
 	/* fill the zone in config */
 	mz = get_next_free_memzone();
@@ -244,6 +244,7 @@ memzone_reserve_aligned_thread_unsafe(const char *name, size_t len,
 	if (mz == NULL) {
 		RTE_LOG(ERR, EAL, "%s(): Cannot find free memzone but there is room "
 				"in config!\n", __func__);
+		malloc_elem_free(elem);
 		rte_errno = ENOSPC;
 		return NULL;
 	}
diff --git a/lib/librte_eal/common/eal_common_pci_uio.c b/lib/librte_eal/common/eal_common_pci_uio.c
index 367a6816..6f91ff9c 100644
--- a/lib/librte_eal/common/eal_common_pci_uio.c
+++ b/lib/librte_eal/common/eal_common_pci_uio.c
@@ -117,7 +117,6 @@ pci_uio_map_resource(struct rte_pci_device *dev)
 
 	dev->intr_handle.fd = -1;
 	dev->intr_handle.uio_cfg_fd = -1;
-	dev->intr_handle.type = RTE_INTR_HANDLE_UNKNOWN;
 
 	/* secondary processes - use already recorded details */
 	if (rte_eal_process_type() != RTE_PROC_PRIMARY)
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 fb4fccb4..37f5eff2 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
@@ -64,9 +64,9 @@ extern "C" {
  * occur before the STORE operations generated after.
  */
 #ifdef RTE_ARCH_64
-#define	rte_wmb() {asm volatile("lwsync" : : : "memory"); }
+#define	rte_wmb() asm volatile("lwsync" : : : "memory")
 #else
-#define	rte_wmb() {asm volatile("sync" : : : "memory"); }
+#define	rte_wmb() asm volatile("sync" : : : "memory")
 #endif
 
 /**
@@ -76,9 +76,9 @@ extern "C" {
  * occur before the LOAD operations generated after.
  */
 #ifdef RTE_ARCH_64
-#define	rte_rmb() {asm volatile("lwsync" : : : "memory"); }
+#define	rte_rmb() asm volatile("lwsync" : : : "memory")
 #else
-#define	rte_rmb() {asm volatile("sync" : : : "memory"); }
+#define	rte_rmb() asm volatile("sync" : : : "memory")
 #endif
 
 #define rte_smp_mb() rte_mb()
diff --git a/lib/librte_eal/common/include/arch/x86/rte_atomic.h b/lib/librte_eal/common/include/arch/x86/rte_atomic.h
index 00b1cdf5..d12b679a 100644
--- a/lib/librte_eal/common/include/arch/x86/rte_atomic.h
+++ b/lib/librte_eal/common/include/arch/x86/rte_atomic.h
@@ -55,12 +55,52 @@ extern "C" {
 
 #define	rte_rmb() _mm_lfence()
 
-#define rte_smp_mb() rte_mb()
-
 #define rte_smp_wmb() rte_compiler_barrier()
 
 #define rte_smp_rmb() rte_compiler_barrier()
 
+/*
+ * From Intel Software Development Manual; Vol 3;
+ * 8.2.2 Memory Ordering in P6 and More Recent Processor Families:
+ * ...
+ * . Reads are not reordered with other reads.
+ * . Writes are not reordered with older reads.
+ * . Writes to memory are not reordered with other writes,
+ *   with the following exceptions:
+ *   . streaming stores (writes) executed with the non-temporal move
+ *     instructions (MOVNTI, MOVNTQ, MOVNTDQ, MOVNTPS, and MOVNTPD); and
+ *   . string operations (see Section 8.2.4.1).
+ *  ...
+ * . Reads may be reordered with older writes to different locations but not
+ * with older writes to the same location.
+ * . Reads or writes cannot be reordered with I/O instructions,
+ * locked instructions, or serializing instructions.
+ * . Reads cannot pass earlier LFENCE and MFENCE instructions.
+ * . Writes ... cannot pass earlier LFENCE, SFENCE, and MFENCE instructions.
+ * . LFENCE instructions cannot pass earlier reads.
+ * . SFENCE instructions cannot pass earlier writes ...
+ * . MFENCE instructions cannot pass earlier reads, writes ...
+ *
+ * As pointed by Java guys, that makes possible to use lock-prefixed
+ * instructions to get the same effect as mfence and on most modern HW
+ * that gives a better perfomance then using mfence:
+ * https://shipilev.net/blog/2014/on-the-fence-with-dependencies/
+ * Basic idea is to use lock prefixed add with some dummy memory location
+ * as the destination. From their experiments 128B(2 cache lines) below
+ * current stack pointer looks like a good candidate.
+ * So below we use that techinque for rte_smp_mb() implementation.
+ */
+
+static inline void __attribute__((always_inline))
+rte_smp_mb(void)
+{
+#ifdef RTE_ARCH_I686
+	asm volatile("lock addl $0, -128(%%esp); " ::: "memory");
+#else
+	asm volatile("lock addl $0, -128(%%rsp); " ::: "memory");
+#endif
+}
+
 /*------------------------- 16 bit atomic operations -------------------------*/
 
