Add _dl_x86_cpu_features to rtld_global

This patch adds _dl_x86_cpu_features to rtld_global in x86 ld.so
and initializes it early before __libc_start_main is called so that
cpu_features is always available when it is used and we can avoid
calling __init_cpu_features in IFUNC selectors.

	* sysdeps/i386/dl-machine.h: Include <cpu-features.c>.
	(dl_platform_init): Call init_cpu_features.
	* sysdeps/i386/dl-procinfo.c (_dl_x86_cpu_features): New.
	* sysdeps/i386/i686/cacheinfo.c
	(DISABLE_PREFERRED_MEMORY_INSTRUCTION): Removed.
	* sysdeps/i386/i686/multiarch/Makefile (aux): Remove init-arch.
	* sysdeps/i386/i686/multiarch/Versions: Removed.
	* sysdeps/i386/i686/multiarch/ifunc-defines.sym (KIND_OFFSET):
	Removed.
	* sysdeps/i386/ldsodefs.h: Include <cpu-features.h>.
	* sysdeps/unix/sysv/linux/x86/Makefile
	(libpthread-sysdep_routines): Remove init-arch.
	* sysdeps/unix/sysv/linux/x86_64/dl-procinfo.c: Include
	<sysdeps/x86_64/dl-procinfo.c> instead of
	sysdeps/generic/dl-procinfo.c>.
	* sysdeps/x86/Makefile [$(subdir) == csu] (gen-as-const-headers):
	Add cpu-features-offsets.sym and rtld-global-offsets.sym.
	[$(subdir) == elf] (sysdep-dl-routines): Add dl-get-cpu-features.
	[$(subdir) == elf] (tests): Add tst-get-cpu-features.
	[$(subdir) == elf] (tests-static): Add
	tst-get-cpu-features-static.
	* sysdeps/x86/Versions: New file.
	* sysdeps/x86/cpu-features-offsets.sym: Likewise.
	* sysdeps/x86/cpu-features.c: Likewise.
	* sysdeps/x86/cpu-features.h: Likewise.
	* sysdeps/x86/dl-get-cpu-features.c: Likewise.
	* sysdeps/x86/libc-start.c: Likewise.
	* sysdeps/x86/rtld-global-offsets.sym: Likewise.
	* sysdeps/x86/tst-get-cpu-features-static.c: Likewise.
	* sysdeps/x86/tst-get-cpu-features.c: Likewise.
	* sysdeps/x86_64/dl-procinfo.c: Likewise.
	* sysdeps/x86_64/cacheinfo.c (__cpuid_count): Removed.
	Assume USE_MULTIARCH is defined and don't check it.
	(is_intel): Replace __cpu_features with GLRO(dl_x86_cpu_features).
	(is_amd): Likewise.
	(max_cpuid): Likewise.
	(intel_check_word): Likewise.
	(__cache_sysconf): Don't call __init_cpu_features.
	(__x86_preferred_memory_instruction): Removed.
	(init_cacheinfo): Don't call __init_cpu_features. Replace
	__cpu_features with GLRO(dl_x86_cpu_features).
	* sysdeps/x86_64/dl-machine.h: <cpu-features.c>.
	(dl_platform_init): Call init_cpu_features.
	* sysdeps/x86_64/ldsodefs.h: Include <cpu-features.h>.
	* sysdeps/x86_64/multiarch/Makefile (aux): Remove init-arch.
	* sysdeps/x86_64/multiarch/Versions: Removed.
	* sysdeps/x86_64/multiarch/cacheinfo.c: Likewise.
	* sysdeps/x86_64/multiarch/init-arch.c: Likewise.
	* sysdeps/x86_64/multiarch/ifunc-defines.sym (KIND_OFFSET):
	Removed.
	* sysdeps/x86_64/multiarch/init-arch.h: Rewrite.

