[dpdk-dev] [PATCH v6 10/33] eal/trace: implement trace memory allocation

[jerinj at marvell.com]

From: Jerin Jacob <jerinj at marvell.com>

Trace memory will be allocated per thread to enable lockless trace
events updates to the memory. The allocator will first attempt to
allocate from hugepage, if not available from hugepage then
fallback to malloc memory.

Later in the patches series, This API will be hooked to DPDK fastpath
and control plane thread creation API. It is possible for non
DPDK thread to use trace events, in that case, trace memory
will be allocated on the first event emission.

Signed-off-by: Jerin Jacob <jerinj at marvell.com>
---
 lib/librte_eal/common/eal_common_trace.c      | 97 +++++++++++++++++++
 .../common/eal_common_trace_utils.c           | 20 ++++
 lib/librte_eal/common/eal_trace.h             | 28 ++++++
 lib/librte_eal/include/rte_trace_point.h      |  9 ++
 .../include/rte_trace_point_provider.h        | 20 ++++
 lib/librte_eal/rte_eal_version.map            |  2 +
 6 files changed, 176 insertions(+)

diff --git a/lib/librte_eal/common/eal_common_trace.c b/lib/librte_eal/common/eal_common_trace.c
index 8bbc07c03..4c03a676a 100644
--- a/lib/librte_eal/common/eal_common_trace.c
+++ b/lib/librte_eal/common/eal_common_trace.c
@@ -16,6 +16,7 @@
 #include "eal_trace.h"
 
 RTE_DEFINE_PER_LCORE(volatile int, trace_point_sz);
+RTE_DEFINE_PER_LCORE(void *, trace_mem);
 static RTE_DEFINE_PER_LCORE(char, ctf_field[TRACE_CTF_FIELD_SIZE]);
 static RTE_DEFINE_PER_LCORE(int, ctf_count);
 
@@ -37,6 +38,9 @@ trace_list_head_get(void)
 int
 eal_trace_init(void)
 {
+	/* Trace memory should start with 8B aligned for natural alignment */
+	RTE_BUILD_BUG_ON((offsetof(struct __rte_trace_header, mem) % 8) != 0);
+
 	/* One of the Trace registration failed */
 	if (trace.register_errno) {
 		rte_errno = trace.register_errno;
@@ -83,6 +87,7 @@ eal_trace_fini(void)
 {
 	if (rte_trace_is_enabled() == false)
 		return;
+	trace_mem_per_thread_free();
 	trace_metadata_destroy();
 }
 
