From 73127104a245052cd5cf29cdaaca3e5c32c70348 Mon Sep 17 00:00:00 2001
From: CoprDistGit <infra@openeuler.org>
Date: Fri, 28 Feb 2025 10:03:49 +0000
Subject: automatic import of gcc

---
 ...tigation-Disable-gather-generation-in-vec.patch | 220 +++++++++++++++++++++
 1 file changed, 220 insertions(+)
 create mode 100644 0263-Software-mitigation-Disable-gather-generation-in-vec.patch

(limited to '0263-Software-mitigation-Disable-gather-generation-in-vec.patch')

diff --git a/0263-Software-mitigation-Disable-gather-generation-in-vec.patch b/0263-Software-mitigation-Disable-gather-generation-in-vec.patch
new file mode 100644
index 0000000..2a1e4e7
--- /dev/null
+++ b/0263-Software-mitigation-Disable-gather-generation-in-vec.patch
@@ -0,0 +1,220 @@
+From cfffbec938afdc45c31db5ec282ce21ad1ba2dc7 Mon Sep 17 00:00:00 2001
+From: liuhongt <hongtao.liu@intel.com>
+Date: Thu, 10 Aug 2023 11:41:39 +0800
+Subject: [PATCH 09/28] Software mitigation: Disable gather generation in
+ vectorization for GDS affected Intel Processors.
+
+For more details of GDS (Gather Data Sampling), refer to
+https://www.intel.com/content/www/us/en/developer/articles/technical/software-security-guidance/advisory-guidance/gather-data-sampling.html
+
+After microcode update, there's performance regression. To avoid that,
+the patch disables gather generation in autovectorization but uses
+gather scalar emulation instead.
+
+gcc/ChangeLog:
+
+	* config/i386/i386-options.cc (m_GDS): New macro.
+	* config/i386/x86-tune.def (X86_TUNE_USE_GATHER_2PARTS): Don't
+	enable for m_GDS.
+	(X86_TUNE_USE_GATHER_4PARTS): Ditto.
+	(X86_TUNE_USE_GATHER): Ditto.
+
+gcc/testsuite/ChangeLog:
+
+	* gcc.target/i386/avx2-gather-2.c: Adjust options to keep
+	gather vectorization.
+	* gcc.target/i386/avx2-gather-6.c: Ditto.
+	* gcc.target/i386/avx512f-pr88464-1.c: Ditto.
+	* gcc.target/i386/avx512f-pr88464-5.c: Ditto.
+	* gcc.target/i386/avx512vl-pr88464-1.c: Ditto.
+	* gcc.target/i386/avx512vl-pr88464-11.c: Ditto.
+	* gcc.target/i386/avx512vl-pr88464-3.c: Ditto.
+	* gcc.target/i386/avx512vl-pr88464-9.c: Ditto.
+	* gcc.target/i386/pr88531-1b.c: Ditto.
+	* gcc.target/i386/pr88531-1c.c: Ditto.
+
+(cherry picked from commit 3064d1f5c48cb6ce1b4133570dd08ecca8abb52d)
+---
+ gcc/config/i386/i386-options.cc                     | 5 +++++
+ gcc/config/i386/x86-tune.def                        | 9 ++++++---
+ gcc/testsuite/gcc.target/i386/avx2-gather-2.c       | 2 +-
+ gcc/testsuite/gcc.target/i386/avx2-gather-6.c       | 2 +-
+ gcc/testsuite/gcc.target/i386/avx512f-pr88464-1.c   | 2 +-
+ gcc/testsuite/gcc.target/i386/avx512f-pr88464-5.c   | 2 +-
+ gcc/testsuite/gcc.target/i386/avx512vl-pr88464-1.c  | 2 +-
+ gcc/testsuite/gcc.target/i386/avx512vl-pr88464-11.c | 2 +-
+ gcc/testsuite/gcc.target/i386/avx512vl-pr88464-3.c  | 2 +-
+ gcc/testsuite/gcc.target/i386/avx512vl-pr88464-9.c  | 2 +-
+ gcc/testsuite/gcc.target/i386/pr88531-1b.c          | 2 +-
+ gcc/testsuite/gcc.target/i386/pr88531-1c.c          | 2 +-
+ 12 files changed, 21 insertions(+), 13 deletions(-)
+
+diff --git a/gcc/config/i386/i386-options.cc b/gcc/config/i386/i386-options.cc
+index fb2ed942f..9617fc162 100644
+--- a/gcc/config/i386/i386-options.cc
++++ b/gcc/config/i386/i386-options.cc
+@@ -137,6 +137,11 @@ along with GCC; see the file COPYING3.  If not see
+ #define m_GOLDMONT_PLUS (HOST_WIDE_INT_1U<<PROCESSOR_GOLDMONT_PLUS)
+ #define m_TREMONT (HOST_WIDE_INT_1U<<PROCESSOR_TREMONT)
+ #define m_INTEL (HOST_WIDE_INT_1U<<PROCESSOR_INTEL)
++/* Gather Data Sampling / CVE-2022-40982 / INTEL-SA-00828.