 #ifndef RTE_FORCE_INTRINSICS
diff --git a/lib/librte_eal/common/include/rte_debug.h b/lib/librte_eal/common/include/rte_debug.h
index cab6fb4c..ec1dce03 100644
--- a/lib/librte_eal/common/include/rte_debug.h
+++ b/lib/librte_eal/common/include/rte_debug.h
@@ -86,7 +86,7 @@ void rte_dump_registers(void);
 #endif
 #define	RTE_VERIFY(exp)	do {                                                  \
 	if (unlikely(!(exp)))                                                           \
-		rte_panic("line %d\tassert \"" #exp "\" failed\n", __LINE__); \
+		rte_panic("line %d\tassert \"%s\" failed\n", __LINE__, #exp); \
 } while (0)
 
 /*
diff --git a/lib/librte_eal/common/include/rte_version.h b/lib/librte_eal/common/include/rte_version.h
index e92737d2..4a9f4821 100644
--- a/lib/librte_eal/common/include/rte_version.h
+++ b/lib/librte_eal/common/include/rte_version.h
@@ -66,7 +66,7 @@ extern "C" {
 /**
  * Patch level number i.e. the z in yy.mm.z
  */
-#define RTE_VER_MINOR 4
+#define RTE_VER_MINOR 5
 
 /**
  * Extra string to be appended to version number
diff --git a/lib/librte_eal/common/malloc_elem.c b/lib/librte_eal/common/malloc_elem.c
index 77a86151..e2bd3ac2 100644
--- a/lib/librte_eal/common/malloc_elem.c
+++ b/lib/librte_eal/common/malloc_elem.c
@@ -98,6 +98,7 @@ elem_start_pt(struct malloc_elem *elem, size_t size, unsigned align,
 	if ((new_data_start & bmask) != ((end_pt - 1) & bmask)) {
 		end_pt = RTE_ALIGN_FLOOR(end_pt, bound);
 		new_data_start = RTE_ALIGN_FLOOR((end_pt - size), align);
+		end_pt = new_data_start + size;
 		if (((end_pt - 1) & bmask) != (new_data_start & bmask))
 			return NULL;
 	}
diff --git a/lib/librte_eal/common/malloc_heap.c b/lib/librte_eal/common/malloc_heap.c
index 267a4c6c..c731f1cd 100644
--- a/lib/librte_eal/common/malloc_heap.c
+++ b/lib/librte_eal/common/malloc_heap.c
@@ -178,12 +178,14 @@ malloc_heap_alloc(struct malloc_heap *heap,
  * Function to retrieve data for heap on given socket
  */
 int
-malloc_heap_get_stats(const struct malloc_heap *heap,
+malloc_heap_get_stats(struct malloc_heap *heap,
 		struct rte_malloc_socket_stats *socket_stats)
 {
 	size_t idx;
 	struct malloc_elem *elem;
 
+	rte_spinlock_lock(&heap->lock);
+
 	/* Initialise variables for heap */
 	socket_stats->free_count = 0;
 	socket_stats->heap_freesz_bytes = 0;
@@ -205,6 +207,8 @@ malloc_heap_get_stats(const struct malloc_heap *heap,
 	socket_stats->heap_allocsz_bytes = (socket_stats->heap_totalsz_bytes -
 			socket_stats->heap_freesz_bytes);
 	socket_stats->alloc_count = heap->alloc_count;
+
+	rte_spinlock_unlock(&heap->lock);
 	return 0;
 }
 
diff --git a/lib/librte_eal/common/malloc_heap.h b/lib/librte_eal/common/malloc_heap.h
index 3ccbef0f..3b1166f0 100644
--- a/lib/librte_eal/common/malloc_heap.h
+++ b/lib/librte_eal/common/malloc_heap.h
@@ -57,7 +57,7 @@ malloc_heap_alloc(struct malloc_heap *heap,	const char *type, size_t size,
 		unsigned flags, size_t align, size_t bound);
 