@@ -231,6 +236,98 @@ rte_trace_point_lookup(const char *name)
 	return NULL;
 }
 
+static inline size_t
+list_sz(uint32_t index)
+{
+	return sizeof(struct thread_mem_meta) * (index + 1);
+}
+
+void
+__rte_trace_mem_per_thread_alloc(void)
+{
+	struct trace *trace = trace_obj_get();
+	struct __rte_trace_header *header;
+	uint32_t count;
+
+	if (rte_trace_is_enabled() == false)
+		return;
+
+	if (RTE_PER_LCORE(trace_mem))
+		return;
+
+	rte_spinlock_lock(&trace->lock);
+
+	count = trace->nb_trace_mem_list;
+
+	/* Allocate room for storing the thread trace mem meta */
+	trace->lcore_meta = realloc(trace->lcore_meta, list_sz(count));
+
+	/* Provide dummy space for fastpath to consume */
+	if (trace->lcore_meta == NULL) {
+		trace_crit("trace mem meta memory realloc failed");
+		header = NULL; goto fail;
+	}
+
+	/* First attempt from huge page */
+	header = rte_malloc(NULL, trace_mem_sz(trace->buff_len), 8);
+	if (header) {
+		trace->lcore_meta[count].area = TRACE_AREA_HUGEPAGE;
+		goto found;
+	}
+
+	/* Second attempt from heap */
+	header = malloc(trace_mem_sz(trace->buff_len));
+	if (header == NULL) {
+		trace_crit("trace mem malloc attempt failed");
+		header = NULL; goto fail;
+
+	}
+
+	/* Second attempt from heap is success */
+	trace->lcore_meta[count].area = TRACE_AREA_HEAP;
+
+	/* Initialize the trace header */
+found:
+	header->offset = 0;
+	header->len = trace->buff_len;
+	header->stream_header.magic = TRACE_CTF_MAGIC;
+	rte_uuid_copy(header->stream_header.uuid, trace->uuid);
+	header->stream_header.lcore_id = rte_lcore_id();
+
+	/* Store the thread name */
+	char *name = header->stream_header.thread_name;
+	memset(name, 0, __RTE_TRACE_EMIT_STRING_LEN_MAX);
+	rte_thread_getname(pthread_self(), name,
+			   __RTE_TRACE_EMIT_STRING_LEN_MAX);
+
+	trace->lcore_meta[count].mem = header;
+	trace->nb_trace_mem_list++;
+fail:
+	RTE_PER_LCORE(trace_mem) = header;
+	rte_spinlock_unlock(&trace->lock);
+}
+
+void
+trace_mem_per_thread_free(void)
+{
+	struct trace *trace = trace_obj_get();
+	uint32_t count;
+	void *mem;
+
+	if (rte_trace_is_enabled() == false)
+		return;
+
+	rte_spinlock_lock(&trace->lock);
+	for (count = 0; count < trace->nb_trace_mem_list; count++) {
+		mem = trace->lcore_meta[count].mem;
+		if (trace->lcore_meta[count].area == TRACE_AREA_HUGEPAGE)
+			rte_free(mem);
+		else if (trace->lcore_meta[count].area == TRACE_AREA_HEAP)
+			free(mem);
+	}
+	rte_spinlock_unlock(&trace->lock);
+}
+
 int
 __rte_trace_point_register(rte_trace_point_t *handle, const char *name,
 			   void (*register_fn)(void))
diff --git a/lib/librte_eal/common/eal_common_trace_utils.c b/lib/librte_eal/common/eal_common_trace_utils.c
index f7700934b..de8d43661 100644
--- a/lib/librte_eal/common/eal_common_trace_utils.c
+++ b/lib/librte_eal/common/eal_common_trace_utils.c
@@ -14,6 +14,26 @@
 #include "eal_filesystem.h"
 #include "eal_trace.h"
 
+const char *
+trace_mode_to_string(enum rte_trace_mode mode)
+{
+	switch (mode) {
+	case RTE_TRACE_MODE_OVERWRITE: return "overwrite";
+	case RTE_TRACE_MODE_DISCARD: return "discard";
+	default: return "unknown";
+	}
+}
+
+const char *
+trace_area_to_string(enum trace_area_e area)
+{
+	switch (area) {
+	case TRACE_AREA_HEAP: return "heap";
+	case TRACE_AREA_HUGEPAGE: return "hugepage";
+	default: return "unknown";
+	}
+}
+
 static bool
 trace_entry_compare(const char *name)
 {
diff --git a/lib/librte_eal/common/eal_trace.h b/lib/librte_eal/common/eal_trace.h
index 8e8d1160e..e2538d24a 100644
--- a/lib/librte_eal/common/eal_trace.h
+++ b/lib/librte_eal/common/eal_trace.h
@@ -6,11 +6,16 @@
 #define __EAL_TRACE_H
 
 #include <rte_cycles.h>
+#include <rte_log.h>
+#include <rte_malloc.h>
 #include <rte_spinlock.h>
 #include <rte_trace.h>
 #include <rte_trace_point.h>
 #include <rte_uuid.h>
 
+#include "eal_private.h"
+#include "eal_thread.h"
+
 #define trace_err(fmt, args...)\
 	RTE_LOG(ERR, EAL, "%s():%u " fmt "\n",\
 		__func__, __LINE__, ## args)
@@ -23,6 +28,8 @@
 #define TRACE_DIR_STR_LEN (sizeof("YYYY-mm-dd-AM-HH-MM-SS") + TRACE_PREFIX_LEN)
 #define TRACE_CTF_FIELD_SIZE 384
 #define TRACE_POINT_NAME_SIZE 64
+#define TRACE_CTF_MAGIC 0xC1FC1FC1
+
 
 struct trace_point {
 	STAILQ_ENTRY(trace_point) next;
@@ -31,6 +38,16 @@ struct trace_point {
 	char ctf_field[TRACE_CTF_FIELD_SIZE];
 };
 
