From cc67724ae1275b350a8976d97ad763196ac9fe00 Mon Sep 17 00:00:00 2001
From: liuhongt <hongtao.liu@intel.com>
Date: Thu, 10 Aug 2023 11:41:39 +0800
Subject: [PATCH] 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.c (m_GDS): New macro.
	* config/i386/x86-tune.def (X86_TUNE_USE_GATHER): Don't enable
	for m_GDS.

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.

(cherry picked from commit 3064d1f5c48cb6ce1b4133570dd08ecca8abb52d)
---
 gcc/config/i386/i386-options.c                      | 5 +++++
 gcc/config/i386/x86-tune.def                        | 2 +-
 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 +-
 10 files changed, 14 insertions(+), 9 deletions(-)

diff --git a/gcc/config/i386/i386-options.c b/gcc/config/i386/i386-options.c
index d47a5433126f..e3450345b5a1 100644
--- a/gcc/config/i386/i386-options.c
+++ b/gcc/config/i386/i386-options.c
@@ -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 eb057a677508..b390b29843ad 100644
--- a/gcc/config/i386/x86-tune.def
+++ b/gcc/config/i386/x86-tune.def
@@ -442,7 +442,7 @@ DEF_TUNE (X86_TUNE_AVOID_4BYTE_PREFIXES, "avoid_4byte_prefixes",
 
 /* X86_TUNE_USE_GATHER: Use gather instructions.  */
 DEF_TUNE (X86_TUNE_USE_GATHER, "use_gather",
-	  ~(m_ZNVER1 | m_ZNVER2 | m_GENERIC))
+	  ~(m_ZNVER1 | m_ZNVER2 | m_GENERIC | m_GDS))
 
 /* X86_TUNE_AVOID_128FMA_CHAINS: Avoid creating loops with tight 128bit or
    smaller FMA chain.  */
diff --git a/gcc/testsuite/gcc.target/i386/avx2-gather-2.c b/gcc/testsuite/gcc.target/i386/avx2-gather-2.c
index 1a704afd8344..a8bcd0eb3f16 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 -mavx2 -fdump-tree-vect-details -mtune=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 b9119581ae2c..067b251e3936 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 06d21bb01299..d1a2298618ea 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 462e951fdc17..d7b0b2b28cb7 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 55a28dddbf84..07439185ec17 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 9696008855da..3a98108279a4 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 6b0c8a85957f..ac669e048129 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 3af568ab3237..14a1083b6d11 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" } } */
 
-- 
2.47.2