lib/glibc
1
0
Fork 0
mirror of https://sourceware.org/git/glibc.git synced 2025-11-03 20:53:13 +03:00
Code Activity
Files
15e995a8fb94a00d76da03756579ae6ff645b161
glibc/sysdeps/x86/cpu-features.c
H.J. Lu 76d5b2f002 x86: Update Intel Atom processor family optimization 
Enable Intel Silvermont optimization for Intel Goldmont Plus.  Detect more
Intel Airmont processors.  Optimize Intel Tremont like Intel Silvermont
with rep string instructions.
2020-05-21 13:36:54 -07:00

677 lines
21 KiB
C
Raw Blame History

/* Initialize CPU feature data.
This file is part of the GNU C Library.
Copyright (C) 2008-2020 Free Software Foundation, Inc.
The GNU C Library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
The GNU C Library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with the GNU C Library; if not, see
<https://www.gnu.org/licenses/>. */
#include <cpuid.h>
#include <cpu-features.h>
#include <dl-hwcap.h>
#include <libc-pointer-arith.h>
#if HAVE_TUNABLES
# define TUNABLE_NAMESPACE cpu
# include <unistd.h> /* Get STDOUT_FILENO for _dl_printf. */
# include <elf/dl-tunables.h>
extern void TUNABLE_CALLBACK (set_hwcaps) (tunable_val_t *)
attribute_hidden;
# if CET_ENABLED
extern void TUNABLE_CALLBACK (set_x86_ibt) (tunable_val_t *)
attribute_hidden;
extern void TUNABLE_CALLBACK (set_x86_shstk) (tunable_val_t *)
attribute_hidden;
# endif
#endif
#if CET_ENABLED
# include <dl-cet.h>
#endif
static void
get_extended_indices (struct cpu_features *cpu_features)
{
unsigned int eax, ebx, ecx, edx;
__cpuid (0x80000000, eax, ebx, ecx, edx);
if (eax >= 0x80000001)
__cpuid (0x80000001,
cpu_features->cpuid[COMMON_CPUID_INDEX_80000001].eax,
cpu_features->cpuid[COMMON_CPUID_INDEX_80000001].ebx,
cpu_features->cpuid[COMMON_CPUID_INDEX_80000001].ecx,
cpu_features->cpuid[COMMON_CPUID_INDEX_80000001].edx);
if (eax >= 0x80000007)
__cpuid (0x80000007,
cpu_features->cpuid[COMMON_CPUID_INDEX_80000007].eax,
cpu_features->cpuid[COMMON_CPUID_INDEX_80000007].ebx,
cpu_features->cpuid[COMMON_CPUID_INDEX_80000007].ecx,
cpu_features->cpuid[COMMON_CPUID_INDEX_80000007].edx);
if (eax >= 0x80000008)
__cpuid (0x80000008,
cpu_features->cpuid[COMMON_CPUID_INDEX_80000008].eax,
cpu_features->cpuid[COMMON_CPUID_INDEX_80000008].ebx,
cpu_features->cpuid[COMMON_CPUID_INDEX_80000008].ecx,
cpu_features->cpuid[COMMON_CPUID_INDEX_80000008].edx);
}
static void
get_common_indices (struct cpu_features *cpu_features,
unsigned int *family, unsigned int *model,
unsigned int *extended_model, unsigned int *stepping)
{
if (family)
{
unsigned int eax;
__cpuid (1, eax, cpu_features->cpuid[COMMON_CPUID_INDEX_1].ebx,
cpu_features->cpuid[COMMON_CPUID_INDEX_1].ecx,
cpu_features->cpuid[COMMON_CPUID_INDEX_1].edx);