+enum trace_area_e {
+	TRACE_AREA_HEAP,
+	TRACE_AREA_HUGEPAGE,
+};
+
+struct thread_mem_meta {
+	void *mem;
+	enum trace_area_e area;
+};
+
 struct trace {
 	char dir[PATH_MAX];
 	int dir_offset;
@@ -40,6 +57,8 @@ struct trace {
 	rte_uuid_t uuid;
 	uint32_t buff_len;
 	uint32_t nb_trace_points;
+	uint32_t nb_trace_mem_list;
+	struct thread_mem_meta *lcore_meta;
 	uint64_t epoch_sec;
 	uint64_t epoch_nsec;
 	uint64_t uptime_ticks;
@@ -59,6 +78,12 @@ trace_id_get(rte_trace_point_t *trace)
 		__RTE_TRACE_FIELD_ID_SHIFT;
 }
 
+static inline size_t
+trace_mem_sz(uint32_t len)
+{
+	return len + sizeof(struct __rte_trace_header);
+}
+
 /* Trace object functions */
 struct trace *trace_obj_get(void);
 
@@ -67,12 +92,15 @@ STAILQ_HEAD(trace_point_head, trace_point);
 struct trace_point_head *trace_list_head_get(void);
 
 /* Util functions */
+const char *trace_mode_to_string(enum rte_trace_mode mode);
+const char *trace_area_to_string(enum trace_area_e area);
 bool trace_has_duplicate_entry(void);
 void trace_uuid_generate(void);
 int trace_metadata_create(void);
 void trace_metadata_destroy(void);
 int trace_mkdir(void);
 int trace_epoch_time_save(void);
+void trace_mem_per_thread_free(void);
 
 /* EAL interface */
 int eal_trace_init(void);
diff --git a/lib/librte_eal/include/rte_trace_point.h b/lib/librte_eal/include/rte_trace_point.h
index f9924225a..8e37f971e 100644
--- a/lib/librte_eal/include/rte_trace_point.h
+++ b/lib/librte_eal/include/rte_trace_point.h
@@ -227,6 +227,15 @@ __rte_trace_point_fp_is_enabled(void)
 #endif
 }
 
+/**
+ * @internal
+ *
+ * Allocate trace memory buffer per thread.
+ *
+ */
+__rte_experimental
+void __rte_trace_mem_per_thread_alloc(void);
+
 /**
  * @internal
  *
diff --git a/lib/librte_eal/include/rte_trace_point_provider.h b/lib/librte_eal/include/rte_trace_point_provider.h
index 45a113c0d..b8d727387 100644
--- a/lib/librte_eal/include/rte_trace_point_provider.h
+++ b/lib/librte_eal/include/rte_trace_point_provider.h
@@ -9,6 +9,10 @@
 #ifndef _RTE_TRACE_POINT_PROVIDER_H_
 #define _RTE_TRACE_POINT_PROVIDER_H_
 
+#include <rte_per_lcore.h>
+#include <rte_string_fns.h>
+#include <rte_uuid.h>
+
 #define __RTE_TRACE_EVENT_HEADER_ID_SHIFT (48)
 
 #define __RTE_TRACE_FIELD_SIZE_SHIFT 0
@@ -18,4 +22,20 @@
 #define __RTE_TRACE_FIELD_ENABLE_MASK (1ULL << 63)
 #define __RTE_TRACE_FIELD_ENABLE_DISCARD (1ULL << 62)
 
+struct __rte_trace_stream_header {
+	uint32_t magic;
+	rte_uuid_t uuid;
+	uint32_t lcore_id;
+	char thread_name[__RTE_TRACE_EMIT_STRING_LEN_MAX];
+} __rte_packed;
+
+struct __rte_trace_header {
+	uint32_t offset;
+	uint32_t len;
+	struct __rte_trace_stream_header stream_header;
+	uint8_t mem[];
+};
+
+RTE_DECLARE_PER_LCORE(void *, trace_mem);
+
 #endif /* _RTE_TRACE_POINT_PROVIDER_H_ */
diff --git a/lib/librte_eal/rte_eal_version.map b/lib/librte_eal/rte_eal_version.map
index 2e6aacc17..98e0f8413 100644
--- a/lib/librte_eal/rte_eal_version.map
+++ b/lib/librte_eal/rte_eal_version.map
@@ -337,7 +337,9 @@ EXPERIMENTAL {
 	rte_thread_is_intr;
 
 	# added in 20.05
+	__rte_trace_mem_per_thread_alloc;
 	__rte_trace_point_register;
+	per_lcore_trace_mem;
 	per_lcore_trace_point_sz;
 	rte_log_can_log;
 	rte_thread_getname;
-- 
2.25.1