++   Software mitigation.  */
++#define m_GDS (m_SKYLAKE | m_SKYLAKE_AVX512 | m_CANNONLAKE \
++	       | m_ICELAKE_CLIENT | m_ICELAKE_SERVER | m_CASCADELAKE \
++	       | m_TIGERLAKE | m_COOPERLAKE | m_ROCKETLAKE)
+ 
+ #define m_GEODE (HOST_WIDE_INT_1U<<PROCESSOR_GEODE)
+ #define m_K6 (HOST_WIDE_INT_1U<<PROCESSOR_K6)
+diff --git a/gcc/config/i386/x86-tune.def b/gcc/config/i386/x86-tune.def
+index e6b9e2125..4392709fc 100644
+--- a/gcc/config/i386/x86-tune.def
++++ b/gcc/config/i386/x86-tune.def
+@@ -467,7 +467,8 @@ DEF_TUNE (X86_TUNE_AVOID_4BYTE_PREFIXES, "avoid_4byte_prefixes",
+ /* X86_TUNE_USE_GATHER_2PARTS: Use gather instructions for vectors with 2
+    elements.  */
+ DEF_TUNE (X86_TUNE_USE_GATHER_2PARTS, "use_gather_2parts",
+-	  ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER3 | m_ZNVER4 | m_ALDERLAKE | m_GENERIC))
++	  ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER3 | m_ZNVER4 | m_ALDERLAKE
++	    | m_GENERIC | m_GDS))
+ 
+ /* X86_TUNE_USE_SCATTER_2PARTS: Use scater instructions for vectors with 2
+    elements.  */
+@@ -477,7 +478,8 @@ DEF_TUNE (X86_TUNE_USE_SCATTER_2PARTS, "use_scatter_2parts",
+ /* X86_TUNE_USE_GATHER_4PARTS: Use gather instructions for vectors with 4
+    elements.  */
+ DEF_TUNE (X86_TUNE_USE_GATHER_4PARTS, "use_gather_4parts",
+-	  ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER3 | m_ZNVER4 |  m_ALDERLAKE | m_GENERIC))
++	  ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER3 | m_ZNVER4 | m_ALDERLAKE
++	    | m_GENERIC | m_GDS))
+ 
+ /* X86_TUNE_USE_SCATTER_4PARTS: Use scater instructions for vectors with 4
+    elements.  */
+@@ -487,7 +489,8 @@ DEF_TUNE (X86_TUNE_USE_SCATTER_4PARTS, "use_scatter_4parts",
+ /* X86_TUNE_USE_GATHER: Use gather instructions for vectors with 8 or more
+    elements.  */
+ DEF_TUNE (X86_TUNE_USE_GATHER, "use_gather",
+-	  ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER4 | m_ALDERLAKE | m_GENERIC))
++	  ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER4 | m_ALDERLAKE
++	    | m_GENERIC | m_GDS))
+ 
+ /* X86_TUNE_USE_SCATTER: Use scater instructions for vectors with 8 or more
+    elements.  */
+diff --git a/gcc/testsuite/gcc.target/i386/avx2-gather-2.c b/gcc/testsuite/gcc.target/i386/avx2-gather-2.c
+index ad5ef7310..978924b0f 100644
+--- a/gcc/testsuite/gcc.target/i386/avx2-gather-2.c
++++ b/gcc/testsuite/gcc.target/i386/avx2-gather-2.c
+@@ -1,5 +1,5 @@
+ /* { dg-do compile } */
+-/* { dg-options "-O3 -fdump-tree-vect-details -march=skylake" } */
++/* { dg-options "-O3 -fdump-tree-vect-details -march=skylake -mtune=haswell" } */
+ 
+ #include "avx2-gather-1.c"
+ 
+diff --git a/gcc/testsuite/gcc.target/i386/avx2-gather-6.c b/gcc/testsuite/gcc.target/i386/avx2-gather-6.c
+index b9119581a..067b251e3 100644
+--- a/gcc/testsuite/gcc.target/i386/avx2-gather-6.c
