[PATCH v6 5/7] eal: provide option to use compiler memcpy instead of RTE

[Mattias Rönnblom]

Provide build option to have functions in <rte_memcpy.h> delegate to
the standard compiler/libc memcpy(), instead of using the various
custom DPDK, handcrafted, per-architecture rte_memcpy()
implementations.

A new meson build option 'use_cc_memcpy' is added. By default, the
traditional, custom DPDK rte_memcpy() implementation is used.

The performance benefits of the custom DPDK rte_memcpy()
implementations have been diminishing with every compiler release, and
with current toolchains the use of a custom memcpy() implementation
may even be a liability.

An additional benefit of this change is that compilers and static
analysis tools have an easier time detecting incorrect usage of
rte_memcpy() (e.g., buffer overruns, or overlapping source and
destination buffers).

Signed-off-by: Mattias Rönnblom <mattias.ronnblom at ericsson.com>
Acked-by: Morten Brørup <mb at smartsharesystems.com>

---

PATCH v6:
 * Rebase for 24.11.

PATCH v5:
 o Take a more cautious approach, setting use_cc_memcpy to disabled by
   default.
 o Fix ARM build issue in case RTE_ARCH_ARM64_MEMCPY was set.
 o Use separate macros to indicate that the rte_memcpy() is implemented
   by the compiler, and that use_cc_memcpy is set, to avoid accidental
   <rte_build_config.h> #undefs.
 o Remove redundant rte_config.h includes.

PATCH:
 o Add entry in release notes.
 o Update meson help text.

RFC v3:
 o Fix missing #endif on loongarch.
 o PPC and RISCV now implemented, meaning all architectures are supported.
 o Unnecessary <rte_vect.h> include is removed from <rte_memcpy.h>.

RFC v2:
 * Fix bug where rte_memcpy.h was not installed on x86.
 * Made attempt to make Loongarch compile.
---
 config/meson.build                     |  1 +
 doc/guides/rel_notes/release_24_11.rst | 20 +++++++++
 lib/eal/arm/include/rte_memcpy.h       |  9 ++++
 lib/eal/include/generic/rte_memcpy.h   | 61 +++++++++++++++++++++++---
 lib/eal/loongarch/include/rte_memcpy.h | 54 +----------------------
 lib/eal/ppc/include/rte_memcpy.h       |  9 ++++
 lib/eal/riscv/include/rte_memcpy.h     | 54 +----------------------
 lib/eal/x86/include/meson.build        |  1 +
 lib/eal/x86/include/rte_memcpy.h       |  9 ++++
 meson_options.txt                      |  2 +
 10 files changed, 109 insertions(+), 111 deletions(-)

diff --git a/config/meson.build b/config/meson.build
index 8c8b019c25..456056628e 100644
--- a/config/meson.build
+++ b/config/meson.build
@@ -353,6 +353,7 @@ endforeach
 # set other values pulled from the build options
 dpdk_conf.set('RTE_MAX_ETHPORTS', get_option('max_ethports'))
 dpdk_conf.set('RTE_LIBEAL_USE_HPET', get_option('use_hpet'))
+dpdk_conf.set('RTE_USE_CC_MEMCPY', get_option('use_cc_memcpy'))
 dpdk_conf.set('RTE_ENABLE_STDATOMIC', get_option('enable_stdatomic'))
 dpdk_conf.set('RTE_ENABLE_TRACE_FP', get_option('enable_trace_fp'))
 dpdk_conf.set('RTE_PKTMBUF_HEADROOM', get_option('pkt_mbuf_headroom'))
diff --git a/doc/guides/rel_notes/release_24_11.rst b/doc/guides/rel_notes/release_24_11.rst
index 0ff70d9057..8be000294d 100644
--- a/doc/guides/rel_notes/release_24_11.rst
+++ b/doc/guides/rel_notes/release_24_11.rst
@@ -55,6 +55,26 @@ New Features
      Also, make sure to start the actual text at the margin.
      =======================================================
 