cpu_features->cpuid[COMMON_CPUID_INDEX_1].eax = eax;
*family = (eax >> 8) & 0x0f;
*model = (eax >> 4) & 0x0f;
*extended_model = (eax >> 12) & 0xf0;
*stepping = eax & 0x0f;
if (*family == 0x0f)
{
*family += (eax >> 20) & 0xff;
*model += *extended_model;
}
}
if (cpu_features->basic.max_cpuid >= 7)
__cpuid_count (7, 0,
cpu_features->cpuid[COMMON_CPUID_INDEX_7].eax,
cpu_features->cpuid[COMMON_CPUID_INDEX_7].ebx,
cpu_features->cpuid[COMMON_CPUID_INDEX_7].ecx,
cpu_features->cpuid[COMMON_CPUID_INDEX_7].edx);
if (cpu_features->basic.max_cpuid >= 0xd)
__cpuid_count (0xd, 1,
cpu_features->cpuid[COMMON_CPUID_INDEX_D_ECX_1].eax,
cpu_features->cpuid[COMMON_CPUID_INDEX_D_ECX_1].ebx,
cpu_features->cpuid[COMMON_CPUID_INDEX_D_ECX_1].ecx,
cpu_features->cpuid[COMMON_CPUID_INDEX_D_ECX_1].edx);
/* Can we call xgetbv? */
if (CPU_FEATURES_CPU_P (cpu_features, OSXSAVE))
{
unsigned int xcrlow;
unsigned int xcrhigh;
asm ("xgetbv" : "=a" (xcrlow), "=d" (xcrhigh) : "c" (0));
/* Is YMM and XMM state usable? */
if ((xcrlow & (bit_YMM_state | bit_XMM_state))
== (bit_YMM_state | bit_XMM_state))
{
/* Determine if AVX is usable. */
if (CPU_FEATURES_CPU_P (cpu_features, AVX))
{
cpu_features->feature[index_arch_AVX_Usable]
|= bit_arch_AVX_Usable;
/* The following features depend on AVX being usable. */
/* Determine if AVX2 is usable. */
if (CPU_FEATURES_CPU_P (cpu_features, AVX2))
{
cpu_features->feature[index_arch_AVX2_Usable]
|= bit_arch_AVX2_Usable;
/* Unaligned load with 256-bit AVX registers are faster on
Intel/AMD processors with AVX2. */
cpu_features->feature[index_arch_AVX_Fast_Unaligned_Load]
|= bit_arch_AVX_Fast_Unaligned_Load;
}
/* Determine if FMA is usable. */
if (CPU_FEATURES_CPU_P (cpu_features, FMA))
cpu_features->feature[index_arch_FMA_Usable]
|= bit_arch_FMA_Usable;
/* Determine if VAES is usable. */
if (CPU_FEATURES_CPU_P (cpu_features, VAES))
cpu_features->feature[index_arch_VAES_Usable]
|= bit_arch_VAES_Usable;
/* Determine if VPCLMULQDQ is usable. */
if (CPU_FEATURES_CPU_P (cpu_features, VPCLMULQDQ))
cpu_features->feature[index_arch_VPCLMULQDQ_Usable]
|= bit_arch_VPCLMULQDQ_Usable;
/* Determine if XOP is usable. */
if (CPU_FEATURES_CPU_P (cpu_features, XOP))
cpu_features->feature[index_arch_XOP_Usable]
|= bit_arch_XOP_Usable;
}
/* Check if OPMASK state, upper 256-bit of ZMM0-ZMM15 and
ZMM16-ZMM31 state are enabled. */
if ((xcrlow & (bit_Opmask_state | bit_ZMM0_15_state
| bit_ZMM16_31_state))
== (bit_Opmask_state | bit_ZMM0_15_state | bit_ZMM16_31_state))
{
/* Determine if AVX512F is usable. */
if (CPU_FEATURES_CPU_P (cpu_features, AVX512F))
{
cpu_features->feature[index_arch_AVX512F_Usable]
|= bit_arch_AVX512F_Usable;
/* Determine if AVX512CD is usable. */
if (CPU_FEATURES_CPU_P (cpu_features, AVX512CD))