++++ b/gcc/testsuite/gcc.target/i386/avx2-gather-6.c
+@@ -1,5 +1,5 @@
+ /* { dg-do compile } */
+-/* { dg-options "-O3 -mavx2 -fno-common -fdump-tree-vect-details -mtune=skylake" } */
++/* { dg-options "-O3 -mavx2 -fno-common -fdump-tree-vect-details  -mtune=haswell" } */
+ 
+ #include "avx2-gather-5.c"
+ 
+diff --git a/gcc/testsuite/gcc.target/i386/avx512f-pr88464-1.c b/gcc/testsuite/gcc.target/i386/avx512f-pr88464-1.c
+index 06d21bb01..d1a229861 100644
+--- a/gcc/testsuite/gcc.target/i386/avx512f-pr88464-1.c
++++ b/gcc/testsuite/gcc.target/i386/avx512f-pr88464-1.c
+@@ -1,6 +1,6 @@
+ /* PR tree-optimization/88464 */
+ /* { dg-do compile } */
+-/* { dg-options "-O3 -mavx512f -mprefer-vector-width=512 -mtune=skylake-avx512 -fdump-tree-vect-details" } */
++/* { dg-options "-O3 -mavx512f -mprefer-vector-width=512 -mtune=haswell -fdump-tree-vect-details" } */
+ /* { dg-final { scan-tree-dump-times "loop vectorized using 64 byte vectors" 4 "vect" } } */
+ /* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 4 "vect" } } */
+ 
+diff --git a/gcc/testsuite/gcc.target/i386/avx512f-pr88464-5.c b/gcc/testsuite/gcc.target/i386/avx512f-pr88464-5.c
+index 462e951fd..d7b0b2b28 100644
+--- a/gcc/testsuite/gcc.target/i386/avx512f-pr88464-5.c
++++ b/gcc/testsuite/gcc.target/i386/avx512f-pr88464-5.c
+@@ -1,6 +1,6 @@
+ /* PR tree-optimization/88464 */
+ /* { dg-do compile } */
+-/* { dg-options "-O3 -mavx512f -mprefer-vector-width=512 -mtune=skylake-avx512 -fdump-tree-vect-details" } */
++/* { dg-options "-O3 -mavx512f -mprefer-vector-width=512 -mtune=haswell -fdump-tree-vect-details" } */
+ /* { dg-final { scan-tree-dump-times "loop vectorized using 64 byte vectors" 4 "vect" } } */
+ /* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 4 "vect" } } */
+ 
+diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-pr88464-1.c b/gcc/testsuite/gcc.target/i386/avx512vl-pr88464-1.c
+index 55a28dddb..07439185e 100644
+--- a/gcc/testsuite/gcc.target/i386/avx512vl-pr88464-1.c
++++ b/gcc/testsuite/gcc.target/i386/avx512vl-pr88464-1.c
+@@ -1,6 +1,6 @@
+ /* PR tree-optimization/88464 */
+ /* { dg-do compile } */
+-/* { dg-options "-O3 -mavx512vl -mprefer-vector-width=256 -mtune=skylake-avx512 -fdump-tree-vect-details" } */
++/* { dg-options "-O3 -mavx512vl -mprefer-vector-width=256 -mtune=haswell -fdump-tree-vect-details" } */
+ /* { dg-final { scan-tree-dump-times "loop vectorized using 32 byte vectors" 4 "vect" } } */
+ /* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 4 "vect" } } */
+ 
+diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-pr88464-11.c b/gcc/testsuite/gcc.target/i386/avx512vl-pr88464-11.c
+index 969600885..3a9810827 100644
+--- a/gcc/testsuite/gcc.target/i386/avx512vl-pr88464-11.c
++++ b/gcc/testsuite/gcc.target/i386/avx512vl-pr88464-11.c
+@@ -1,6 +1,6 @@
+ /* PR tree-optimization/88464 */