1 files changed, 5 insertions, 189 deletions

diff --git a/sysdeps/x86_64/multiarch/init-arch.h b/sysdeps/x86_64/multiarch/init-arch.h
index cfc6e7049e..2b9988ebc3 100644
--- a/sysdeps/x86_64/multiarch/init-arch.h
+++ b/sysdeps/x86_64/multiarch/init-arch.h
@@ -15,192 +15,8 @@
    License along with the GNU C Library; if not, see
    <http://www.gnu.org/licenses/>.  */
 
-#define bit_Fast_Rep_String		(1 << 0)
-#define bit_Fast_Copy_Backward		(1 << 1)
-#define bit_Slow_BSF			(1 << 2)
-#define bit_Fast_Unaligned_Load		(1 << 4)
-#define bit_Prefer_PMINUB_for_stringop	(1 << 5)
-#define bit_AVX_Usable			(1 << 6)
-#define bit_FMA_Usable			(1 << 7)
-#define bit_FMA4_Usable			(1 << 8)
-#define bit_Slow_SSE4_2			(1 << 9)
-#define bit_AVX2_Usable			(1 << 10)
-#define bit_AVX_Fast_Unaligned_Load	(1 << 11)
-#define bit_AVX512F_Usable		(1 << 12)
-#define bit_AVX512DQ_Usable		(1 << 13)
-
-/* CPUID Feature flags.  */
-
-/* COMMON_CPUID_INDEX_1.  */
-#define bit_SSE2	(1 << 26)
-#define bit_SSSE3	(1 << 9)
-#define bit_SSE4_1	(1 << 19)
-#define bit_SSE4_2	(1 << 20)
-#define bit_OSXSAVE	(1 << 27)
-#define bit_AVX		(1 << 28)
-#define bit_POPCOUNT	(1 << 23)
-#define bit_FMA		(1 << 12)
-#define bit_FMA4	(1 << 16)
-
-/* COMMON_CPUID_INDEX_7.  */
-#define bit_RTM		(1 << 11)
-#define bit_AVX2	(1 << 5)
-#define bit_AVX512F	(1 << 16)
-#define bit_AVX512DQ	(1 << 17)
-
-/* XCR0 Feature flags.  */
-#define bit_XMM_state  (1 << 1)
-#define bit_YMM_state  (2 << 1)
-#define bit_Opmask_state	(1 << 5)
-#define bit_ZMM0_15_state	(1 << 6)
-#define bit_ZMM16_31_state	(1 << 7)
-
-/* The integer bit array index for the first set of internal feature bits.  */
-# define FEATURE_INDEX_1 0
-
-/* The current maximum size of the feature integer bit array.  */
-# define FEATURE_INDEX_MAX 1
-
-#ifdef	__ASSEMBLER__
-
-# include <ifunc-defines.h>
-
-# define index_SSE2	COMMON_CPUID_INDEX_1*CPUID_SIZE+CPUID_EDX_OFFSET
-# define index_SSSE3	COMMON_CPUID_INDEX_1*CPUID_SIZE+CPUID_ECX_OFFSET
-# define index_SSE4_1	COMMON_CPUID_INDEX_1*CPUID_SIZE+CPUID_ECX_OFFSET
-# define index_SSE4_2	COMMON_CPUID_INDEX_1*CPUID_SIZE+CPUID_ECX_OFFSET
-# define index_AVX	COMMON_CPUID_INDEX_1*CPUID_SIZE+CPUID_ECX_OFFSET
-# define index_AVX2	COMMON_CPUID_INDEX_7*CPUID_SIZE+CPUID_EBX_OFFSET
