From: Maxime Coquelin <maxime.coquelin@redhat.com>
Date: Wed, 29 May 2019 13:04:20 +0000 (+0200)
Subject: eal/x86: force inlining of all memcpy and mov helpers
X-Git-Url: http://git.droids-corp.org/?a=commitdiff_plain;h=1f4d55be438b428bed74f2e3dc49cfd6efc3e6fd;p=dpdk.git

eal/x86: force inlining of all memcpy and mov helpers

Some helpers in the header file are forced inlined other are
only inlined, this patch forces inline for all.

It will avoid it to be embedded as functions when called multiple
times in the same object file. For example, when we added packed
ring support in vhost-user library, rte_memcpy_generic got no
more inlined.

Signed-off-by: Maxime Coquelin <maxime.coquelin@redhat.com>
Acked-by: Bruce Richardson <bruce.richardson@intel.com>
---

diff --git a/lib/librte_eal/common/include/arch/x86/rte_memcpy.h b/lib/librte_eal/common/include/arch/x86/rte_memcpy.h
index 7b758094df..ba44c4a328 100644
--- a/lib/librte_eal/common/include/arch/x86/rte_memcpy.h
+++ b/lib/librte_eal/common/include/arch/x86/rte_memcpy.h
@@ -115,7 +115,7 @@ rte_mov256(uint8_t *dst, const uint8_t *src)
  * Copy 128-byte blocks from one location to another,
  * locations should not overlap.
  */
-static inline void
+static __rte_always_inline void
 rte_mov128blocks(uint8_t *dst, const uint8_t *src, size_t n)
 {
 	__m512i zmm0, zmm1;
@@ -163,7 +163,7 @@ rte_mov512blocks(uint8_t *dst, const uint8_t *src, size_t n)
 	}
 }
 
-static inline void *
+static __rte_always_inline void *
 rte_memcpy_generic(void *dst, const void *src, size_t n)
 {
 	uintptr_t dstu = (uintptr_t)dst;
@@ -330,7 +330,7 @@ rte_mov64(uint8_t *dst, const uint8_t *src)
  * Copy 128 bytes from one location to another,
  * locations should not overlap.
  */
-static inline void
+static __rte_always_inline void
 rte_mov128(uint8_t *dst, const uint8_t *src)
 {
 	rte_mov32((uint8_t *)dst + 0 * 32, (const uint8_t *)src + 0 * 32);
@@ -343,7 +343,7 @@ rte_mov128(uint8_t *dst, const uint8_t *src)
  * Copy 128-byte blocks from one location to another,
  * locations should not overlap.
  */
-static inline void
+static __rte_always_inline void
 rte_mov128blocks(uint8_t *dst, const uint8_t *src, size_t n)
 {
 	__m256i ymm0, ymm1, ymm2, ymm3;
@@ -363,7 +363,7 @@ rte_mov128blocks(uint8_t *dst, const uint8_t *src, size_t n)
 	}
 }
 
-static inline void *
+static __rte_always_inline void *
 rte_memcpy_generic(void *dst, const void *src, size_t n)
 {
 	uintptr_t dstu = (uintptr_t)dst;
@@ -523,7 +523,7 @@ rte_mov64(uint8_t *dst, const uint8_t *src)
  * Copy 128 bytes from one location to another,
  * locations should not overlap.
  */
-static inline void
+static __rte_always_inline void
 rte_mov128(uint8_t *dst, const uint8_t *src)
 {
 	rte_mov16((uint8_t *)dst + 0 * 16, (const uint8_t *)src + 0 * 16);
@@ -655,7 +655,7 @@ __extension__ ({                                                      \
     }                                                                 \
 })
 
-static inline void *
+static __rte_always_inline void *
 rte_memcpy_generic(void *dst, const void *src, size_t n)
 {
 	__m128i xmm0, xmm1, xmm2, xmm3, xmm4, xmm5, xmm6, xmm7, xmm8;
@@ -800,7 +800,7 @@ COPY_BLOCK_64_BACK15:
 
 #endif /* RTE_MACHINE_CPUFLAG */
 
-static inline void *
+static __rte_always_inline void *
 rte_memcpy_aligned(void *dst, const void *src, size_t n)
 {
 	void *ret = dst;
@@ -860,7 +860,7 @@ rte_memcpy_aligned(void *dst, const void *src, size_t n)
 	return ret;
 }
 
-static inline void *
+static __rte_always_inline void *
 rte_memcpy(void *dst, const void *src, size_t n)
 {
 	if (!(((uintptr_t)dst | (uintptr_t)src) & ALIGNMENT_MASK))