 int
-malloc_heap_get_stats(const struct malloc_heap *heap,
+malloc_heap_get_stats(struct malloc_heap *heap,
 		struct rte_malloc_socket_stats *socket_stats);
 
 int
diff --git a/lib/librte_eal/common/rte_keepalive.c b/lib/librte_eal/common/rte_keepalive.c
index 9765d1bd..4625fab0 100644
--- a/lib/librte_eal/common/rte_keepalive.c
+++ b/lib/librte_eal/common/rte_keepalive.c
@@ -42,8 +42,12 @@
 
 struct rte_keepalive {
 	/** Core Liveness. */
-	enum rte_keepalive_state __rte_cache_aligned state_flags[
-		RTE_KEEPALIVE_MAXCORES];
+	struct {
+		/*
+		 * Each element must be cache aligned to prevent false sharing.
+		 */
+		enum rte_keepalive_state core_state __rte_cache_aligned;
+	} live_data[RTE_KEEPALIVE_MAXCORES];
 
 	/** Last-seen-alive timestamps */
 	uint64_t last_alive[RTE_KEEPALIVE_MAXCORES];
@@ -96,19 +100,22 @@ rte_keepalive_dispatch_pings(__rte_unused void *ptr_timer,
 		if (keepcfg->active_cores[idx_core] == 0)
 			continue;
 
-		switch (keepcfg->state_flags[idx_core]) {
+		switch (keepcfg->live_data[idx_core].core_state) {
 		case RTE_KA_STATE_UNUSED:
 			break;
 		case RTE_KA_STATE_ALIVE: /* Alive */
-			keepcfg->state_flags[idx_core] = RTE_KA_STATE_MISSING;
+			keepcfg->live_data[idx_core].core_state =
+			    RTE_KA_STATE_MISSING;
 			keepcfg->last_alive[idx_core] = rte_rdtsc();
 			break;
 		case RTE_KA_STATE_MISSING: /* MIA */
 			print_trace("Core MIA. ", keepcfg, idx_core);
-			keepcfg->state_flags[idx_core] = RTE_KA_STATE_DEAD;
+			keepcfg->live_data[idx_core].core_state =
+			    RTE_KA_STATE_DEAD;
 			break;
 		case RTE_KA_STATE_DEAD: /* Dead */
-			keepcfg->state_flags[idx_core] = RTE_KA_STATE_GONE;
+			keepcfg->live_data[idx_core].core_state =
+			    RTE_KA_STATE_GONE;
 			print_trace("Core died. ", keepcfg, idx_core);
 			if (keepcfg->callback)
 				keepcfg->callback(
@@ -119,7 +126,8 @@ rte_keepalive_dispatch_pings(__rte_unused void *ptr_timer,
 		case RTE_KA_STATE_GONE: /* Buried */
 			break;
 		case RTE_KA_STATE_DOZING: /* Core going idle */
-			keepcfg->state_flags[idx_core] = RTE_KA_STATE_SLEEP;
+			keepcfg->live_data[idx_core].core_state =
+			    RTE_KA_STATE_SLEEP;
 			keepcfg->last_alive[idx_core] = rte_rdtsc();
 			break;
 		case RTE_KA_STATE_SLEEP: /* Idled core */
@@ -129,7 +137,7 @@ rte_keepalive_dispatch_pings(__rte_unused void *ptr_timer,
 			keepcfg->relay_callback(
 				keepcfg->relay_callback_data,
 				idx_core,
-				keepcfg->state_flags[idx_core],
+				keepcfg->live_data[idx_core].core_state,
 				keepcfg->last_alive[idx_core]
 				);
 	}
@@ -173,11 +181,11 @@ rte_keepalive_register_core(struct rte_keepalive *keepcfg, const int id_core)
 void
 rte_keepalive_mark_alive(struct rte_keepalive *keepcfg)
 {
-	keepcfg->state_flags[rte_lcore_id()] = RTE_KA_STATE_ALIVE;
+	keepcfg->live_data[rte_lcore_id()].core_state = RTE_KA_STATE_ALIVE;
 }
 
 void
 rte_keepalive_mark_sleep(struct rte_keepalive *keepcfg)
 {
-	keepcfg->state_flags[rte_lcore_id()] = RTE_KA_STATE_DOZING;
+	keepcfg->live_data[rte_lcore_id()].core_state = RTE_KA_STATE_DOZING;
 }