cpu_features->feature[index_arch_AVX512CD_Usable]
|= bit_arch_AVX512CD_Usable;
/* Determine if AVX512ER is usable. */
if (CPU_FEATURES_CPU_P (cpu_features, AVX512ER))
cpu_features->feature[index_arch_AVX512ER_Usable]
|= bit_arch_AVX512ER_Usable;
/* Determine if AVX512PF is usable. */
if (CPU_FEATURES_CPU_P (cpu_features, AVX512PF))
cpu_features->feature[index_arch_AVX512PF_Usable]
|= bit_arch_AVX512PF_Usable;
/* Determine if AVX512VL is usable. */
if (CPU_FEATURES_CPU_P (cpu_features, AVX512VL))
cpu_features->feature[index_arch_AVX512VL_Usable]
|= bit_arch_AVX512VL_Usable;
/* Determine if AVX512DQ is usable. */
if (CPU_FEATURES_CPU_P (cpu_features, AVX512DQ))
cpu_features->feature[index_arch_AVX512DQ_Usable]
|= bit_arch_AVX512DQ_Usable;
/* Determine if AVX512BW is usable. */
if (CPU_FEATURES_CPU_P (cpu_features, AVX512BW))
cpu_features->feature[index_arch_AVX512BW_Usable]
|= bit_arch_AVX512BW_Usable;
/* Determine if AVX512_4FMAPS is usable. */
if (CPU_FEATURES_CPU_P (cpu_features, AVX512_4FMAPS))
cpu_features->feature[index_arch_AVX512_4FMAPS_Usable]
|= bit_arch_AVX512_4FMAPS_Usable;
/* Determine if AVX512_4VNNIW is usable. */
if (CPU_FEATURES_CPU_P (cpu_features, AVX512_4VNNIW))
cpu_features->feature[index_arch_AVX512_4VNNIW_Usable]
|= bit_arch_AVX512_4VNNIW_Usable;
/* Determine if AVX512_BITALG is usable. */
if (CPU_FEATURES_CPU_P (cpu_features, AVX512_BITALG))
cpu_features->feature[index_arch_AVX512_BITALG_Usable]
|= bit_arch_AVX512_BITALG_Usable;
/* Determine if AVX512_IFMA is usable. */
if (CPU_FEATURES_CPU_P (cpu_features, AVX512_IFMA))
cpu_features->feature[index_arch_AVX512_IFMA_Usable]
|= bit_arch_AVX512_IFMA_Usable;
/* Determine if AVX512_VBMI is usable. */
if (CPU_FEATURES_CPU_P (cpu_features, AVX512_VBMI))
cpu_features->feature[index_arch_AVX512_VBMI_Usable]
|= bit_arch_AVX512_VBMI_Usable;
/* Determine if AVX512_VBMI2 is usable. */
if (CPU_FEATURES_CPU_P (cpu_features, AVX512_VBMI2))
cpu_features->feature[index_arch_AVX512_VBMI2_Usable]
|= bit_arch_AVX512_VBMI2_Usable;
/* Determine if is AVX512_VNNI usable. */
if (CPU_FEATURES_CPU_P (cpu_features, AVX512_VNNI))
cpu_features->feature[index_arch_AVX512_VNNI_Usable]
|= bit_arch_AVX512_VNNI_Usable;
/* Determine if AVX512_VPOPCNTDQ is usable. */
if (CPU_FEATURES_CPU_P (cpu_features, AVX512_VPOPCNTDQ))
cpu_features->feature[index_arch_AVX512_VPOPCNTDQ_Usable]
|= bit_arch_AVX512_VPOPCNTDQ_Usable;
}
}
}
/* For _dl_runtime_resolve, set xsave_state_size to xsave area
size + integer register save size and align it to 64 bytes. */
if (cpu_features->basic.max_cpuid >= 0xd)
{
unsigned int eax, ebx, ecx, edx;
__cpuid_count (0xd, 0, eax, ebx, ecx, edx);
if (ebx != 0)
{
unsigned int xsave_state_full_size