+* **Compiler memcpy replaces custom DPDK implementation.**
+
+  The memory copy functions of ``<rte_memcpy.h>`` now optionally
+  delegates to the standard memcpy() function, implemented by the
+  compiler and the C runtime (e.g., libc).
+
+  In this release of DPDK, the handcrafted, per-architecture memory
+  copy implementations are still the default. Compiler memcpy is
+  enabled by setting the new ``use_cc_memcpy`` build option to true.
+
+  The performance benefits of the custom DPDK rte_memcpy()
+  implementations have been diminishing with every new compiler
+  release, and with current toolchains the use of a custom memcpy()
+  implementation may even result in worse performance than the
+  standard memcpy().
+
+  An additional benefit of using compiler memcpy is that compilers and
+  static analysis tools have an easier time detecting incorrect usage
+  of rte_memcpy() (e.g., buffer overruns, or overlapping source and
+  destination buffers).
 
 Removed Items
 -------------
diff --git a/lib/eal/arm/include/rte_memcpy.h b/lib/eal/arm/include/rte_memcpy.h
index 47dea9a8cc..5d2ea7dbfa 100644
--- a/lib/eal/arm/include/rte_memcpy.h
+++ b/lib/eal/arm/include/rte_memcpy.h
@@ -5,10 +5,19 @@
 #ifndef _RTE_MEMCPY_ARM_H_
 #define _RTE_MEMCPY_ARM_H_
 
+#if defined(RTE_USE_CC_MEMCPY) || !defined(RTE_ARCH_ARM64_MEMCPY)
+
+#define RTE_CC_MEMCPY
+#include <generic/rte_memcpy.h>
+
+#else
+
 #ifdef RTE_ARCH_64
 #include <rte_memcpy_64.h>
 #else
 #include <rte_memcpy_32.h>
 #endif
 
+#endif /* RTE_USE_CC_MEMCPY */
+
 #endif /* _RTE_MEMCPY_ARM_H_ */
diff --git a/lib/eal/include/generic/rte_memcpy.h b/lib/eal/include/generic/rte_memcpy.h
index e7f0f8eaa9..cfb0175bd2 100644
--- a/lib/eal/include/generic/rte_memcpy.h
+++ b/lib/eal/include/generic/rte_memcpy.h
@@ -5,12 +5,19 @@
 #ifndef _RTE_MEMCPY_H_
 #define _RTE_MEMCPY_H_
 
+#ifdef __cplusplus
+extern "C" {
+#endif
+
 /**
  * @file
  *
  * Functions for vectorised implementation of memcpy().
  */
 
+#include <stdint.h>
+#include <string.h>
+
 /**
  * Copy 16 bytes from one location to another using optimised
  * instructions. The locations should not overlap.
@@ -35,8 +42,6 @@ rte_mov16(uint8_t *dst, const uint8_t *src);
 static inline void
 rte_mov32(uint8_t *dst, const uint8_t *src);
 
-#ifdef __DOXYGEN__
-
 /**
  * Copy 48 bytes from one location to another using optimised
  * instructions. The locations should not overlap.
@@ -49,8 +54,6 @@ rte_mov32(uint8_t *dst, const uint8_t *src);
 static inline void
 rte_mov48(uint8_t *dst, const uint8_t *src);
 
-#endif /* __DOXYGEN__ */
-
 /**
  * Copy 64 bytes from one location to another using optimised
  * instructions. The locations should not overlap.
@@ -87,8 +90,6 @@ rte_mov128(uint8_t *dst, const uint8_t *src);
 static inline void
 rte_mov256(uint8_t *dst, const uint8_t *src);
 
-#ifdef __DOXYGEN__
-
 /**
  * Copy bytes from one location to another. The locations must not overlap.
  *
@@ -111,6 +112,52 @@ rte_mov256(uint8_t *dst, const uint8_t *src);
 static void *
 rte_memcpy(void *dst, const void *src, size_t n);
 
