patch 'eal/x86: avoid cast-align warning in memcpy functions' has been queued to stable release 19.11.11
christian.ehrhardt at canonical.com
christian.ehrhardt at canonical.com
Tue Nov 30 17:35:04 CET 2021
Hi,
FYI, your patch has been queued to stable release 19.11.11
Note it hasn't been pushed to http://dpdk.org/browse/dpdk-stable yet.
It will be pushed if I get no objections before December 10th 2021. So please
shout if anyone has objections.
Also note that after the patch there's a diff of the upstream commit vs the
patch applied to the branch. This will indicate if there was any rebasing
needed to apply to the stable branch. If there were code changes for rebasing
(ie: not only metadata diffs), please double check that the rebase was
correctly done.
Queued patches are on a temporary branch at:
https://github.com/cpaelzer/dpdk-stable-queue
This queued commit can be viewed at:
https://github.com/cpaelzer/dpdk-stable-queue/commit/545b8e9ee5faaa4983cffc669c743fe372a75263
Thanks.
Christian Ehrhardt <christian.ehrhardt at canonical.com>
---
>From 545b8e9ee5faaa4983cffc669c743fe372a75263 Mon Sep 17 00:00:00 2001
From: Eli Britstein <elibr at nvidia.com>
Date: Thu, 21 Oct 2021 11:51:32 +0300
Subject: [PATCH] eal/x86: avoid cast-align warning in memcpy functions
[ upstream commit 6de430b7079e8f7c29f9c18869393f74f8dffcb6 ]
Functions and macros in x86 rte_memcpy.h may cause cast-align warnings,
when using strict cast align flag with supporting gcc:
gcc (Ubuntu 9.3.0-17ubuntu1~20.04) 9.3.0
CFLAGS="-Wcast-align=strict" make V=1 -C examples/l2fwd clean static
For example:
In file included from main.c:24:
/dpdk/build/include/rte_memcpy.h: In function 'rte_mov16':
/dpdk/build/include/rte_memcpy.h:306:25: warning: cast increases
required alignment of target type [-Wcast-align]
306 | xmm0 = _mm_loadu_si128((const __m128i *)src);
| ^
As the code assumes correct alignment, add first a (void *) or (const
void *) castings, to avoid the warnings.
Fixes: 9484092baad3 ("eal/x86: optimize memcpy for AVX512 platforms")
Signed-off-by: Eli Britstein <elibr at nvidia.com>
---
.../common/include/arch/x86/rte_memcpy.h | 80 ++++++++++---------
1 file changed, 44 insertions(+), 36 deletions(-)
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 d01832fa15..f1751dd41c 100644
--- a/lib/librte_eal/common/include/arch/x86/rte_memcpy.h
+++ b/lib/librte_eal/common/include/arch/x86/rte_memcpy.h
@@ -303,8 +303,8 @@ rte_mov16(uint8_t *dst, const uint8_t *src)
{
__m128i xmm0;
- xmm0 = _mm_loadu_si128((const __m128i *)src);
- _mm_storeu_si128((__m128i *)dst, xmm0);
+ xmm0 = _mm_loadu_si128((const __m128i *)(const void *)src);
+ _mm_storeu_si128((__m128i *)(void *)dst, xmm0);
}
/**
@@ -316,8 +316,8 @@ rte_mov32(uint8_t *dst, const uint8_t *src)
{
__m256i ymm0;
- ymm0 = _mm256_loadu_si256((const __m256i *)src);
- _mm256_storeu_si256((__m256i *)dst, ymm0);
+ ymm0 = _mm256_loadu_si256((const __m256i *)(const void *)src);
+ _mm256_storeu_si256((__m256i *)(void *)dst, ymm0);
}
/**
@@ -354,16 +354,24 @@ rte_mov128blocks(uint8_t *dst, const uint8_t *src, size_t n)
__m256i ymm0, ymm1, ymm2, ymm3;
while (n >= 128) {
- ymm0 = _mm256_loadu_si256((const __m256i *)((const uint8_t *)src + 0 * 32));
+ ymm0 = _mm256_loadu_si256((const __m256i *)(const void *)
+ ((const uint8_t *)src + 0 * 32));
n -= 128;
- ymm1 = _mm256_loadu_si256((const __m256i *)((const uint8_t *)src + 1 * 32));
- ymm2 = _mm256_loadu_si256((const __m256i *)((const uint8_t *)src + 2 * 32));
- ymm3 = _mm256_loadu_si256((const __m256i *)((const uint8_t *)src + 3 * 32));