-
-# define index_Fast_Rep_String		FEATURE_INDEX_1*FEATURE_SIZE
-# define index_Fast_Copy_Backward	FEATURE_INDEX_1*FEATURE_SIZE
-# define index_Slow_BSF			FEATURE_INDEX_1*FEATURE_SIZE
-# define index_Fast_Unaligned_Load	FEATURE_INDEX_1*FEATURE_SIZE
-# define index_Prefer_PMINUB_for_stringop FEATURE_INDEX_1*FEATURE_SIZE
-# define index_AVX_Usable		FEATURE_INDEX_1*FEATURE_SIZE
-# define index_FMA_Usable		FEATURE_INDEX_1*FEATURE_SIZE
-# define index_FMA4_Usable		FEATURE_INDEX_1*FEATURE_SIZE
-# define index_Slow_SSE4_2		FEATURE_INDEX_1*FEATURE_SIZE
-# define index_AVX2_Usable		FEATURE_INDEX_1*FEATURE_SIZE
-# define index_AVX_Fast_Unaligned_Load	FEATURE_INDEX_1*FEATURE_SIZE
-# define index_AVX512F_Usable		FEATURE_INDEX_1*FEATURE_SIZE
-# define index_AVX512DQ_Usable		FEATURE_INDEX_1*FEATURE_SIZE
-
-#else	/* __ASSEMBLER__ */
-
-# include <sys/param.h>
-
-enum
-  {
-    COMMON_CPUID_INDEX_1 = 0,
-    COMMON_CPUID_INDEX_7,
-    COMMON_CPUID_INDEX_80000001,	/* for AMD */
-    /* Keep the following line at the end.  */
-    COMMON_CPUID_INDEX_MAX
-  };
-
-extern struct cpu_features
-{
-  enum cpu_features_kind
-    {
-      arch_kind_unknown = 0,
-      arch_kind_intel,
-      arch_kind_amd,
-      arch_kind_other
-    } kind;
-  int max_cpuid;
-  struct cpuid_registers
-  {
-    unsigned int eax;
-    unsigned int ebx;
-    unsigned int ecx;
-    unsigned int edx;
-  } cpuid[COMMON_CPUID_INDEX_MAX];
-  unsigned int family;
-  unsigned int model;
-  unsigned int feature[FEATURE_INDEX_MAX];
-} __cpu_features attribute_hidden;
-
-
-extern void __init_cpu_features (void) attribute_hidden;
-# define INIT_ARCH() \
-  do							\
-    if (__cpu_features.kind == arch_kind_unknown)	\
-      __init_cpu_features ();				\
-  while (0)
-
-/* Used from outside libc.so to get access to the CPU features structure.  */
-extern const struct cpu_features *__get_cpu_features (void)
-     __attribute__ ((const));
-
-# if IS_IN (libc)
-#  define __get_cpu_features()	(&__cpu_features)
-# endif
-
-# define HAS_CPU_FEATURE(idx, reg, bit) \
-  ((__get_cpu_features ()->cpuid[idx].reg & (bit)) != 0)
-
-/* Following are the feature tests used throughout libc.  */
-
-/* CPUID_* evaluates to true if the feature flag is enabled.