-#endif /* __DOXYGEN__ */
+#ifdef RTE_CC_MEMCPY
+static inline void
+rte_mov16(uint8_t *dst, const uint8_t *src)
+{
+	memcpy(dst, src, 16);
+}
+
+static inline void
+rte_mov32(uint8_t *dst, const uint8_t *src)
+{
+	memcpy(dst, src, 32);
+}
+
+static inline void
+rte_mov48(uint8_t *dst, const uint8_t *src)
+{
+	memcpy(dst, src, 48);
+}
+
+static inline void
+rte_mov64(uint8_t *dst, const uint8_t *src)
+{
+	memcpy(dst, src, 64);
+}
+
+static inline void
+rte_mov128(uint8_t *dst, const uint8_t *src)
+{
+	memcpy(dst, src, 128);
+}
+
+static inline void
+rte_mov256(uint8_t *dst, const uint8_t *src)
+{
+	memcpy(dst, src, 256);
+}
+
+static inline void *
+rte_memcpy(void *dst, const void *src, size_t n)
+{
+	return memcpy(dst, src, n);
+}
+#endif /* RTE_CC_MEMCPY */
+
+#ifdef __cplusplus
+}
+#endif
 
 #endif /* _RTE_MEMCPY_H_ */
diff --git a/lib/eal/loongarch/include/rte_memcpy.h b/lib/eal/loongarch/include/rte_memcpy.h
index 22578d40f4..4e6027caee 100644
--- a/lib/eal/loongarch/include/rte_memcpy.h
+++ b/lib/eal/loongarch/include/rte_memcpy.h
@@ -5,57 +5,7 @@
 #ifndef RTE_MEMCPY_LOONGARCH_H
 #define RTE_MEMCPY_LOONGARCH_H
 
-#include <stdint.h>
-#include <string.h>
-
-#include "rte_common.h"
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-#include "generic/rte_memcpy.h"
-
-static inline void
-rte_mov16(uint8_t *dst, const uint8_t *src)
-{
-	memcpy(dst, src, 16);
-}
-
-static inline void
-rte_mov32(uint8_t *dst, const uint8_t *src)
-{
-	memcpy(dst, src, 32);
-}
-
-static inline void
-rte_mov48(uint8_t *dst, const uint8_t *src)
-{
-	memcpy(dst, src, 48);
-}
-
-static inline void
-rte_mov64(uint8_t *dst, const uint8_t *src)
-{
-	memcpy(dst, src, 64);
-}
-
-static inline void
-rte_mov128(uint8_t *dst, const uint8_t *src)
-{
-	memcpy(dst, src, 128);
-}
-
-static inline void
-rte_mov256(uint8_t *dst, const uint8_t *src)
-{
-	memcpy(dst, src, 256);
-}
-
-#define rte_memcpy(d, s, n)	memcpy((d), (s), (n))
-
-#ifdef __cplusplus
-}
-#endif
+#define RTE_CC_MEMCPY
+#include <generic/rte_memcpy.h>
 
 #endif /* RTE_MEMCPY_LOONGARCH_H */
diff --git a/lib/eal/ppc/include/rte_memcpy.h b/lib/eal/ppc/include/rte_memcpy.h
index 6f388c0234..162c1483f5 100644
--- a/lib/eal/ppc/include/rte_memcpy.h
+++ b/lib/eal/ppc/include/rte_memcpy.h
@@ -6,6 +6,13 @@
 #ifndef _RTE_MEMCPY_PPC_64_H_
 #define _RTE_MEMCPY_PPC_64_H_
 
+#ifdef RTE_USE_CC_MEMCPY
+
+#define RTE_CC_MEMCPY
+#include <generic/rte_memcpy.h>
+
+#else
+
 #include <stdint.h>
 #include <string.h>
 
@@ -215,4 +222,6 @@ rte_memcpy_func(void *dst, const void *src, size_t n)
 }
 #endif
 