+ ymm1 = _mm256_loadu_si256((const __m256i *)(const void *)
+ ((const uint8_t *)src + 1 * 32));
+ ymm2 = _mm256_loadu_si256((const __m256i *)(const void *)
+ ((const uint8_t *)src + 2 * 32));
+ ymm3 = _mm256_loadu_si256((const __m256i *)(const void *)
+ ((const uint8_t *)src + 3 * 32));
src = (const uint8_t *)src + 128;
- _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 0 * 32), ymm0);
- _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 1 * 32), ymm1);
- _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 2 * 32), ymm2);
- _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 3 * 32), ymm3);
+ _mm256_storeu_si256((__m256i *)(void *)
+ ((uint8_t *)dst + 0 * 32), ymm0);
+ _mm256_storeu_si256((__m256i *)(void *)
+ ((uint8_t *)dst + 1 * 32), ymm1);
+ _mm256_storeu_si256((__m256i *)(void *)
+ ((uint8_t *)dst + 2 * 32), ymm2);
+ _mm256_storeu_si256((__m256i *)(void *)
+ ((uint8_t *)dst + 3 * 32), ymm3);
dst = (uint8_t *)dst + 128;
}
}
@@ -496,8 +504,8 @@ rte_mov16(uint8_t *dst, const uint8_t *src)
{
__m128i xmm0;
- xmm0 = _mm_loadu_si128((const __m128i *)(const __m128i *)src);
- _mm_storeu_si128((__m128i *)dst, xmm0);
+ xmm0 = _mm_loadu_si128((const __m128i *)(const void *)src);
+ _mm_storeu_si128((__m128i *)(void *)dst, xmm0);
}
/**
@@ -581,25 +589,25 @@ rte_mov256(uint8_t *dst, const uint8_t *src)
__extension__ ({ \
size_t tmp; \
while (len >= 128 + 16 - offset) { \
- xmm0 = _mm_loadu_si128((const __m128i *)((const uint8_t *)src - offset + 0 * 16)); \
+ xmm0 = _mm_loadu_si128((const __m128i *)(const void *)((const uint8_t *)src - offset + 0 * 16)); \
len -= 128; \
- xmm1 = _mm_loadu_si128((const __m128i *)((const uint8_t *)src - offset + 1 * 16)); \
- xmm2 = _mm_loadu_si128((const __m128i *)((const uint8_t *)src - offset + 2 * 16)); \
- xmm3 = _mm_loadu_si128((const __m128i *)((const uint8_t *)src - offset + 3 * 16)); \
- xmm4 = _mm_loadu_si128((const __m128i *)((const uint8_t *)src - offset + 4 * 16)); \
- xmm5 = _mm_loadu_si128((const __m128i *)((const uint8_t *)src - offset + 5 * 16)); \
- xmm6 = _mm_loadu_si128((const __m128i *)((const uint8_t *)src - offset + 6 * 16)); \
- xmm7 = _mm_loadu_si128((const __m128i *)((const uint8_t *)src - offset + 7 * 16)); \
- xmm8 = _mm_loadu_si128((const __m128i *)((const uint8_t *)src - offset + 8 * 16)); \
+ xmm1 = _mm_loadu_si128((const __m128i *)(const void *)((const uint8_t *)src - offset + 1 * 16)); \
+ xmm2 = _mm_loadu_si128((const __m128i *)(const void *)((const uint8_t *)src - offset + 2 * 16)); \
+ xmm3 = _mm_loadu_si128((const __m128i *)(const void *)((const uint8_t *)src - offset + 3 * 16)); \
+ xmm4 = _mm_loadu_si128((const __m128i *)(const void *)((const uint8_t *)src - offset + 4 * 16)); \
+ xmm5 = _mm_loadu_si128((const __m128i *)(const void *)((const uint8_t *)src - offset + 5 * 16)); \
+ xmm6 = _mm_loadu_si128((const __m128i *)(const void *)((const uint8_t *)src - offset + 6 * 16)); \
+ xmm7 = _mm_loadu_si128((const __m128i *)(const void *)((const uint8_t *)src - offset + 7 * 16)); \
+ xmm8 = _mm_loadu_si128((const __m128i *)(const void *)((const uint8_t *)src - offset + 8 * 16)); \
src = (const uint8_t *)src + 128; \
- _mm_storeu_si128((__m128i *)((uint8_t *)dst + 0 * 16), _mm_alignr_epi8(xmm1, xmm0, offset)); \
- _mm_storeu_si128((__m128i *)((uint8_t *)dst + 1 * 16), _mm_alignr_epi8(xmm2, xmm1, offset)); \
- _mm_storeu_si128((__m128i *)((uint8_t *)dst + 2 * 16), _mm_alignr_epi8(xmm3, xmm2, offset)); \
- _mm_storeu_si128((__m128i *)((uint8_t *)dst + 3 * 16), _mm_alignr_epi8(xmm4, xmm3, offset)); \
- _mm_storeu_si128((__m128i *)((uint8_t *)dst + 4 * 16), _mm_alignr_epi8(xmm5, xmm4, offset)); \