-   We always use &__cpu_features because the HAS_CPUID_* macros
-   are called only within __init_cpu_features, where we can't
-   call __get_cpu_features without infinite recursion.  */
-# define HAS_CPUID_FLAG(idx, reg, bit) \
-  (((&__cpu_features)->cpuid[idx].reg & (bit)) != 0)
-
-# define CPUID_OSXSAVE \
-  HAS_CPUID_FLAG (COMMON_CPUID_INDEX_1, ecx, bit_OSXSAVE)
-# define CPUID_AVX \
-  HAS_CPUID_FLAG (COMMON_CPUID_INDEX_1, ecx, bit_AVX)
-# define CPUID_FMA \
-  HAS_CPUID_FLAG (COMMON_CPUID_INDEX_1, ecx, bit_FMA)
-# define CPUID_FMA4 \
-  HAS_CPUID_FLAG (COMMON_CPUID_INDEX_80000001, ecx, bit_FMA4)
-# define CPUID_RTM \
-  HAS_CPUID_FLAG (COMMON_CPUID_INDEX_7, ebx, bit_RTM)
-# define CPUID_AVX2 \
-  HAS_CPUID_FLAG (COMMON_CPUID_INDEX_7, ebx, bit_AVX2)
-# define CPUID_AVX512F \
-  HAS_CPUID_FLAG (COMMON_CPUID_INDEX_7, ebx, bit_AVX512F)
-# define CPUID_AVX512DQ \
-  HAS_CPUID_FLAG (COMMON_CPUID_INDEX_7, ebx, bit_AVX512DQ)
-
-/* HAS_* evaluates to true if we may use the feature at runtime.  */
-# define HAS_SSE2	HAS_CPU_FEATURE (COMMON_CPUID_INDEX_1, edx, bit_SSE2)
-# define HAS_POPCOUNT	HAS_CPU_FEATURE (COMMON_CPUID_INDEX_1, ecx, bit_POPCOUNT)
-# define HAS_SSSE3	HAS_CPU_FEATURE (COMMON_CPUID_INDEX_1, ecx, bit_SSSE3)
-# define HAS_SSE4_1	HAS_CPU_FEATURE (COMMON_CPUID_INDEX_1, ecx, bit_SSE4_1)
-# define HAS_SSE4_2	HAS_CPU_FEATURE (COMMON_CPUID_INDEX_1, ecx, bit_SSE4_2)
-# define HAS_RTM	HAS_CPU_FEATURE (COMMON_CPUID_INDEX_7, ebx, bit_RTM)
-
-# define index_Fast_Rep_String		FEATURE_INDEX_1
-# define index_Fast_Copy_Backward	FEATURE_INDEX_1
-# define index_Slow_BSF			FEATURE_INDEX_1
-# define index_Fast_Unaligned_Load	FEATURE_INDEX_1
-# define index_Prefer_PMINUB_for_stringop FEATURE_INDEX_1
-# define index_AVX_Usable		FEATURE_INDEX_1
-# define index_FMA_Usable		FEATURE_INDEX_1
-# define index_FMA4_Usable		FEATURE_INDEX_1
-# define index_Slow_SSE4_2		FEATURE_INDEX_1
-# define index_AVX2_Usable		FEATURE_INDEX_1
-# define index_AVX_Fast_Unaligned_Load	FEATURE_INDEX_1
-# define index_AVX512F_Usable		FEATURE_INDEX_1
-# define index_AVX512DQ_Usable		FEATURE_INDEX_1
-
-# define HAS_ARCH_FEATURE(name) \
-  ((__get_cpu_features ()->feature[index_##name] & (bit_##name)) != 0)
-
-# define HAS_FAST_REP_STRING		HAS_ARCH_FEATURE (Fast_Rep_String)
-# define HAS_FAST_COPY_BACKWARD		HAS_ARCH_FEATURE (Fast_Copy_Backward)
-# define HAS_SLOW_BSF			HAS_ARCH_FEATURE (Slow_BSF)
-# define HAS_FAST_UNALIGNED_LOAD	HAS_ARCH_FEATURE (Fast_Unaligned_Load)
-# define HAS_AVX			HAS_ARCH_FEATURE (AVX_Usable)
-# define HAS_AVX2			HAS_ARCH_FEATURE (AVX2_Usable)
-# define HAS_AVX512F			HAS_ARCH_FEATURE (AVX512F_Usable)
-# define HAS_AVX512DQ			HAS_ARCH_FEATURE (AVX512DQ_Usable)
-# define HAS_FMA			HAS_ARCH_FEATURE (FMA_Usable)
-# define HAS_FMA4			HAS_ARCH_FEATURE (FMA4_Usable)
-# define HAS_AVX_FAST_UNALIGNED_LOAD	HAS_ARCH_FEATURE (AVX_Fast_Unaligned_Load)
-
-#endif	/* __ASSEMBLER__ */
+#ifdef  __ASSEMBLER__
+# include <cpu-features.h>
+#else
+# include <ldsodefs.h>
+#endif