From: Ferruh Yigit <ferruh.yigit@intel.com>
To: Thomas Monjalon <thomas@monjalon.net>,
John McNamara <john.mcnamara@intel.com>,
Marko Kovacevic <marko.kovacevic@intel.com>
Cc: dev@dpdk.org, stable@dpdk.org
Subject: [dpdk-dev] [PATCH v2 2/2] build: fix crash by disabling AVX512 with binutils 2.31
Date: Tue, 16 Apr 2019 16:39:32 +0100 [thread overview]
Message-ID: <20190416153932.21788-2-ferruh.yigit@intel.com> (raw)
Message-ID: <20190416153932.BYKPiWWtPI-MtAhF-QEj4wx8nlcympUM43Iv67tzqUo@z> (raw)
In-Reply-To: <20190416153932.21788-1-ferruh.yigit@intel.com>
On Skylake platform, with native build, KNI kernel module crashes
because of the corrupted values passed to kernel module.
The corruption occurs because the userspace kni library works
unexpectedly. Compiler [1] is using AVX512 instructions and generated
binary is wrong [2].
It turned around gcc does its job correct, but gas is generating binary
wrong. And expected binutils 2.30, 2.31 & 2.31.1 are affected. Issue has
been fixed in binutils 2.32 with:
Commit x86: don't mistakenly scale non-8-bit displacements
AVX512 was already disabled with bintuils 2.30 [3], extending it to
2.31 & 2.31.1 too.
[1] gcc (GCC) 8.3.1 20190223 (Red Hat 8.3.1-2)
[2] gcc bug: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=90028
[3] Bugzilla ID 97 has the details.
Bugzilla ID: 249
Cc: stable@dpdk.org
Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
---
v2:
* Release notes "Known Issues" section updated
---
config/x86/meson.build | 6 ++++++
doc/guides/rel_notes/release_19_05.rst | 6 ++++++
mk/toolchain/gcc/rte.toolchain-compat.mk | 9 ++++++++-
3 files changed, 20 insertions(+), 1 deletion(-)
diff --git a/config/x86/meson.build b/config/x86/meson.build
index 692aebe7a..9e9d5dc8c 100644
--- a/config/x86/meson.build
+++ b/config/x86/meson.build
@@ -10,6 +10,12 @@ if host_machine.system() != 'windows'
message('Binutils 2.30 detected, disabling AVX512 support as workaround for bug #97')
endif
endif
+ if ldver.contains('2.31')
+ if cc.has_argument('-mno-avx512f')
+ machine_args += '-mno-avx512f'
+ message('Binutils 2.31 detected, disabling AVX512 support as workaround for bug #249')
+ endif
+ endif
endif
# we require SSE4.2 for DPDK
diff --git a/doc/guides/rel_notes/release_19_05.rst b/doc/guides/rel_notes/release_19_05.rst
index 25cd61ca2..cf04b9b26 100644
--- a/doc/guides/rel_notes/release_19_05.rst
+++ b/doc/guides/rel_notes/release_19_05.rst
@@ -338,6 +338,12 @@ Known Issues
Also, make sure to start the actual text at the margin.
=========================================================
+* **On x86 platforms, AVX512 support is disabled with binutils 2.31**
+
+ Because a defect in binutils 2.31 AVX512 support is disabled.
+ DPDK defect: https://bugs.dpdk.org/show_bug.cgi?id=249
+ GCC defect: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=90028
+
* **No software AES-XTS implementation.**
There are currently no cryptodev software PMDs available which implement
diff --git a/mk/toolchain/gcc/rte.toolchain-compat.mk b/mk/toolchain/gcc/rte.toolchain-compat.mk
index df71e4a8b..ea40a11c0 100644
--- a/mk/toolchain/gcc/rte.toolchain-compat.mk
+++ b/mk/toolchain/gcc/rte.toolchain-compat.mk
@@ -27,7 +27,14 @@ ifneq ($(filter 2.30%,$(LD_VERSION)),)
FORCE_DISABLE_AVX512 := y
# print warning only once for librte_eal
ifneq ($(filter %librte_eal,$(CURDIR)),)
-$(warning AVX512 support disabled because of ld 2.30. See Bug 97)
+$(warning AVX512 support disabled because of binutils 2.30. See Bug 97)
+endif
+endif
+ifneq ($(filter 2.31%,$(LD_VERSION)),)
+FORCE_DISABLE_AVX512 := y
+# print warning only once for librte_eal
+ifneq ($(filter %librte_eal,$(CURDIR)),)
+$(warning AVX512 support disabled because of binutils 2.31. See Bug 249)
endif
endif
endif
--
2.20.1
next prev parent reply other threads:[~2019-04-16 15:39 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-04-10 14:00 [dpdk-dev] [PATCH 1/2] build: fix meson binutils workaround Ferruh Yigit
2019-04-10 14:00 ` Ferruh Yigit
2019-04-10 14:00 ` [dpdk-dev] [PATCH 2/2] build: fix crash by disabling AVX512 with binutils 2.31 Ferruh Yigit
2019-04-10 14:00 ` Ferruh Yigit
2019-04-16 15:39 ` [dpdk-dev] [PATCH v2 1/2] build: fix meson binutils workaround Ferruh Yigit
2019-04-16 15:39 ` Ferruh Yigit
2019-04-16 15:39 ` Ferruh Yigit [this message]
2019-04-16 15:39 ` [dpdk-dev] [PATCH v2 2/2] build: fix crash by disabling AVX512 with binutils 2.31 Ferruh Yigit
2019-04-16 15:47 ` Bruce Richardson
2019-04-16 15:47 ` Bruce Richardson
2019-04-16 15:47 ` [dpdk-dev] [PATCH v2 1/2] build: fix meson binutils workaround Bruce Richardson
2019-04-16 15:47 ` Bruce Richardson
2019-05-02 13:35 ` [dpdk-dev] [PATCH v3 1/3] " Ferruh Yigit
2019-05-02 13:35 ` Ferruh Yigit
2019-05-02 13:35 ` [dpdk-dev] [PATCH v3 2/3] build: fix crash by disabling AVX512 with binutils 2.31 Ferruh Yigit
2019-05-02 13:35 ` Ferruh Yigit
2019-05-02 13:35 ` [dpdk-dev] [PATCH v3 3/3] build: reduce indentation in meson check Ferruh Yigit
2019-05-02 13:35 ` Ferruh Yigit
2019-05-02 13:44 ` [dpdk-dev] [dpdk-stable] [PATCH v3 1/3] build: fix meson binutils workaround Ferruh Yigit
2019-05-02 13:44 ` Ferruh Yigit
2019-05-02 15:48 ` Thomas Monjalon
2019-05-02 15:48 ` Thomas Monjalon
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190416153932.21788-2-ferruh.yigit@intel.com \
--to=ferruh.yigit@intel.com \
--cc=dev@dpdk.org \
--cc=john.mcnamara@intel.com \
--cc=marko.kovacevic@intel.com \
--cc=stable@dpdk.org \
--cc=thomas@monjalon.net \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).