[dpdk-dev] [PATCH] ring: relax alignment constraint on ring structure

[Olivier Matz]

The initial objective of
commit d9f0d3a1ffd4 ("ring: remove split cacheline build setting")
was to add an empty cache line betwee, the producer and consumer
data (on platform with cache line size = 64B), preventing from
having them on adjacent cache lines.

Following discussion on the mailing list, it appears that this
also imposes an alignment constraint that is not required.

This patch removes the extra alignment constraint and adds the
empty cache lines using padding fields in the structure. The
size of rte_ring structure and the offset of the fields remain
the same on platforms with cache line size = 64B:

  rte_ring = 384
  rte_ring.name = 0
  rte_ring.flags = 32
  rte_ring.memzone = 40
  rte_ring.size = 48
  rte_ring.mask = 52
  rte_ring.prod = 128
  rte_ring.cons = 256

But it has an impact on platform where cache line size is 128B:

  rte_ring = 384        -> 768
  rte_ring.name = 0
  rte_ring.flags = 32
  rte_ring.memzone = 40
  rte_ring.size = 48
  rte_ring.mask = 52
  rte_ring.prod = 128   -> 256
  rte_ring.cons = 256   -> 512

Link: http://dpdk.org/dev/patchwork/patch/25039/
Suggested-by: Konstantin Ananyev <konstantin.ananyev at intel.com>
Signed-off-by: Olivier Matz <olivier.matz at 6wind.com>
---
 doc/guides/rel_notes/deprecation.rst   |  6 ------
 doc/guides/rel_notes/release_18_05.rst |  8 +++++++-
 lib/librte_ring/Makefile               |  2 +-
 lib/librte_ring/rte_ring.h             | 16 ++++++----------
 4 files changed, 14 insertions(+), 18 deletions(-)

diff --git a/doc/guides/rel_notes/deprecation.rst b/doc/guides/rel_notes/deprecation.rst
index 40448961a..84e153461 100644
--- a/doc/guides/rel_notes/deprecation.rst
+++ b/doc/guides/rel_notes/deprecation.rst
@@ -139,9 +139,3 @@ Deprecation Notices
   required the previous behavior can be configured using existing flow
   director APIs. There is no ABI/API break. This change will just remove a
   global configuration setting and require explicit configuration.
-
-* ring: The alignment constraints on the ring structure will be relaxed
-  to one cache line instead of two, and an empty cache line padding will
-  be added between the producer and consumer structures. The size of the
-  structure and the offset of the fields will remain the same on
-  platforms with 64B cache line, but will change on other platforms.
diff --git a/doc/guides/rel_notes/release_18_05.rst b/doc/guides/rel_notes/release_18_05.rst
index 9cc77f893..4d0276f1d 100644
--- a/doc/guides/rel_notes/release_18_05.rst
+++ b/doc/guides/rel_notes/release_18_05.rst
@@ -86,6 +86,12 @@ ABI Changes
    Also, make sure to start the actual text at the margin.
    =========================================================
 
+* ring: the alignment constraints on the ring structure has been relaxed
+  to one cache line instead of two, and an empty cache line padding is
+  added between the producer and consumer structures. The size of the
+  structure and the offset of the fields remains the same on platforms
+  with 64B cache line, but changes on other platforms.
+
 
 Removed Items
 -------------
@@ -176,7 +182,7 @@ The libraries prepended with a plus sign were incremented in this version.
      librte_power.so.1
      librte_rawdev.so.1
      librte_reorder.so.1
-     librte_ring.so.1
+   + librte_ring.so.2
      librte_sched.so.1
      librte_security.so.1
      librte_table.so.3
diff --git a/lib/librte_ring/Makefile b/lib/librte_ring/Makefile
index bde8907d6..21a36770d 100644
--- a/lib/librte_ring/Makefile
+++ b/lib/librte_ring/Makefile
@@ -11,7 +11,7 @@ LDLIBS += -lrte_eal
 
 EXPORT_MAP := rte_ring_version.map
 
-LIBABIVER := 1
+LIBABIVER := 2
 
 # all source are stored in SRCS-y
 SRCS-$(CONFIG_RTE_LIBRTE_RING) := rte_ring.c
diff --git a/lib/librte_ring/rte_ring.h b/lib/librte_ring/rte_ring.h
index 253cdc96a..d3d3f7f97 100644
--- a/lib/librte_ring/rte_ring.h
+++ b/lib/librte_ring/rte_ring.h
@@ -62,14 +62,6 @@ enum rte_ring_queue_behavior {
 
 struct rte_memzone; /* forward declaration, so as not to require memzone.h */
 
-#if RTE_CACHE_LINE_SIZE < 128
-#define PROD_ALIGN (RTE_CACHE_LINE_SIZE * 2)
-#define CONS_ALIGN (RTE_CACHE_LINE_SIZE * 2)
-#else
-#define PROD_ALIGN RTE_CACHE_LINE_SIZE
-#define CONS_ALIGN RTE_CACHE_LINE_SIZE
-#endif
-
 /* structure to hold a pair of head/tail values and other metadata */
 struct rte_ring_headtail {
 	volatile uint32_t head;  /**< Prod/consumer head. */
@@ -101,11 +93,15 @@ struct rte_ring {
 	uint32_t mask;           /**< Mask (size-1) of ring. */
 	uint32_t capacity;       /**< Usable size of ring */
 
+	char pad0 __rte_cache_aligned; /**< empty cache line */
+
 	/** Ring producer status. */
-	struct rte_ring_headtail prod __rte_aligned(PROD_ALIGN);
+	struct rte_ring_headtail prod __rte_cache_aligned;
+	char pad1 __rte_cache_aligned; /**< empty cache line */
 
 	/** Ring consumer status. */
-	struct rte_ring_headtail cons __rte_aligned(CONS_ALIGN);
+	struct rte_ring_headtail cons __rte_cache_aligned;
+	char pad2 __rte_cache_aligned; /**< empty cache line */
 };
 
 #define RING_F_SP_ENQ 0x0001 /**< The default enqueue is "single-producer". */
-- 
2.11.0