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.

12 files changed, 18 insertions, 13 deletions

diff --git a/gcc/config/i386/i386-options.cc b/gcc/config/i386/i386-options.cc
index 127ee24..e6ba33c 100644
--- a/gcc/config/i386/i386-options.cc
+++ b/gcc/config/i386/i386-options.cc
@@ -141,6 +141,11 @@ along with GCC; see the file COPYING3.  If not see
 #define m_ARROWLAKE (HOST_WIDE_INT_1U<<PROCESSOR_ARROWLAKE)
 #define m_CORE_ATOM (m_SIERRAFOREST | m_GRANDRIDGE)
 #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_LUJIAZUI (HOST_WIDE_INT_1U<<PROCESSOR_LUJIAZUI)
 
diff --git a/gcc/config/i386/x86-tune.def b/gcc/config/i386/x86-tune.def
index 40e04ec..22d26bb 100644
--- a/gcc/config/i386/x86-tune.def
+++ b/gcc/config/i386/x86-tune.def
@@ -491,7 +491,7 @@ DEF_TUNE (X86_TUNE_AVOID_4BYTE_PREFIXES, "avoid_4byte_prefixes",
    elements.  */
 DEF_TUNE (X86_TUNE_USE_GATHER_2PARTS, "use_gather_2parts",
 	  ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER3 | m_ZNVER4 | m_ALDERLAKE
-	    | m_ARROWLAKE | m_CORE_ATOM | m_GENERIC))
+	    | m_ARROWLAKE | m_CORE_ATOM | m_GENERIC | m_GDS))
 
 /* X86_TUNE_USE_SCATTER_2PARTS: Use scater instructions for vectors with 2
    elements.  */
@@ -502,7 +502,7 @@ DEF_TUNE (X86_TUNE_USE_SCATTER_2PARTS, "use_scatter_2parts",
    elements.  */
 DEF_TUNE (X86_TUNE_USE_GATHER_4PARTS, "use_gather_4parts",
 	  ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER3 | m_ZNVER4 | m_ALDERLAKE
-	    | m_ARROWLAKE | m_CORE_ATOM | m_GENERIC))
+	    | m_ARROWLAKE | m_CORE_ATOM | m_GENERIC | m_GDS))
 
 /* X86_TUNE_USE_SCATTER_4PARTS: Use scater instructions for vectors with 4
    elements.  */
@@ -513,7 +513,7 @@ DEF_TUNE (X86_TUNE_USE_SCATTER_4PARTS, "use_scatter_4parts",
    elements.  */
 DEF_TUNE (X86_TUNE_USE_GATHER, "use_gather",
 	  ~(m_ZNVER1 | m_ZNVER2 | m_ZNVER4 | m_ALDERLAKE | m_ARROWLAKE
-	    | m_CORE_ATOM | m_GENERIC))
+	    | m_CORE_ATOM | 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 ad5ef73..978924b 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 47a95db..0bb40ac 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 -fno-split-loops" } */
+/* { dg-options "-O3 -mavx2 -fno-common -fdump-tree-vect-details  -mtune=haswell -fno-split-loops" } */
 
 #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 06d21bb..d1a2298 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 462e951..d7b0b2b 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 55a28dd..0743918 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 9696008..3a98108 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 6b0c8a8..ac669e0 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 3af568a..14a1083 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 812c8a1..e6df789 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 43fc591..a093c87 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"