+#endif /* RTE_USE_CC_MEMCPY */
+
 #endif /* _RTE_MEMCPY_PPC_64_H_ */
diff --git a/lib/eal/riscv/include/rte_memcpy.h b/lib/eal/riscv/include/rte_memcpy.h
index e34f19396e..7f6c07d090 100644
--- a/lib/eal/riscv/include/rte_memcpy.h
+++ b/lib/eal/riscv/include/rte_memcpy.h
@@ -7,57 +7,7 @@
 #ifndef RTE_MEMCPY_RISCV_H
 #define RTE_MEMCPY_RISCV_H
 
-#include <stdint.h>
-#include <string.h>
-
-#include "rte_common.h"
-
-#ifdef __cplusplus
-extern "C" {
-#endif
-
-#include "generic/rte_memcpy.h"
-
-static inline void
-rte_mov16(uint8_t *dst, const uint8_t *src)
-{
-	memcpy(dst, src, 16);
-}
-
-static inline void
-rte_mov32(uint8_t *dst, const uint8_t *src)
-{
-	memcpy(dst, src, 32);
-}
-
-static inline void
-rte_mov48(uint8_t *dst, const uint8_t *src)
-{
-	memcpy(dst, src, 48);
-}
-
-static inline void
-rte_mov64(uint8_t *dst, const uint8_t *src)
-{
-	memcpy(dst, src, 64);
-}
-
-static inline void
-rte_mov128(uint8_t *dst, const uint8_t *src)
-{
-	memcpy(dst, src, 128);
-}
-
-static inline void
-rte_mov256(uint8_t *dst, const uint8_t *src)
-{
-	memcpy(dst, src, 256);
-}
-
-#define rte_memcpy(d, s, n)	memcpy((d), (s), (n))
-
-#ifdef __cplusplus
-}
-#endif
+#define RTE_CC_MEMCPY
+#include <generic/rte_memcpy.h>
 
 #endif /* RTE_MEMCPY_RISCV_H */
diff --git a/lib/eal/x86/include/meson.build b/lib/eal/x86/include/meson.build
index 52d2f8e969..09c2fe2485 100644
--- a/lib/eal/x86/include/meson.build
+++ b/lib/eal/x86/include/meson.build
@@ -16,6 +16,7 @@ arch_headers = files(
         'rte_spinlock.h',
         'rte_vect.h',
 )
+
 arch_indirect_headers = files(
         'rte_atomic_32.h',
         'rte_atomic_64.h',
diff --git a/lib/eal/x86/include/rte_memcpy.h b/lib/eal/x86/include/rte_memcpy.h
index 42058e4a3f..2d9f5954f1 100644
--- a/lib/eal/x86/include/rte_memcpy.h
+++ b/lib/eal/x86/include/rte_memcpy.h
@@ -11,6 +11,13 @@
  * Functions for SSE/AVX/AVX2/AVX512 implementation of memcpy().
  */
 
+#ifdef RTE_USE_CC_MEMCPY
+
+#define RTE_CC_MEMCPY
+#include <generic/rte_memcpy.h>
+
+#else
+
 #include <stdio.h>
 #include <stdint.h>
 #include <string.h>
@@ -767,4 +774,6 @@ rte_memcpy(void *dst, const void *src, size_t n)
 }
 #endif
 
+#endif /* RTE_USE_CC_MEMCPY */
+
 #endif /* _RTE_MEMCPY_X86_64_H_ */
diff --git a/meson_options.txt b/meson_options.txt
index e49b2fc089..69a01f6578 100644
--- a/meson_options.txt
+++ b/meson_options.txt
@@ -60,3 +60,5 @@ option('tests', type: 'boolean', value: true, description:
        'build unit tests')
 option('use_hpet', type: 'boolean', value: false, description:
        'use HPET timer in EAL')
+option('use_cc_memcpy', type: 'boolean', value: false, description:
+       'Have the functions of <rte_memcpy.h> delegate to compiler/libc memcpy() instead of using custom implementation.')
-- 
2.43.0