- _mm_storeu_si128((__m128i *)((uint8_t *)dst + 5 * 16), _mm_alignr_epi8(xmm6, xmm5, offset)); \
- _mm_storeu_si128((__m128i *)((uint8_t *)dst + 6 * 16), _mm_alignr_epi8(xmm7, xmm6, offset)); \
- _mm_storeu_si128((__m128i *)((uint8_t *)dst + 7 * 16), _mm_alignr_epi8(xmm8, xmm7, offset)); \
+ _mm_storeu_si128((__m128i *)(void *)((uint8_t *)dst + 0 * 16), _mm_alignr_epi8(xmm1, xmm0, offset)); \
+ _mm_storeu_si128((__m128i *)(void *)((uint8_t *)dst + 1 * 16), _mm_alignr_epi8(xmm2, xmm1, offset)); \
+ _mm_storeu_si128((__m128i *)(void *)((uint8_t *)dst + 2 * 16), _mm_alignr_epi8(xmm3, xmm2, offset)); \
+ _mm_storeu_si128((__m128i *)(void *)((uint8_t *)dst + 3 * 16), _mm_alignr_epi8(xmm4, xmm3, offset)); \
+ _mm_storeu_si128((__m128i *)(void *)((uint8_t *)dst + 4 * 16), _mm_alignr_epi8(xmm5, xmm4, offset)); \
+ _mm_storeu_si128((__m128i *)(void *)((uint8_t *)dst + 5 * 16), _mm_alignr_epi8(xmm6, xmm5, offset)); \
+ _mm_storeu_si128((__m128i *)(void *)((uint8_t *)dst + 6 * 16), _mm_alignr_epi8(xmm7, xmm6, offset)); \
+ _mm_storeu_si128((__m128i *)(void *)((uint8_t *)dst + 7 * 16), _mm_alignr_epi8(xmm8, xmm7, offset)); \
dst = (uint8_t *)dst + 128; \
} \
tmp = len; \
@@ -609,13 +617,13 @@ __extension__ ({
dst = (uint8_t *)dst + tmp; \
if (len >= 32 + 16 - offset) { \
while (len >= 32 + 16 - offset) { \
- xmm0 = _mm_loadu_si128((const __m128i *)((const uint8_t *)src - offset + 0 * 16)); \
+ xmm0 = _mm_loadu_si128((const __m128i *)(const void *)((const uint8_t *)src - offset + 0 * 16)); \
len -= 32; \
- xmm1 = _mm_loadu_si128((const __m128i *)((const uint8_t *)src - offset + 1 * 16)); \
- xmm2 = _mm_loadu_si128((const __m128i *)((const uint8_t *)src - offset + 2 * 16)); \
+ xmm1 = _mm_loadu_si128((const __m128i *)(const void *)((const uint8_t *)src - offset + 1 * 16)); \
+ xmm2 = _mm_loadu_si128((const __m128i *)(const void *)((const uint8_t *)src - offset + 2 * 16)); \
src = (const uint8_t *)src + 32; \
- _mm_storeu_si128((__m128i *)((uint8_t *)dst + 0 * 16), _mm_alignr_epi8(xmm1, xmm0, offset)); \
- _mm_storeu_si128((__m128i *)((uint8_t *)dst + 1 * 16), _mm_alignr_epi8(xmm2, xmm1, offset)); \
+ _mm_storeu_si128((__m128i *)(void *)((uint8_t *)dst + 0 * 16), _mm_alignr_epi8(xmm1, xmm0, offset)); \
+ _mm_storeu_si128((__m128i *)(void *)((uint8_t *)dst + 1 * 16), _mm_alignr_epi8(xmm2, xmm1, offset)); \
dst = (uint8_t *)dst + 32; \
} \
tmp = len; \
--
2.34.0
---
Diff of the applied patch vs upstream commit (please double-check if non-empty:
---
--- - 2021-11-30 16:50:11.658164101 +0100
+++ 0100-eal-x86-avoid-cast-align-warning-in-memcpy-functions.patch 2021-11-30 16:50:05.898874322 +0100
@@ -1 +1 @@
-From 6de430b7079e8f7c29f9c18869393f74f8dffcb6 Mon Sep 17 00:00:00 2001
+From 545b8e9ee5faaa4983cffc669c743fe372a75263 Mon Sep 17 00:00:00 2001
@@ -5,0 +6,2 @@
+[ upstream commit 6de430b7079e8f7c29f9c18869393f74f8dffcb6 ]
+
@@ -23 +24,0 @@
-Cc: stable at dpdk.org
@@ -27 +28 @@
- lib/eal/x86/include/rte_memcpy.h | 80 ++++++++++++++++++--------------
+ .../common/include/arch/x86/rte_memcpy.h | 80 ++++++++++---------
@@ -30,4 +31,4 @@
-diff --git a/lib/eal/x86/include/rte_memcpy.h b/lib/eal/x86/include/rte_memcpy.h
-index 79f381dd9b..1b6c6e585f 100644
---- a/lib/eal/x86/include/rte_memcpy.h
-+++ b/lib/eal/x86/include/rte_memcpy.h
+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 d01832fa15..f1751dd41c 100644
+--- a/lib/librte_eal/common/include/arch/x86/rte_memcpy.h
++++ b/lib/librte_eal/common/include/arch/x86/rte_memcpy.h
More information about the stable
mailing list