= ALIGN_UP (ebx + STATE_SAVE_OFFSET, 64);
cpu_features->xsave_state_size
= xsave_state_full_size;
cpu_features->xsave_state_full_size
= xsave_state_full_size;
/* Check if XSAVEC is available. */
if (CPU_FEATURES_CPU_P (cpu_features, XSAVEC))
{
unsigned int xstate_comp_offsets[32];
unsigned int xstate_comp_sizes[32];
unsigned int i;
xstate_comp_offsets[0] = 0;
xstate_comp_offsets[1] = 160;
xstate_comp_offsets[2] = 576;
xstate_comp_sizes[0] = 160;
xstate_comp_sizes[1] = 256;
for (i = 2; i < 32; i++)
{
if ((STATE_SAVE_MASK & (1 << i)) != 0)
{
__cpuid_count (0xd, i, eax, ebx, ecx, edx);
xstate_comp_sizes[i] = eax;
}
else
{
ecx = 0;
xstate_comp_sizes[i] = 0;
}
if (i > 2)
{
xstate_comp_offsets[i]
= (xstate_comp_offsets[i - 1]
+ xstate_comp_sizes[i -1]);
if ((ecx & (1 << 1)) != 0)
xstate_comp_offsets[i]
= ALIGN_UP (xstate_comp_offsets[i], 64);
}
}
/* Use XSAVEC. */
unsigned int size
= xstate_comp_offsets[31] + xstate_comp_sizes[31];
if (size)
{
cpu_features->xsave_state_size
= ALIGN_UP (size + STATE_SAVE_OFFSET, 64);
cpu_features->feature[index_arch_XSAVEC_Usable]
|= bit_arch_XSAVEC_Usable;
}
}
}
}
}
}
_Static_assert (((index_arch_Fast_Unaligned_Load
== index_arch_Fast_Unaligned_Copy)
&& (index_arch_Fast_Unaligned_Load
== index_arch_Prefer_PMINUB_for_stringop)
&& (index_arch_Fast_Unaligned_Load
== index_arch_Slow_SSE4_2)
&& (index_arch_Fast_Unaligned_Load
== index_arch_Fast_Rep_String)
&& (index_arch_Fast_Unaligned_Load
== index_arch_Fast_Copy_Backward)),
"Incorrect index_arch_Fast_Unaligned_Load");
static inline void
init_cpu_features (struct cpu_features *cpu_features)
{
unsigned int ebx, ecx, edx;
unsigned int family = 0;
unsigned int model = 0;
unsigned int stepping = 0;
enum cpu_features_kind kind;
#if !HAS_CPUID
if (__get_cpuid_max (0, 0) == 0)
{
kind = arch_kind_other;
goto no_cpuid;
}
#endif
__cpuid (0, cpu_features->basic.max_cpuid, ebx, ecx, edx);
/* This spells out "GenuineIntel". */
if (ebx == 0x756e6547 && ecx == 0x6c65746e && edx == 0x49656e69)
{
unsigned int extended_model;
kind = arch_kind_intel;
get_common_indices (cpu_features, &family, &model, &extended_model,
&stepping);
get_extended_indices (cpu_features);
if (family == 0x06)
{
model += extended_model;
switch (model)
{
case 0x1c:
case 0x26:
/* BSF is slow on Atom. */
cpu_features->feature[index_arch_Slow_BSF]
|= bit_arch_Slow_BSF;
break;
case 0x57:
/* Knights Landing. Enable Silvermont optimizations. */
case 0x7a:
/* Unaligned load versions are faster than SSSE3
on Goldmont Plus. */
case 0x5c:
case 0x5f:
/* Unaligned load versions are faster than SSSE3
on Goldmont. */
case 0x4c:
case 0x5a:
case 0x75:
/* Airmont is a die shrink of Silvermont. */
case 0x37:
case 0x4a:
case 0x4d:
case 0x5d:
