eal/x86: tune memcpy for platforms without AVX512

For prior platforms, add condition for unalignment handling, to keep this
operation from interrupting the batch copy loop for aligned cases.

Signed-off-by: Zhihong Wang <zhihong.wang@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 fee954a..d965957 100644 (file)
--- a/lib/librte_eal/common/include/arch/x86/rte_memcpy.h
+++ b/lib/librte_eal/common/include/arch/x86/rte_memcpy.h
@@ -513,10 +513,12 @@ COPY_BLOCK_64_BACK31:
         * Make store aligned when copy size exceeds 512 bytes
         */
        dstofss = 32 - ((uintptr_t)dst & 0x1F);
-       n -= dstofss;
-       rte_mov32((uint8_t *)dst, (const uint8_t *)src);
-       src = (const uint8_t *)src + dstofss;
-       dst = (uint8_t *)dst + dstofss;
+       if (dstofss > 0) {
+               n -= dstofss;
+               rte_mov32((uint8_t *)dst, (const uint8_t *)src);
+               src = (const uint8_t *)src + dstofss;
+               dst = (uint8_t *)dst + dstofss;
+       }
 
        /**
         * Copy 256-byte blocks.
@@ -833,11 +835,13 @@ COPY_BLOCK_64_BACK15:
         * backwards access.
         */
        dstofss = 16 - ((uintptr_t)dst & 0x0F) + 16;
-       n -= dstofss;
-       rte_mov32((uint8_t *)dst, (const uint8_t *)src);
-       src = (const uint8_t *)src + dstofss;
-       dst = (uint8_t *)dst + dstofss;
-       srcofs = ((uintptr_t)src & 0x0F);
+       if (dstofss > 0) {
+               n -= dstofss;
+               rte_mov32((uint8_t *)dst, (const uint8_t *)src);
+               src = (const uint8_t *)src + dstofss;
+               dst = (uint8_t *)dst + dstofss;
+               srcofs = ((uintptr_t)src & 0x0F);
+       }
 
        /**
         * For aligned copy