+ /* { dg-do compile } */
+-/* { dg-options "-O3 -mavx512vl -mprefer-vector-width=128 -mtune=skylake-avx512 -fdump-tree-vect-details" } */
++/* { dg-options "-O3 -mavx512vl -mprefer-vector-width=128 -mtune=haswell -fdump-tree-vect-details" } */
+ /* { dg-final { scan-tree-dump-times "loop vectorized using 16 byte vectors" 4 "vect" } } */
+ /* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 4 "vect" } } */
+ 
+diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-pr88464-3.c b/gcc/testsuite/gcc.target/i386/avx512vl-pr88464-3.c
+index 6b0c8a859..ac669e048 100644
+--- a/gcc/testsuite/gcc.target/i386/avx512vl-pr88464-3.c
++++ b/gcc/testsuite/gcc.target/i386/avx512vl-pr88464-3.c
+@@ -1,6 +1,6 @@
+ /* PR tree-optimization/88464 */
+ /* { dg-do compile } */
+-/* { dg-options "-O3 -mavx512vl -mprefer-vector-width=128 -mtune=skylake-avx512 -fdump-tree-vect-details" } */
++/* { dg-options "-O3 -mavx512vl -mprefer-vector-width=128 -mtune=haswell -fdump-tree-vect-details" } */
+ /* { dg-final { scan-tree-dump-times "loop vectorized using 16 byte vectors" 4 "vect" } } */
+ /* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 4 "vect" } } */
+ 
+diff --git a/gcc/testsuite/gcc.target/i386/avx512vl-pr88464-9.c b/gcc/testsuite/gcc.target/i386/avx512vl-pr88464-9.c
+index 3af568ab3..14a1083b6 100644
+--- a/gcc/testsuite/gcc.target/i386/avx512vl-pr88464-9.c
++++ b/gcc/testsuite/gcc.target/i386/avx512vl-pr88464-9.c
+@@ -1,6 +1,6 @@
+ /* PR tree-optimization/88464 */
+ /* { dg-do compile } */
+-/* { dg-options "-O3 -mavx512vl -mprefer-vector-width=256 -mtune=skylake-avx512 -fdump-tree-vect-details" } */
++/* { dg-options "-O3 -mavx512vl -mprefer-vector-width=256 -mtune=haswell -fdump-tree-vect-details" } */
+ /* { dg-final { scan-tree-dump-times "loop vectorized using 32 byte vectors" 4 "vect" } } */
+ /* { dg-final { scan-tree-dump-times "vectorized 1 loops in function" 4 "vect" } } */
+ 
+diff --git a/gcc/testsuite/gcc.target/i386/pr88531-1b.c b/gcc/testsuite/gcc.target/i386/pr88531-1b.c
+index 812c8a10f..e6df789de 100644
+--- a/gcc/testsuite/gcc.target/i386/pr88531-1b.c
++++ b/gcc/testsuite/gcc.target/i386/pr88531-1b.c
+@@ -1,5 +1,5 @@
+ /* { dg-do compile } */
+-/* { dg-options "-O3 -march=skylake -mfpmath=sse" } */
++/* { dg-options "-O3 -march=skylake -mfpmath=sse -mtune=haswell" } */
+ 
+ #include "pr88531-1a.c"
+ 
+diff --git a/gcc/testsuite/gcc.target/i386/pr88531-1c.c b/gcc/testsuite/gcc.target/i386/pr88531-1c.c
+index 43fc5913e..a093c87c0 100644
+--- a/gcc/testsuite/gcc.target/i386/pr88531-1c.c
++++ b/gcc/testsuite/gcc.target/i386/pr88531-1c.c
+@@ -1,5 +1,5 @@
+ /* { dg-do compile } */
+-/* { dg-options "-O3 -march=skylake-avx512 -mfpmath=sse" } */
++/* { dg-options "-O3 -march=skylake-avx512 -mfpmath=sse -mtune=haswell" } */
+ 
+ #include "pr88531-1a.c"
+ 
+-- 
+2.31.1
+
-- 
cgit v1.2.3