/* Unaligned load versions are faster than SSSE3
on Silvermont. */
cpu_features->feature[index_arch_Fast_Unaligned_Load]
|= (bit_arch_Fast_Unaligned_Load
| bit_arch_Fast_Unaligned_Copy
| bit_arch_Prefer_PMINUB_for_stringop
| bit_arch_Slow_SSE4_2);
break;
case 0x86:
case 0x96:
case 0x9c:
/* Enable rep string instructions, unaligned load, unaligned
copy, pminub and avoid SSE 4.2 on Tremont. */
cpu_features->feature[index_arch_Fast_Rep_String]
|= (bit_arch_Fast_Rep_String
| bit_arch_Fast_Unaligned_Load
| bit_arch_Fast_Unaligned_Copy
| bit_arch_Prefer_PMINUB_for_stringop
| bit_arch_Slow_SSE4_2);
break;
default:
/* Unknown family 0x06 processors. Assuming this is one
of Core i3/i5/i7 processors if AVX is available. */
if (!CPU_FEATURES_CPU_P (cpu_features, AVX))
break;
/* Fall through. */
case 0x1a:
case 0x1e:
case 0x1f:
case 0x25:
case 0x2c:
case 0x2e:
case 0x2f:
/* Rep string instructions, unaligned load, unaligned copy,
and pminub are fast on Intel Core i3, i5 and i7. */
cpu_features->feature[index_arch_Fast_Rep_String]
|= (bit_arch_Fast_Rep_String
| bit_arch_Fast_Unaligned_Load
| bit_arch_Fast_Unaligned_Copy
| bit_arch_Prefer_PMINUB_for_stringop);
break;
}
/* Disable TSX on some Haswell processors to avoid TSX on kernels that
weren't updated with the latest microcode package (which disables
broken feature by default). */
switch (model)
{
case 0x3f:
/* Xeon E7 v3 with stepping >= 4 has working TSX. */
if (stepping >= 4)
break;
/* Fall through. */
case 0x3c:
case 0x45:
case 0x46:
/* Disable Intel TSX on Haswell processors (except Xeon E7 v3
with stepping >= 4) to avoid TSX on kernels that weren't
updated with the latest microcode package (which disables
broken feature by default). */
cpu_features->cpuid[index_cpu_RTM].reg_RTM &= ~bit_cpu_RTM;
break;
}
}
/* Since AVX512ER is unique to Xeon Phi, set Prefer_No_VZEROUPPER
if AVX512ER is available. Don't use AVX512 to avoid lower CPU
frequency if AVX512ER isn't available. */
if (CPU_FEATURES_CPU_P (cpu_features, AVX512ER))
cpu_features->feature[index_arch_Prefer_No_VZEROUPPER]
|= bit_arch_Prefer_No_VZEROUPPER;
else
cpu_features->feature[index_arch_Prefer_No_AVX512]
|= bit_arch_Prefer_No_AVX512;
}
/* This spells out "AuthenticAMD" or "HygonGenuine". */
else if ((ebx == 0x68747541 && ecx == 0x444d4163 && edx == 0x69746e65)
|| (ebx == 0x6f677948 && ecx == 0x656e6975 && edx == 0x6e65476e))
{
unsigned int extended_model;
kind = arch_kind_amd;
get_common_indices (cpu_features, &family, &model, &extended_model,
&stepping);
get_extended_indices (cpu_features);
ecx = cpu_features->cpuid[COMMON_CPUID_INDEX_1].ecx;
if (HAS_ARCH_FEATURE (AVX_Usable))
{
/* Since the FMA4 bit is in COMMON_CPUID_INDEX_80000001 and
FMA4 requires AVX, determine if FMA4 is usable here. */
if (CPU_FEATURES_CPU_P (cpu_features, FMA4))
cpu_features->feature[index_arch_FMA4_Usable]
|= bit_arch_FMA4_Usable;
}
if (family == 0x15)
{
/* "Excavator" */
if (model >= 0x60 && model <= 0x7f)
{
cpu_features->feature[index_arch_Fast_Unaligned_Load]
|= (bit_arch_Fast_Unaligned_Load
| bit_arch_Fast_Copy_Backward);
/* Unaligned AVX loads are slower.*/
cpu_features->feature[index_arch_AVX_Fast_Unaligned_Load]
&= ~bit_arch_AVX_Fast_Unaligned_Load;
}
}
}
/* This spells out "CentaurHauls" or " Shanghai ". */
else if ((ebx == 0x746e6543 && ecx == 0x736c7561 && edx == 0x48727561)
|| (ebx == 0x68532020 && ecx == 0x20206961 && edx == 0x68676e61))
{
unsigned int extended_model, stepping;
kind = arch_kind_zhaoxin;
get_common_indices (cpu_features, &family, &model, &extended_model,
&stepping);
get_extended_indices (cpu_features);
model += extended_model;
if (family == 0x6)
{
if (model == 0xf || model == 0x19)
{
cpu_features->feature[index_arch_AVX_Usable]
&= (~bit_arch_AVX_Usable
& ~bit_arch_AVX2_Usable);
cpu_features->feature[index_arch_Slow_SSE4_2]
|= (bit_arch_Slow_SSE4_2);
cpu_features->feature[index_arch_AVX_Fast_Unaligned_Load]
&= ~bit_arch_AVX_Fast_Unaligned_Load;
}
}
else if (family == 0x7)
{
if (model == 0x1b)
{
cpu_features->feature[index_arch_AVX_Usable]
&= (~bit_arch_AVX_Usable
& ~bit_arch_AVX2_Usable);
cpu_features->feature[index_arch_Slow_SSE4_2]
|= bit_arch_Slow_SSE4_2;
cpu_features->feature[index_arch_AVX_Fast_Unaligned_Load]
&= ~bit_arch_AVX_Fast_Unaligned_Load;
}
else if (model == 0x3b)
{
cpu_features->feature[index_arch_AVX_Usable]
&= (~bit_arch_AVX_Usable
& ~bit_arch_AVX2_Usable);
cpu_features->feature[index_arch_AVX_Fast_Unaligned_Load]
&= ~bit_arch_AVX_Fast_Unaligned_Load;
}
}
}
else
{
kind = arch_kind_other;
get_common_indices (cpu_features, NULL, NULL, NULL, NULL);
}
/* Support i586 if CX8 is available. */
if (CPU_FEATURES_CPU_P (cpu_features, CX8))
cpu_features->feature[index_arch_I586] |= bit_arch_I586;
/* Support i686 if CMOV is available. */
if (CPU_FEATURES_CPU_P (cpu_features, CMOV))
cpu_features->feature[index_arch_I686] |= bit_arch_I686;
#if !HAS_CPUID
no_cpuid:
#endif
cpu_features->basic.kind = kind;
cpu_features->basic.family = family;
cpu_features->basic.model = model;
cpu_features->basic.stepping = stepping;
#if HAVE_TUNABLES
TUNABLE_GET (hwcaps, tunable_val_t *, TUNABLE_CALLBACK (set_hwcaps));
cpu_features->non_temporal_threshold
= TUNABLE_GET (x86_non_temporal_threshold, long int, NULL);
cpu_features->data_cache_size
= TUNABLE_GET (x86_data_cache_size, long int, NULL);
cpu_features->shared_cache_size
= TUNABLE_GET (x86_shared_cache_size, long int, NULL);
#endif
/* Reuse dl_platform, dl_hwcap and dl_hwcap_mask for x86. */
#if !HAVE_TUNABLES && defined SHARED
/* The glibc.cpu.hwcap_mask tunable is initialized already, so no need to do
this. */
GLRO(dl_hwcap_mask) = HWCAP_IMPORTANT;
#endif
#ifdef __x86_64__
GLRO(dl_hwcap) = HWCAP_X86_64;
if (cpu_features->basic.kind == arch_kind_intel)
{
const char *platform = NULL;
if (CPU_FEATURES_ARCH_P (cpu_features, AVX512F_Usable)
&& CPU_FEATURES_CPU_P (cpu_features, AVX512CD))
{
if (CPU_FEATURES_CPU_P (cpu_features, AVX512ER))
{
if (CPU_FEATURES_CPU_P (cpu_features, AVX512PF))
platform = "xeon_phi";
}
else
{
if (CPU_FEATURES_CPU_P (cpu_features, AVX512BW)
&& CPU_FEATURES_CPU_P (cpu_features, AVX512DQ)
&& CPU_FEATURES_CPU_P (cpu_features, AVX512VL))
GLRO(dl_hwcap) |= HWCAP_X86_AVX512_1;
}
}
if (platform == NULL
&& CPU_FEATURES_ARCH_P (cpu_features, AVX2_Usable)
&& CPU_FEATURES_ARCH_P (cpu_features, FMA_Usable)
&& CPU_FEATURES_CPU_P (cpu_features, BMI1)
&& CPU_FEATURES_CPU_P (cpu_features, BMI2)
&& CPU_FEATURES_CPU_P (cpu_features, LZCNT)
&& CPU_FEATURES_CPU_P (cpu_features, MOVBE)
&& CPU_FEATURES_CPU_P (cpu_features, POPCNT))
platform = "haswell";
if (platform != NULL)
GLRO(dl_platform) = platform;
}
#else
GLRO(dl_hwcap) = 0;
if (CPU_FEATURES_CPU_P (cpu_features, SSE2))
GLRO(dl_hwcap) |= HWCAP_X86_SSE2;
if (CPU_FEATURES_ARCH_P (cpu_features, I686))
GLRO(dl_platform) = "i686";
else if (CPU_FEATURES_ARCH_P (cpu_features, I586))
GLRO(dl_platform) = "i586";
#endif
#if CET_ENABLED
# if HAVE_TUNABLES
TUNABLE_GET (x86_ibt, tunable_val_t *,
TUNABLE_CALLBACK (set_x86_ibt));
TUNABLE_GET (x86_shstk, tunable_val_t *,
TUNABLE_CALLBACK (set_x86_shstk));
# endif
/* Check CET status. */
unsigned int cet_status = get_cet_status ();
if (cet_status)
{
GL(dl_x86_feature_1) = cet_status;
# ifndef SHARED
/* Check if IBT and SHSTK are enabled by kernel. */
if ((cet_status & GNU_PROPERTY_X86_FEATURE_1_IBT)
|| (cet_status & GNU_PROPERTY_X86_FEATURE_1_SHSTK))
{
/* Disable IBT and/or SHSTK if they are enabled by kernel, but
disabled by environment variable:
GLIBC_TUNABLES=glibc.cpu.hwcaps=-IBT,-SHSTK
*/
unsigned int cet_feature = 0;
if (!HAS_CPU_FEATURE (IBT))
cet_feature |= GNU_PROPERTY_X86_FEATURE_1_IBT;
if (!HAS_CPU_FEATURE (SHSTK))
cet_feature |= GNU_PROPERTY_X86_FEATURE_1_SHSTK;
if (cet_feature)
{
int res = dl_cet_disable_cet (cet_feature);
/* Clear the disabled bits in dl_x86_feature_1. */
if (res == 0)
GL(dl_x86_feature_1) &= ~cet_feature;
}
/* Lock CET if IBT or SHSTK is enabled in executable. Don't
lock CET if IBT or SHSTK is enabled permissively. */
if (GL(dl_x86_feature_control).ibt != cet_permissive
&& GL(dl_x86_feature_control).shstk != cet_permissive)
dl_cet_lock_cet ();
}
# endif
}
#endif
}
View Git Blame Copy Permalink